chore: add .gitignore
This commit is contained in:
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "deepseek-v3.2:cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-19T22:06:42.892978",
|
||||
"run_id": "20260219_220642_baseline_existing",
|
||||
"dossiers": [
|
||||
"116_23065570",
|
||||
"132_23080179",
|
||||
"134_23050890",
|
||||
"143_23096917",
|
||||
"145_23057452",
|
||||
"153_23102610",
|
||||
"170_23077016",
|
||||
"176_23124187",
|
||||
"17_23100690",
|
||||
"183_23087212"
|
||||
],
|
||||
"args": {
|
||||
"n": 10,
|
||||
"gold_standard": true,
|
||||
"clean": false,
|
||||
"no_reprocess": true,
|
||||
"seed": 42,
|
||||
"label": "baseline_existing"
|
||||
}
|
||||
}
|
||||
799
output/benchmarks/20260219_220642_baseline_existing/metrics.json
Normal file
799
output/benchmarks/20260219_220642_baseline_existing/metrics.json
Normal file
@@ -0,0 +1,799 @@
|
||||
{
|
||||
"aggregate": {
|
||||
"n_total": 10,
|
||||
"n_success": 10,
|
||||
"n_failed": 0,
|
||||
"dp": {
|
||||
"has_code_rate": 0.9,
|
||||
"valid_code_rate": 0.9,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 1,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0
|
||||
},
|
||||
"das": {
|
||||
"total": 150,
|
||||
"mean_per_dossier": 15.0,
|
||||
"with_code": 150,
|
||||
"valid": 150,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 105,
|
||||
"medium": 38,
|
||||
"low": 7
|
||||
},
|
||||
"confidence_high_rate": 0.7,
|
||||
"downgraded": 2,
|
||||
"downgrade_rate": 0.013
|
||||
},
|
||||
"veto": {
|
||||
"verdicts": {
|
||||
"NO_REPORT": 8,
|
||||
"NEED_INFO": 2
|
||||
},
|
||||
"hard_total": 0,
|
||||
"dossiers_with_hard": 0
|
||||
},
|
||||
"ghm": {
|
||||
"estimated_rate": 0.5
|
||||
},
|
||||
"cpam": {
|
||||
"controls_total": 10,
|
||||
"with_response": 10
|
||||
},
|
||||
"timing": {
|
||||
"mean_s": 0.0,
|
||||
"median_s": 0.0,
|
||||
"p90_s": 0.0,
|
||||
"total_s": 0.0
|
||||
},
|
||||
"invalid_codes": [],
|
||||
"invalid_codes_count": 0
|
||||
},
|
||||
"per_dossier": [
|
||||
{
|
||||
"dossier_id": "116_23065570",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Insuffisance rénale aig",
|
||||
"code_suggestion": "N17.8",
|
||||
"code_final": "N17.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 8,
|
||||
"with_code": 8,
|
||||
"no_code": 0,
|
||||
"valid": 8,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"K59.0",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"N21.0",
|
||||
"N21.1",
|
||||
"N32.8",
|
||||
"N40.0",
|
||||
"Z01.4"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "11",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 0,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "132_23080179",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Adénopathie",
|
||||
"code_suggestion": "R59.0",
|
||||
"code_final": "R59.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 22,
|
||||
"with_code": 22,
|
||||
"no_code": 0,
|
||||
"valid": 22,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 11,
|
||||
"medium": 11,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.045,
|
||||
"codes_uniques": [
|
||||
"C83.3",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E66.84",
|
||||
"E78.5",
|
||||
"E86",
|
||||
"E87.6",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"J90",
|
||||
"M48.5",
|
||||
"M54.2",
|
||||
"M54.3",
|
||||
"M54.8",
|
||||
"M89.5",
|
||||
"R06.0",
|
||||
"R11",
|
||||
"R13",
|
||||
"R93.1",
|
||||
"R93.8",
|
||||
"T98.1",
|
||||
"Z51.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 56,
|
||||
"issues_count": 10,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 7,
|
||||
"anomalies": 3
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "134_23050890",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Epispadia",
|
||||
"code_suggestion": "Q54.2",
|
||||
"code_final": "Q54.2",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 13,
|
||||
"medium": 1,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"A49.8",
|
||||
"D55.9",
|
||||
"E66.05",
|
||||
"E66.99",
|
||||
"F32.30",
|
||||
"I95.1",
|
||||
"M16",
|
||||
"M54.2",
|
||||
"Q64.0",
|
||||
"Q64.1",
|
||||
"Q65.8",
|
||||
"Q71.3",
|
||||
"Z00.8",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": false,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 8
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 3,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "143_23096917",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Appendicite aigue",
|
||||
"code_suggestion": "K35.8",
|
||||
"code_final": "K35.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 10,
|
||||
"medium": 3,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"A04.4",
|
||||
"C10.4",
|
||||
"D69.6",
|
||||
"F07.0",
|
||||
"G44",
|
||||
"K35.3",
|
||||
"K35.8",
|
||||
"K65.9",
|
||||
"K71.2",
|
||||
"K74.2",
|
||||
"L24.4",
|
||||
"N17.8",
|
||||
"R18",
|
||||
"R19.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": false,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 8
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 10,
|
||||
"anomalies": 5
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "145_23057452",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Examen général",
|
||||
"code_suggestion": "Z00.0",
|
||||
"code_final": "Z00.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 12,
|
||||
"with_code": 12,
|
||||
"no_code": 0,
|
||||
"valid": 12,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 9,
|
||||
"medium": 3,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"G82.10",
|
||||
"G82.11",
|
||||
"G82.19",
|
||||
"G91.2",
|
||||
"H40",
|
||||
"I10",
|
||||
"M10",
|
||||
"M54.2",
|
||||
"N18.2",
|
||||
"N19",
|
||||
"R49",
|
||||
"R51"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 0
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "153_23102610",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Cétonurie",
|
||||
"code_suggestion": "R82.4",
|
||||
"code_final": "R82.4",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 17,
|
||||
"with_code": 17,
|
||||
"no_code": 0,
|
||||
"valid": 17,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 11,
|
||||
"medium": 3,
|
||||
"low": 3
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"A49.1",
|
||||
"A49.8",
|
||||
"C94",
|
||||
"E11.9",
|
||||
"E29.1",
|
||||
"E78.5",
|
||||
"F07.0",
|
||||
"I12.0",
|
||||
"K42.9",
|
||||
"K72.1",
|
||||
"L83",
|
||||
"N18.3",
|
||||
"N39.0",
|
||||
"R59.9",
|
||||
"R63.4",
|
||||
"Y88.0",
|
||||
"Z03.8"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": false,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 8
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 8,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "170_23077016",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "À 38",
|
||||
"code_suggestion": "S38.10",
|
||||
"code_final": "S38.10",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"A49.8",
|
||||
"I12.0",
|
||||
"K59.0",
|
||||
"M06.0",
|
||||
"M62.5",
|
||||
"R23.1",
|
||||
"R53",
|
||||
"R62",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": false,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 8
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "176_23124187",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Hta",
|
||||
"code_suggestion": "I10",
|
||||
"code_final": "I10",
|
||||
"confidence": "low",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 25,
|
||||
"with_code": 25,
|
||||
"no_code": 0,
|
||||
"valid": 25,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 18,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"C34.9",
|
||||
"D55.9",
|
||||
"D69.6",
|
||||
"E78.5",
|
||||
"E83.50",
|
||||
"E87.6",
|
||||
"G00",
|
||||
"I12.0",
|
||||
"I25.1",
|
||||
"J18.9",
|
||||
"J47",
|
||||
"J90",
|
||||
"K74.2",
|
||||
"M19.9",
|
||||
"M25.5",
|
||||
"M62.5",
|
||||
"N18.3",
|
||||
"Q91.3",
|
||||
"R05",
|
||||
"R45.4",
|
||||
"R59.9",
|
||||
"R65.1",
|
||||
"R68.3",
|
||||
"R73.0",
|
||||
"T65.2"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": false,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 8
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 9,
|
||||
"anomalies": 5
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "17_23100690",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Pancréatite aiguë",
|
||||
"code_suggestion": "K85.9",
|
||||
"code_final": "K85.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 20,
|
||||
"with_code": 20,
|
||||
"no_code": 0,
|
||||
"valid": 20,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 15,
|
||||
"medium": 5,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.05,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"E66.04",
|
||||
"E78.5",
|
||||
"E87.8",
|
||||
"F10.1",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"K66.0",
|
||||
"K71.8",
|
||||
"K80.0",
|
||||
"K80.1",
|
||||
"K80.2",
|
||||
"K83.0",
|
||||
"N19",
|
||||
"N85.7",
|
||||
"R19",
|
||||
"R52.10",
|
||||
"R73.9",
|
||||
"R82.4",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 20,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 53,
|
||||
"issues_count": 11,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "07",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 19,
|
||||
"anomalies": 16
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "183_23087212",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E66.04",
|
||||
"I10",
|
||||
"N10",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"R35",
|
||||
"T83.1",
|
||||
"T83.5",
|
||||
"Z43.3"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 0,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NO_REPORT",
|
||||
"score": 0,
|
||||
"issues_count": 0,
|
||||
"hard_count": 0,
|
||||
"top_issues": []
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 12
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260219_220642_baseline_existing
|
||||
==================================================================
|
||||
Date : 2026-02-19T22:06:42.892978
|
||||
Modèles : coding=gemma3:27b-cloud cpam=deepseek-v3.2:cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 10/10 traités (0 échecs)
|
||||
Durée : 0s (0.0s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ██████████████████░░ 90.0%
|
||||
Code CIM-10 valide : ██████████████████░░ 90.0%
|
||||
Confiance high : 7/10 medium: 1 low: 1
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 150 (moy 15.0/dossier)
|
||||
Avec code : 150/150
|
||||
Codes valides : ████████████████████ 100.0%
|
||||
Confiance : high=105 medium=38 low=7
|
||||
Confiance high : ██████████████░░░░░░ 70.0%
|
||||
Downgrades : 2 (1.3%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NO_REPORT : 8
|
||||
NEED_INFO : 2
|
||||
Issues HARD : 0 (dans 0 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ██████████░░░░░░░░░░ 50.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 10
|
||||
Avec réponse : 10
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 0.0s
|
||||
Médian : 0.0s
|
||||
P90 : 0.0s
|
||||
Total : 0s
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
116_23065570 N17.8✓ 8 100% NO_REPORT 0s
|
||||
132_23080179 R59.0✓ 22 100% NEED_INFO 0s
|
||||
134_23050890 Q54.2✓ 14 100% NO_REPORT 0s
|
||||
143_23096917 K35.8✓ 14 100% NO_REPORT 0s
|
||||
145_23057452 Z00.0✓ 12 100% NO_REPORT 0s
|
||||
153_23102610 R82.4✓ 17 100% NO_REPORT 0s
|
||||
170_23077016 S38.10✓ 9 100% NO_REPORT 0s
|
||||
176_23124187 I10✓ 25 100% NO_REPORT 0s
|
||||
17_23100690 K85.9✓ 20 100% NEED_INFO 0s
|
||||
183_23087212 -✗ 9 100% NO_REPORT 0s
|
||||
|
||||
==================================================================
|
||||
32
output/benchmarks/20260219_220651_multimodel_v1/config.json
Normal file
32
output/benchmarks/20260219_220651_multimodel_v1/config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "deepseek-v3.2:cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-19T22:06:51.602389",
|
||||
"run_id": "20260219_220651_multimodel_v1",
|
||||
"dossiers": [
|
||||
"116_23065570",
|
||||
"132_23080179",
|
||||
"134_23050890",
|
||||
"143_23096917",
|
||||
"145_23057452",
|
||||
"153_23102610",
|
||||
"170_23077016",
|
||||
"176_23124187",
|
||||
"17_23100690",
|
||||
"183_23087212"
|
||||
],
|
||||
"args": {
|
||||
"n": 10,
|
||||
"gold_standard": true,
|
||||
"clean": true,
|
||||
"no_reprocess": false,
|
||||
"seed": 42,
|
||||
"label": "multimodel_v1"
|
||||
}
|
||||
}
|
||||
843
output/benchmarks/20260219_220651_multimodel_v1/metrics.json
Normal file
843
output/benchmarks/20260219_220651_multimodel_v1/metrics.json
Normal file
@@ -0,0 +1,843 @@
|
||||
{
|
||||
"aggregate": {
|
||||
"n_total": 10,
|
||||
"n_success": 10,
|
||||
"n_failed": 0,
|
||||
"dp": {
|
||||
"has_code_rate": 0.7,
|
||||
"valid_code_rate": 0.7,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 1,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0
|
||||
},
|
||||
"das": {
|
||||
"total": 149,
|
||||
"mean_per_dossier": 14.9,
|
||||
"with_code": 149,
|
||||
"valid": 149,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 71,
|
||||
"medium": 60,
|
||||
"low": 18
|
||||
},
|
||||
"confidence_high_rate": 0.477,
|
||||
"downgraded": 4,
|
||||
"downgrade_rate": 0.027
|
||||
},
|
||||
"veto": {
|
||||
"verdicts": {
|
||||
"NEED_INFO": 8,
|
||||
"PASS": 2
|
||||
},
|
||||
"hard_total": 0,
|
||||
"dossiers_with_hard": 0
|
||||
},
|
||||
"ghm": {
|
||||
"estimated_rate": 1.0
|
||||
},
|
||||
"cpam": {
|
||||
"controls_total": 10,
|
||||
"with_response": 2
|
||||
},
|
||||
"timing": {
|
||||
"mean_s": 482.2,
|
||||
"median_s": 477.8,
|
||||
"p90_s": 552.8,
|
||||
"total_s": 4822.0
|
||||
},
|
||||
"invalid_codes": [],
|
||||
"invalid_codes_count": 0
|
||||
},
|
||||
"per_dossier": [
|
||||
{
|
||||
"dossier_id": "116_23065570",
|
||||
"processing_time_s": 439.3,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Insuffisance rénale aig",
|
||||
"code_suggestion": "N17.9",
|
||||
"code_final": "N17.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 3,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"K59.0",
|
||||
"N13.9",
|
||||
"N19",
|
||||
"N21.0",
|
||||
"N30.0",
|
||||
"N40.0",
|
||||
"N42.0",
|
||||
"T83.5",
|
||||
"Z01.4"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "11",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 0,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "132_23080179",
|
||||
"processing_time_s": 499.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Adénopathie",
|
||||
"code_suggestion": "R59.0",
|
||||
"code_final": "R59.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 22,
|
||||
"with_code": 22,
|
||||
"no_code": 0,
|
||||
"valid": 22,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 13,
|
||||
"medium": 9,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.045,
|
||||
"codes_uniques": [
|
||||
"C83.3",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E66.84",
|
||||
"E78.5",
|
||||
"E86",
|
||||
"E87.6",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"J90",
|
||||
"M48.5",
|
||||
"M54.2",
|
||||
"M54.3",
|
||||
"M54.8",
|
||||
"M89.5",
|
||||
"R06.0",
|
||||
"R11",
|
||||
"R13",
|
||||
"R93.1",
|
||||
"R93.8",
|
||||
"T98.1",
|
||||
"Z51.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 59,
|
||||
"issues_count": 9,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 12,
|
||||
"anomalies": 7
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "134_23050890",
|
||||
"processing_time_s": 475.4,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Epispadia",
|
||||
"code_suggestion": "Q64.0",
|
||||
"code_final": "Q64.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 13,
|
||||
"with_code": 13,
|
||||
"no_code": 0,
|
||||
"valid": 13,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 6,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"D50",
|
||||
"E66.05",
|
||||
"E66.9",
|
||||
"F32.9",
|
||||
"I95.1",
|
||||
"J18.9",
|
||||
"M16.9",
|
||||
"M54.2",
|
||||
"Q05.9",
|
||||
"Q65.0",
|
||||
"Q65.9",
|
||||
"S73.1",
|
||||
"Z04.802"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "15",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "143_23096917",
|
||||
"processing_time_s": 504.1,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Appendicite aigue",
|
||||
"code_suggestion": "K35.8",
|
||||
"code_final": "K35.8",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 10,
|
||||
"medium": 4,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"B96.2",
|
||||
"C69.4",
|
||||
"D69.6",
|
||||
"D72.8",
|
||||
"E87.6",
|
||||
"F06.4",
|
||||
"G44.8",
|
||||
"K65.9",
|
||||
"K74.0",
|
||||
"K74.3",
|
||||
"L27.0",
|
||||
"N17.9",
|
||||
"R18",
|
||||
"T80.8"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-15"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "06",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 9
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 13,
|
||||
"anomalies": 6
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "145_23057452",
|
||||
"processing_time_s": 429.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Examen général",
|
||||
"code_suggestion": "Z00.8",
|
||||
"code_final": "Z00.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 12,
|
||||
"with_code": 12,
|
||||
"no_code": 0,
|
||||
"valid": 12,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 4,
|
||||
"low": 3
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E11.8",
|
||||
"F43.28",
|
||||
"G44.8",
|
||||
"G91.2",
|
||||
"G91.9",
|
||||
"H40.9",
|
||||
"I10",
|
||||
"M10.9",
|
||||
"M54.2",
|
||||
"N18.3",
|
||||
"N19",
|
||||
"O86.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 12,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 72,
|
||||
"issues_count": 7,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "153_23102610",
|
||||
"processing_time_s": 547.2,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 15,
|
||||
"with_code": 15,
|
||||
"no_code": 0,
|
||||
"valid": 15,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 6,
|
||||
"low": 3
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"C49",
|
||||
"E11.9",
|
||||
"E23.0",
|
||||
"E78.5",
|
||||
"F06.4",
|
||||
"H36.0",
|
||||
"K42.9",
|
||||
"K71",
|
||||
"L83",
|
||||
"N19",
|
||||
"N39.0",
|
||||
"R59.9",
|
||||
"R63.4",
|
||||
"T83.5",
|
||||
"T88.7"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 15,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 58,
|
||||
"issues_count": 7,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 11
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 11,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "170_23077016",
|
||||
"processing_time_s": 552.8,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 11,
|
||||
"with_code": 11,
|
||||
"no_code": 0,
|
||||
"valid": 11,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 4,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.091,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"D72.8",
|
||||
"I97.8",
|
||||
"J18.9",
|
||||
"K59.0",
|
||||
"M05.9",
|
||||
"N19",
|
||||
"R23.1",
|
||||
"R50.9",
|
||||
"R52.2",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 11,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "176_23124187",
|
||||
"processing_time_s": 480.1,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Hta",
|
||||
"code_suggestion": "I10",
|
||||
"code_final": "I10",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 24,
|
||||
"with_code": 24,
|
||||
"no_code": 0,
|
||||
"valid": 24,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 9,
|
||||
"medium": 10,
|
||||
"low": 5
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.042,
|
||||
"codes_uniques": [
|
||||
"A41.9",
|
||||
"C31.1",
|
||||
"C34.9",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"D72.1",
|
||||
"E78.5",
|
||||
"E83.5",
|
||||
"E87.6",
|
||||
"G00",
|
||||
"I11.0",
|
||||
"J18.9",
|
||||
"J47",
|
||||
"J90",
|
||||
"K74.0",
|
||||
"M25.5",
|
||||
"N19",
|
||||
"R05",
|
||||
"R45.4",
|
||||
"R59.9",
|
||||
"R68.3",
|
||||
"R93.8",
|
||||
"Z72.0",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 23,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 68,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "05",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 16,
|
||||
"anomalies": 9
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "17_23100690",
|
||||
"processing_time_s": 429.6,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Pancréatite aiguë",
|
||||
"code_suggestion": "K85.9",
|
||||
"code_final": "K85.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 20,
|
||||
"with_code": 20,
|
||||
"no_code": 0,
|
||||
"valid": 20,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 8,
|
||||
"medium": 10,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.05,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"E66.04",
|
||||
"E78.5",
|
||||
"E87.8",
|
||||
"F10.1",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"K66.0",
|
||||
"K71.8",
|
||||
"K80.0",
|
||||
"K80.1",
|
||||
"K80.2",
|
||||
"K83.0",
|
||||
"N19",
|
||||
"N85.7",
|
||||
"R19",
|
||||
"R52.10",
|
||||
"R73.9",
|
||||
"R82.4",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 20,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 68,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "07",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 19,
|
||||
"anomalies": 16
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "183_23087212",
|
||||
"processing_time_s": 465.5,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 2,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E66.04",
|
||||
"I10",
|
||||
"N10",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"R35",
|
||||
"T83.1",
|
||||
"T83.5",
|
||||
"Z43.3"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 88,
|
||||
"issues_count": 4,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": false,
|
||||
"sources_count": 12
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
}
|
||||
]
|
||||
}
|
||||
72
output/benchmarks/20260219_220651_multimodel_v1/report.txt
Normal file
72
output/benchmarks/20260219_220651_multimodel_v1/report.txt
Normal file
@@ -0,0 +1,72 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260219_220651_multimodel_v1
|
||||
==================================================================
|
||||
Date : 2026-02-19T22:06:51.602389
|
||||
Modèles : coding=gemma3:27b-cloud cpam=deepseek-v3.2:cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 10/10 traités (0 échecs)
|
||||
Durée : 4822s (482.2s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ██████████████░░░░░░ 70.0%
|
||||
Code CIM-10 valide : ██████████████░░░░░░ 70.0%
|
||||
Confiance high : 6/10 medium: 1 low: 0
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 149 (moy 14.9/dossier)
|
||||
Avec code : 149/149
|
||||
Codes valides : ████████████████████ 100.0%
|
||||
Confiance : high=71 medium=60 low=18
|
||||
Confiance high : █████████░░░░░░░░░░░ 47.7%
|
||||
Downgrades : 4 (2.7%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NEED_INFO : 8
|
||||
PASS : 2
|
||||
Issues HARD : 0 (dans 0 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ████████████████████ 100.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 10
|
||||
Avec réponse : 2
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 482.2s
|
||||
Médian : 477.8s
|
||||
P90 : 552.8s
|
||||
Total : 4822s
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
116_23065570 N17.9✓ 9 100% NEED_INFO 439s
|
||||
132_23080179 R59.0✓ 22 100% NEED_INFO 499s
|
||||
134_23050890 Q64.0✓ 13 100% NEED_INFO 475s
|
||||
143_23096917 K35.8✓ 14 100% NEED_INFO 504s
|
||||
145_23057452 Z00.8✓ 12 100% NEED_INFO 429s
|
||||
153_23102610 -✗ 15 100% NEED_INFO 547s
|
||||
170_23077016 -✗ 11 100% PASS 553s
|
||||
176_23124187 I10✓ 24 100% NEED_INFO 480s
|
||||
17_23100690 K85.9✓ 20 100% NEED_INFO 430s
|
||||
183_23087212 -✗ 9 100% PASS 466s
|
||||
|
||||
==================================================================
|
||||
==================================================================
|
||||
COMPARAISON avec 20260219_220642_baseline_existing
|
||||
==================================================================
|
||||
Métrique Baseline Actuel Delta
|
||||
------------------------ ---------- ---------- ----------
|
||||
DP code valide 90.0% 70.0% -20.0%
|
||||
DAS validité 100.0% 100.0% +0.0%
|
||||
DAS confiance high 70.0% 47.7% -22.3%
|
||||
DAS downgrade 1.3% 2.7% +1.4%
|
||||
GHM estimé 50.0% 100.0% +50.0%
|
||||
DAS moy/dossier 15.0 14.9 -0.1
|
||||
Temps moyen (s) 0.0 482.2 +482.2
|
||||
==================================================================
|
||||
32
output/benchmarks/20260219_233905_cpam_gemma27b/config.json
Normal file
32
output/benchmarks/20260219_233905_cpam_gemma27b/config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "gemma3:27b-cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-19T23:39:05.178663",
|
||||
"run_id": "20260219_233905_cpam_gemma27b",
|
||||
"dossiers": [
|
||||
"116_23065570",
|
||||
"132_23080179",
|
||||
"134_23050890",
|
||||
"143_23096917",
|
||||
"145_23057452",
|
||||
"153_23102610",
|
||||
"170_23077016",
|
||||
"176_23124187",
|
||||
"17_23100690",
|
||||
"183_23087212"
|
||||
],
|
||||
"args": {
|
||||
"n": 10,
|
||||
"gold_standard": true,
|
||||
"clean": true,
|
||||
"no_reprocess": false,
|
||||
"seed": 42,
|
||||
"label": "cpam_gemma27b"
|
||||
}
|
||||
}
|
||||
842
output/benchmarks/20260219_233905_cpam_gemma27b/metrics.json
Normal file
842
output/benchmarks/20260219_233905_cpam_gemma27b/metrics.json
Normal file
@@ -0,0 +1,842 @@
|
||||
{
|
||||
"aggregate": {
|
||||
"n_total": 10,
|
||||
"n_success": 10,
|
||||
"n_failed": 0,
|
||||
"dp": {
|
||||
"has_code_rate": 0.7,
|
||||
"valid_code_rate": 0.7,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0
|
||||
},
|
||||
"das": {
|
||||
"total": 149,
|
||||
"mean_per_dossier": 14.9,
|
||||
"with_code": 149,
|
||||
"valid": 149,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 78,
|
||||
"medium": 59,
|
||||
"low": 12
|
||||
},
|
||||
"confidence_high_rate": 0.523,
|
||||
"downgraded": 4,
|
||||
"downgrade_rate": 0.027
|
||||
},
|
||||
"veto": {
|
||||
"verdicts": {
|
||||
"NEED_INFO": 8,
|
||||
"PASS": 2
|
||||
},
|
||||
"hard_total": 0,
|
||||
"dossiers_with_hard": 0
|
||||
},
|
||||
"ghm": {
|
||||
"estimated_rate": 1.0
|
||||
},
|
||||
"cpam": {
|
||||
"controls_total": 10,
|
||||
"with_response": 10
|
||||
},
|
||||
"timing": {
|
||||
"mean_s": 242.5,
|
||||
"median_s": 240.8,
|
||||
"p90_s": 346.7,
|
||||
"total_s": 2424.6
|
||||
},
|
||||
"invalid_codes": [],
|
||||
"invalid_codes_count": 0
|
||||
},
|
||||
"per_dossier": [
|
||||
{
|
||||
"dossier_id": "116_23065570",
|
||||
"processing_time_s": 195.8,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Insuffisance rénale aig",
|
||||
"code_suggestion": "N17.9",
|
||||
"code_final": "N17.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 4,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"K59.0",
|
||||
"N13.9",
|
||||
"N19",
|
||||
"N21.0",
|
||||
"N30.0",
|
||||
"N40.0",
|
||||
"N42.0",
|
||||
"T83.5",
|
||||
"Z01.4"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "11",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 0,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "132_23080179",
|
||||
"processing_time_s": 271.2,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Adénopathie",
|
||||
"code_suggestion": "R59.0",
|
||||
"code_final": "R59.0",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 22,
|
||||
"with_code": 22,
|
||||
"no_code": 0,
|
||||
"valid": 22,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 12,
|
||||
"medium": 10,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.045,
|
||||
"codes_uniques": [
|
||||
"C83.3",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E66.84",
|
||||
"E78.5",
|
||||
"E86",
|
||||
"E87.6",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"J90",
|
||||
"M48.5",
|
||||
"M54.2",
|
||||
"M54.3",
|
||||
"M54.8",
|
||||
"M89.5",
|
||||
"R06.0",
|
||||
"R11",
|
||||
"R13",
|
||||
"R93.1",
|
||||
"R93.8",
|
||||
"T98.1",
|
||||
"Z51.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 69,
|
||||
"issues_count": 8,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 12,
|
||||
"anomalies": 7
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "134_23050890",
|
||||
"processing_time_s": 254.4,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Epispadia",
|
||||
"code_suggestion": "Q64.0",
|
||||
"code_final": "Q64.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 13,
|
||||
"with_code": 13,
|
||||
"no_code": 0,
|
||||
"valid": 13,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 5,
|
||||
"low": 3
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"D50",
|
||||
"E66.05",
|
||||
"E66.9",
|
||||
"F32.9",
|
||||
"I95.1",
|
||||
"J18.9",
|
||||
"M16.9",
|
||||
"M54.2",
|
||||
"Q05.9",
|
||||
"Q65.0",
|
||||
"Q65.9",
|
||||
"S73.1",
|
||||
"Z04.802"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "15",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "143_23096917",
|
||||
"processing_time_s": 346.7,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Appendicite aigue",
|
||||
"code_suggestion": "K35.8",
|
||||
"code_final": "K35.8",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 12,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"B96.2",
|
||||
"C69.4",
|
||||
"D69.6",
|
||||
"D72.8",
|
||||
"E87.6",
|
||||
"F06.4",
|
||||
"G44.8",
|
||||
"K65.9",
|
||||
"K74.0",
|
||||
"K74.3",
|
||||
"L27.0",
|
||||
"N17.9",
|
||||
"R18",
|
||||
"T80.8"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-15"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "06",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 9
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 13,
|
||||
"anomalies": 6
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "145_23057452",
|
||||
"processing_time_s": 189.4,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Examen général",
|
||||
"code_suggestion": "Z00.8",
|
||||
"code_final": "Z00.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 12,
|
||||
"with_code": 12,
|
||||
"no_code": 0,
|
||||
"valid": 12,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E11.8",
|
||||
"F43.28",
|
||||
"G44.8",
|
||||
"G91.2",
|
||||
"G91.9",
|
||||
"H40.9",
|
||||
"I10",
|
||||
"M10.9",
|
||||
"M54.2",
|
||||
"N18.3",
|
||||
"N19",
|
||||
"O86.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 12,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-09"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "153_23102610",
|
||||
"processing_time_s": 290.2,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 15,
|
||||
"with_code": 15,
|
||||
"no_code": 0,
|
||||
"valid": 15,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 6,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"C49",
|
||||
"E11.9",
|
||||
"E23.0",
|
||||
"E78.5",
|
||||
"F06.4",
|
||||
"H36.0",
|
||||
"K42.9",
|
||||
"K71",
|
||||
"L83",
|
||||
"N19",
|
||||
"N39.0",
|
||||
"R59.9",
|
||||
"R63.4",
|
||||
"T83.5",
|
||||
"T88.7"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 15,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 55,
|
||||
"issues_count": 8,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 11
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 11,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "170_23077016",
|
||||
"processing_time_s": 185.2,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 11,
|
||||
"with_code": 11,
|
||||
"no_code": 0,
|
||||
"valid": 11,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 4,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.091,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"D72.8",
|
||||
"I97.8",
|
||||
"J18.9",
|
||||
"K59.0",
|
||||
"M05.9",
|
||||
"N19",
|
||||
"R23.1",
|
||||
"R50.9",
|
||||
"R52.2",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 11,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "176_23124187",
|
||||
"processing_time_s": 276.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Hta",
|
||||
"code_suggestion": "I10",
|
||||
"code_final": "I10",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 24,
|
||||
"with_code": 24,
|
||||
"no_code": 0,
|
||||
"valid": 24,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 14,
|
||||
"medium": 9,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.042,
|
||||
"codes_uniques": [
|
||||
"A41.9",
|
||||
"C31.1",
|
||||
"C34.9",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"D72.1",
|
||||
"E78.5",
|
||||
"E83.5",
|
||||
"E87.6",
|
||||
"G00",
|
||||
"I11.0",
|
||||
"J18.9",
|
||||
"J47",
|
||||
"J90",
|
||||
"K74.0",
|
||||
"M25.5",
|
||||
"N19",
|
||||
"R05",
|
||||
"R45.4",
|
||||
"R59.9",
|
||||
"R68.3",
|
||||
"R93.8",
|
||||
"Z72.0",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 23,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 59,
|
||||
"issues_count": 9,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "05",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 16,
|
||||
"anomalies": 9
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "17_23100690",
|
||||
"processing_time_s": 227.2,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Pancréatite aiguë",
|
||||
"code_suggestion": "K85.9",
|
||||
"code_final": "K85.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 20,
|
||||
"with_code": 20,
|
||||
"no_code": 0,
|
||||
"valid": 20,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 11,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.05,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"E66.04",
|
||||
"E78.5",
|
||||
"E87.8",
|
||||
"F10.1",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"K66.0",
|
||||
"K71.8",
|
||||
"K80.0",
|
||||
"K80.1",
|
||||
"K80.2",
|
||||
"K83.0",
|
||||
"N19",
|
||||
"N85.7",
|
||||
"R19",
|
||||
"R52.10",
|
||||
"R73.9",
|
||||
"R82.4",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 20,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "07",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 19,
|
||||
"anomalies": 16
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "183_23087212",
|
||||
"processing_time_s": 188.5,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E66.04",
|
||||
"I10",
|
||||
"N10",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"R35",
|
||||
"T83.1",
|
||||
"T83.5",
|
||||
"Z43.3"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 12
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
}
|
||||
]
|
||||
}
|
||||
72
output/benchmarks/20260219_233905_cpam_gemma27b/report.txt
Normal file
72
output/benchmarks/20260219_233905_cpam_gemma27b/report.txt
Normal file
@@ -0,0 +1,72 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260219_233905_cpam_gemma27b
|
||||
==================================================================
|
||||
Date : 2026-02-19T23:39:05.178663
|
||||
Modèles : coding=gemma3:27b-cloud cpam=gemma3:27b-cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 10/10 traités (0 échecs)
|
||||
Durée : 2425s (242.5s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ██████████████░░░░░░ 70.0%
|
||||
Code CIM-10 valide : ██████████████░░░░░░ 70.0%
|
||||
Confiance high : 5/10 medium: 2 low: 0
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 149 (moy 14.9/dossier)
|
||||
Avec code : 149/149
|
||||
Codes valides : ████████████████████ 100.0%
|
||||
Confiance : high=78 medium=59 low=12
|
||||
Confiance high : ██████████░░░░░░░░░░ 52.3%
|
||||
Downgrades : 4 (2.7%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NEED_INFO : 8
|
||||
PASS : 2
|
||||
Issues HARD : 0 (dans 0 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ████████████████████ 100.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 10
|
||||
Avec réponse : 10
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 242.5s
|
||||
Médian : 240.8s
|
||||
P90 : 346.7s
|
||||
Total : 2425s
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
116_23065570 N17.9✓ 9 100% NEED_INFO 196s
|
||||
132_23080179 R59.0✓ 22 100% NEED_INFO 271s
|
||||
134_23050890 Q64.0✓ 13 100% NEED_INFO 254s
|
||||
143_23096917 K35.8✓ 14 100% NEED_INFO 347s
|
||||
145_23057452 Z00.8✓ 12 100% NEED_INFO 189s
|
||||
153_23102610 -✗ 15 100% NEED_INFO 290s
|
||||
170_23077016 -✗ 11 100% PASS 185s
|
||||
176_23124187 I10✓ 24 100% NEED_INFO 276s
|
||||
17_23100690 K85.9✓ 20 100% NEED_INFO 227s
|
||||
183_23087212 -✗ 9 100% PASS 188s
|
||||
|
||||
==================================================================
|
||||
==================================================================
|
||||
COMPARAISON avec 20260219_220651_multimodel_v1
|
||||
==================================================================
|
||||
Métrique Baseline Actuel Delta
|
||||
------------------------ ---------- ---------- ----------
|
||||
DP code valide 70.0% 70.0% +0.0%
|
||||
DAS validité 100.0% 100.0% +0.0%
|
||||
DAS confiance high 47.7% 52.3% +4.6%
|
||||
DAS downgrade 2.7% 2.7% +0.0%
|
||||
GHM estimé 100.0% 100.0% +0.0%
|
||||
DAS moy/dossier 14.9 14.9 +0.0
|
||||
Temps moyen (s) 482.2 242.5 -239.7
|
||||
==================================================================
|
||||
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "gemma3:27b-cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-20T00:57:58.632958",
|
||||
"run_id": "20260220_005758_baseline_pre_parallel",
|
||||
"dossiers": [
|
||||
"116_23065570",
|
||||
"132_23080179",
|
||||
"134_23050890",
|
||||
"143_23096917",
|
||||
"145_23057452",
|
||||
"153_23102610",
|
||||
"170_23077016",
|
||||
"176_23124187",
|
||||
"17_23100690",
|
||||
"183_23087212"
|
||||
],
|
||||
"args": {
|
||||
"n": 10,
|
||||
"gold_standard": true,
|
||||
"clean": false,
|
||||
"no_reprocess": true,
|
||||
"seed": 42,
|
||||
"label": "baseline_pre_parallel"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,842 @@
|
||||
{
|
||||
"aggregate": {
|
||||
"n_total": 10,
|
||||
"n_success": 10,
|
||||
"n_failed": 0,
|
||||
"dp": {
|
||||
"has_code_rate": 0.7,
|
||||
"valid_code_rate": 0.7,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0
|
||||
},
|
||||
"das": {
|
||||
"total": 149,
|
||||
"mean_per_dossier": 14.9,
|
||||
"with_code": 149,
|
||||
"valid": 149,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 80,
|
||||
"medium": 57,
|
||||
"low": 12
|
||||
},
|
||||
"confidence_high_rate": 0.537,
|
||||
"downgraded": 4,
|
||||
"downgrade_rate": 0.027
|
||||
},
|
||||
"veto": {
|
||||
"verdicts": {
|
||||
"NEED_INFO": 8,
|
||||
"PASS": 2
|
||||
},
|
||||
"hard_total": 0,
|
||||
"dossiers_with_hard": 0
|
||||
},
|
||||
"ghm": {
|
||||
"estimated_rate": 1.0
|
||||
},
|
||||
"cpam": {
|
||||
"controls_total": 10,
|
||||
"with_response": 10
|
||||
},
|
||||
"timing": {
|
||||
"mean_s": 0.0,
|
||||
"median_s": 0.0,
|
||||
"p90_s": 0.0,
|
||||
"total_s": 0.0
|
||||
},
|
||||
"invalid_codes": [],
|
||||
"invalid_codes_count": 0
|
||||
},
|
||||
"per_dossier": [
|
||||
{
|
||||
"dossier_id": "116_23065570",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Insuffisance rénale aig",
|
||||
"code_suggestion": "N17.9",
|
||||
"code_final": "N17.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 3,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"K59.0",
|
||||
"N13.9",
|
||||
"N19",
|
||||
"N21.0",
|
||||
"N30.0",
|
||||
"N40.0",
|
||||
"N42.0",
|
||||
"T83.5",
|
||||
"Z01.4"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "11",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 0,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "132_23080179",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Adénopathie",
|
||||
"code_suggestion": "R59.0",
|
||||
"code_final": "R59.0",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 22,
|
||||
"with_code": 22,
|
||||
"no_code": 0,
|
||||
"valid": 22,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 13,
|
||||
"medium": 9,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.045,
|
||||
"codes_uniques": [
|
||||
"C83.3",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E66.84",
|
||||
"E78.5",
|
||||
"E86",
|
||||
"E87.6",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"J90",
|
||||
"M48.5",
|
||||
"M54.2",
|
||||
"M54.3",
|
||||
"M54.8",
|
||||
"M89.5",
|
||||
"R06.0",
|
||||
"R11",
|
||||
"R13",
|
||||
"R93.1",
|
||||
"R93.8",
|
||||
"T98.1",
|
||||
"Z51.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 66,
|
||||
"issues_count": 9,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 12,
|
||||
"anomalies": 7
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "134_23050890",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Epispadia",
|
||||
"code_suggestion": "Q64.0",
|
||||
"code_final": "Q64.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 13,
|
||||
"with_code": 13,
|
||||
"no_code": 0,
|
||||
"valid": 13,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 5,
|
||||
"low": 3
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"D50",
|
||||
"E66.05",
|
||||
"E66.9",
|
||||
"F32.9",
|
||||
"I95.1",
|
||||
"J18.9",
|
||||
"M16.9",
|
||||
"M54.2",
|
||||
"Q05.9",
|
||||
"Q65.0",
|
||||
"Q65.9",
|
||||
"S73.1",
|
||||
"Z04.802"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "15",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "143_23096917",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Appendicite aigue",
|
||||
"code_suggestion": "K35.8",
|
||||
"code_final": "K35.8",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 12,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"B96.2",
|
||||
"C69.4",
|
||||
"D69.6",
|
||||
"D72.8",
|
||||
"E87.6",
|
||||
"F06.4",
|
||||
"G44.8",
|
||||
"K65.9",
|
||||
"K74.0",
|
||||
"K74.3",
|
||||
"L27.0",
|
||||
"N17.9",
|
||||
"R18",
|
||||
"T80.8"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-15"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "06",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 9
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 13,
|
||||
"anomalies": 6
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "145_23057452",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Examen général",
|
||||
"code_suggestion": "Z00.8",
|
||||
"code_final": "Z00.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 12,
|
||||
"with_code": 12,
|
||||
"no_code": 0,
|
||||
"valid": 12,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E11.8",
|
||||
"F43.28",
|
||||
"G44.8",
|
||||
"G91.2",
|
||||
"G91.9",
|
||||
"H40.9",
|
||||
"I10",
|
||||
"M10.9",
|
||||
"M54.2",
|
||||
"N18.3",
|
||||
"N19",
|
||||
"O86.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 12,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-09"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "153_23102610",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 15,
|
||||
"with_code": 15,
|
||||
"no_code": 0,
|
||||
"valid": 15,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 6,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"C49",
|
||||
"E11.9",
|
||||
"E23.0",
|
||||
"E78.5",
|
||||
"F06.4",
|
||||
"H36.0",
|
||||
"K42.9",
|
||||
"K71",
|
||||
"L83",
|
||||
"N19",
|
||||
"N39.0",
|
||||
"R59.9",
|
||||
"R63.4",
|
||||
"T83.5",
|
||||
"T88.7"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 15,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 55,
|
||||
"issues_count": 8,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 11
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 11,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "170_23077016",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 11,
|
||||
"with_code": 11,
|
||||
"no_code": 0,
|
||||
"valid": 11,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 4,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.091,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"D72.8",
|
||||
"I97.8",
|
||||
"J18.9",
|
||||
"K59.0",
|
||||
"M05.9",
|
||||
"N19",
|
||||
"R23.1",
|
||||
"R50.9",
|
||||
"R52.2",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 11,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "176_23124187",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Hta",
|
||||
"code_suggestion": "I10",
|
||||
"code_final": "I10",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 24,
|
||||
"with_code": 24,
|
||||
"no_code": 0,
|
||||
"valid": 24,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 14,
|
||||
"medium": 9,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.042,
|
||||
"codes_uniques": [
|
||||
"A41.9",
|
||||
"C31.1",
|
||||
"C34.9",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"D72.1",
|
||||
"E78.5",
|
||||
"E83.5",
|
||||
"E87.6",
|
||||
"G00",
|
||||
"I11.0",
|
||||
"J18.9",
|
||||
"J47",
|
||||
"J90",
|
||||
"K74.0",
|
||||
"M25.5",
|
||||
"N19",
|
||||
"R05",
|
||||
"R45.4",
|
||||
"R59.9",
|
||||
"R68.3",
|
||||
"R93.8",
|
||||
"Z72.0",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 23,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 59,
|
||||
"issues_count": 9,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "05",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 16,
|
||||
"anomalies": 9
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "17_23100690",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Pancréatite aiguë",
|
||||
"code_suggestion": "K85.9",
|
||||
"code_final": "K85.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 20,
|
||||
"with_code": 20,
|
||||
"no_code": 0,
|
||||
"valid": 20,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 11,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.05,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"E66.04",
|
||||
"E78.5",
|
||||
"E87.8",
|
||||
"F10.1",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"K66.0",
|
||||
"K71.8",
|
||||
"K80.0",
|
||||
"K80.1",
|
||||
"K80.2",
|
||||
"K83.0",
|
||||
"N19",
|
||||
"N85.7",
|
||||
"R19",
|
||||
"R52.10",
|
||||
"R73.9",
|
||||
"R82.4",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 20,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "07",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 19,
|
||||
"anomalies": 16
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "183_23087212",
|
||||
"processing_time_s": 0.0,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E66.04",
|
||||
"I10",
|
||||
"N10",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"R35",
|
||||
"T83.1",
|
||||
"T83.5",
|
||||
"Z43.3"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 12
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260220_005758_baseline_pre_parallel
|
||||
==================================================================
|
||||
Date : 2026-02-20T00:57:58.632958
|
||||
Modèles : coding=gemma3:27b-cloud cpam=gemma3:27b-cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 10/10 traités (0 échecs)
|
||||
Durée : 0s (0.0s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ██████████████░░░░░░ 70.0%
|
||||
Code CIM-10 valide : ██████████████░░░░░░ 70.0%
|
||||
Confiance high : 5/10 medium: 2 low: 0
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 149 (moy 14.9/dossier)
|
||||
Avec code : 149/149
|
||||
Codes valides : ████████████████████ 100.0%
|
||||
Confiance : high=80 medium=57 low=12
|
||||
Confiance high : ██████████░░░░░░░░░░ 53.7%
|
||||
Downgrades : 4 (2.7%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NEED_INFO : 8
|
||||
PASS : 2
|
||||
Issues HARD : 0 (dans 0 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ████████████████████ 100.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 10
|
||||
Avec réponse : 10
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 0.0s
|
||||
Médian : 0.0s
|
||||
P90 : 0.0s
|
||||
Total : 0s
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
116_23065570 N17.9✓ 9 100% NEED_INFO 0s
|
||||
132_23080179 R59.0✓ 22 100% NEED_INFO 0s
|
||||
134_23050890 Q64.0✓ 13 100% NEED_INFO 0s
|
||||
143_23096917 K35.8✓ 14 100% NEED_INFO 0s
|
||||
145_23057452 Z00.8✓ 12 100% NEED_INFO 0s
|
||||
153_23102610 -✗ 15 100% NEED_INFO 0s
|
||||
170_23077016 -✗ 11 100% PASS 0s
|
||||
176_23124187 I10✓ 24 100% NEED_INFO 0s
|
||||
17_23100690 K85.9✓ 20 100% NEED_INFO 0s
|
||||
183_23087212 -✗ 9 100% PASS 0s
|
||||
|
||||
==================================================================
|
||||
32
output/benchmarks/20260220_005803_parallel_test/config.json
Normal file
32
output/benchmarks/20260220_005803_parallel_test/config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "gemma3:27b-cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-20T00:58:03.899793",
|
||||
"run_id": "20260220_005803_parallel_test",
|
||||
"dossiers": [
|
||||
"116_23065570",
|
||||
"132_23080179",
|
||||
"134_23050890",
|
||||
"143_23096917",
|
||||
"145_23057452",
|
||||
"153_23102610",
|
||||
"170_23077016",
|
||||
"176_23124187",
|
||||
"17_23100690",
|
||||
"183_23087212"
|
||||
],
|
||||
"args": {
|
||||
"n": 10,
|
||||
"gold_standard": true,
|
||||
"clean": true,
|
||||
"no_reprocess": false,
|
||||
"seed": 42,
|
||||
"label": "parallel_test"
|
||||
}
|
||||
}
|
||||
839
output/benchmarks/20260220_005803_parallel_test/metrics.json
Normal file
839
output/benchmarks/20260220_005803_parallel_test/metrics.json
Normal file
@@ -0,0 +1,839 @@
|
||||
{
|
||||
"aggregate": {
|
||||
"n_total": 10,
|
||||
"n_success": 10,
|
||||
"n_failed": 0,
|
||||
"dp": {
|
||||
"has_code_rate": 0.7,
|
||||
"valid_code_rate": 0.7,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 2,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0
|
||||
},
|
||||
"das": {
|
||||
"total": 147,
|
||||
"mean_per_dossier": 14.7,
|
||||
"with_code": 147,
|
||||
"valid": 147,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 71,
|
||||
"medium": 63,
|
||||
"low": 13
|
||||
},
|
||||
"confidence_high_rate": 0.483,
|
||||
"downgraded": 4,
|
||||
"downgrade_rate": 0.027
|
||||
},
|
||||
"veto": {
|
||||
"verdicts": {
|
||||
"NEED_INFO": 8,
|
||||
"PASS": 2
|
||||
},
|
||||
"hard_total": 0,
|
||||
"dossiers_with_hard": 0
|
||||
},
|
||||
"ghm": {
|
||||
"estimated_rate": 1.0
|
||||
},
|
||||
"cpam": {
|
||||
"controls_total": 10,
|
||||
"with_response": 10
|
||||
},
|
||||
"timing": {
|
||||
"mean_s": 239.6,
|
||||
"median_s": 222.4,
|
||||
"p90_s": 317.7,
|
||||
"total_s": 2396.4
|
||||
},
|
||||
"invalid_codes": [],
|
||||
"invalid_codes_count": 0
|
||||
},
|
||||
"per_dossier": [
|
||||
{
|
||||
"dossier_id": "116_23065570",
|
||||
"processing_time_s": 222.4,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Insuffisance rénale aig",
|
||||
"code_suggestion": "N17.9",
|
||||
"code_final": "N17.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 4,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"K59.0",
|
||||
"N13.9",
|
||||
"N19",
|
||||
"N21.0",
|
||||
"N30.0",
|
||||
"N40.0",
|
||||
"N42.0",
|
||||
"T83.5",
|
||||
"Z01.4"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "11",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 0,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "132_23080179",
|
||||
"processing_time_s": 317.7,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Adénopathie",
|
||||
"code_suggestion": "R59.0",
|
||||
"code_final": "R59.0",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 22,
|
||||
"with_code": 22,
|
||||
"no_code": 0,
|
||||
"valid": 22,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 12,
|
||||
"medium": 10,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.045,
|
||||
"codes_uniques": [
|
||||
"C83.3",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E66.84",
|
||||
"E78.5",
|
||||
"E86",
|
||||
"E87.6",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"J90",
|
||||
"M48.5",
|
||||
"M54.2",
|
||||
"M54.3",
|
||||
"M54.8",
|
||||
"M89.5",
|
||||
"R06.0",
|
||||
"R11",
|
||||
"R13",
|
||||
"R93.1",
|
||||
"R93.8",
|
||||
"T98.1",
|
||||
"Z51.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 69,
|
||||
"issues_count": 8,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 12,
|
||||
"anomalies": 7
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "134_23050890",
|
||||
"processing_time_s": 249.7,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Epispadia",
|
||||
"code_suggestion": "Q64.0",
|
||||
"code_final": "Q64.0",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 13,
|
||||
"with_code": 13,
|
||||
"no_code": 0,
|
||||
"valid": 13,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 6,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"D50",
|
||||
"E66.05",
|
||||
"E66.9",
|
||||
"F32.9",
|
||||
"I95.1",
|
||||
"J18.9",
|
||||
"M16.9",
|
||||
"M54.2",
|
||||
"Q05.9",
|
||||
"Q65.0",
|
||||
"Q65.9",
|
||||
"S73.1",
|
||||
"Z04.802"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "15",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 4,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "143_23096917",
|
||||
"processing_time_s": 193.8,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Appendicite aigue",
|
||||
"code_suggestion": "K35.8",
|
||||
"code_final": "K35.8",
|
||||
"confidence": "medium",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 14,
|
||||
"with_code": 14,
|
||||
"no_code": 0,
|
||||
"valid": 14,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 10,
|
||||
"medium": 4,
|
||||
"low": 0
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"B96.2",
|
||||
"C69.4",
|
||||
"D69.6",
|
||||
"D72.8",
|
||||
"E87.6",
|
||||
"F06.4",
|
||||
"G44.8",
|
||||
"K65.9",
|
||||
"K74.0",
|
||||
"K74.3",
|
||||
"L27.0",
|
||||
"N17.9",
|
||||
"R18",
|
||||
"T80.8"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 13,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 78,
|
||||
"issues_count": 5,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-15"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "06",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 9
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 13,
|
||||
"anomalies": 6
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "145_23057452",
|
||||
"processing_time_s": 200.8,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Examen général",
|
||||
"code_suggestion": "Z00.8",
|
||||
"code_final": "Z00.8",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 11,
|
||||
"with_code": 11,
|
||||
"no_code": 0,
|
||||
"valid": 11,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 4,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E11.8",
|
||||
"F43.28",
|
||||
"G44.8",
|
||||
"G91.9",
|
||||
"H40.9",
|
||||
"I10",
|
||||
"M10.9",
|
||||
"M54.2",
|
||||
"N18.3",
|
||||
"N19",
|
||||
"O86.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 11,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 75,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-09"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "23",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 1
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "153_23102610",
|
||||
"processing_time_s": 222.5,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 15,
|
||||
"with_code": 15,
|
||||
"no_code": 0,
|
||||
"valid": 15,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 6,
|
||||
"medium": 7,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"C49",
|
||||
"E11.9",
|
||||
"E23.0",
|
||||
"E78.5",
|
||||
"F06.4",
|
||||
"H36.0",
|
||||
"K42.9",
|
||||
"K71",
|
||||
"L83",
|
||||
"N19",
|
||||
"N39.0",
|
||||
"R59.9",
|
||||
"R63.4",
|
||||
"T83.5",
|
||||
"T88.7"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 15,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 61,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 11
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 11,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "170_23077016",
|
||||
"processing_time_s": 200.3,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 11,
|
||||
"with_code": 11,
|
||||
"no_code": 0,
|
||||
"valid": 11,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 4,
|
||||
"medium": 6,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.091,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"D72.8",
|
||||
"I97.8",
|
||||
"J18.9",
|
||||
"K59.0",
|
||||
"M05.9",
|
||||
"N19",
|
||||
"R23.1",
|
||||
"R50.9",
|
||||
"R52.2",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 11,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 94,
|
||||
"issues_count": 2,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 2
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "176_23124187",
|
||||
"processing_time_s": 293.9,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Hta",
|
||||
"code_suggestion": "I10",
|
||||
"code_final": "I10",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 23,
|
||||
"with_code": 23,
|
||||
"no_code": 0,
|
||||
"valid": 23,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 13,
|
||||
"medium": 8,
|
||||
"low": 2
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.043,
|
||||
"codes_uniques": [
|
||||
"A41.9",
|
||||
"C31.1",
|
||||
"C34.9",
|
||||
"D64.9",
|
||||
"D69.6",
|
||||
"E78.5",
|
||||
"E83.5",
|
||||
"E87.6",
|
||||
"G00",
|
||||
"I11.0",
|
||||
"J18.9",
|
||||
"J47",
|
||||
"J90",
|
||||
"K74.0",
|
||||
"M06.4",
|
||||
"N19",
|
||||
"R05",
|
||||
"R45.4",
|
||||
"R59.9",
|
||||
"R68.3",
|
||||
"R93.8",
|
||||
"Z72.0",
|
||||
"Z99.1"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 22,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 59,
|
||||
"issues_count": 9,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "05",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 16,
|
||||
"anomalies": 9
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "17_23100690",
|
||||
"processing_time_s": 298.8,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "Pancréatite aiguë",
|
||||
"code_suggestion": "K85.9",
|
||||
"code_final": "K85.9",
|
||||
"confidence": "high",
|
||||
"has_code": true,
|
||||
"valid_code": true,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 20,
|
||||
"with_code": 20,
|
||||
"no_code": 0,
|
||||
"valid": 20,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 7,
|
||||
"medium": 9,
|
||||
"low": 4
|
||||
},
|
||||
"downgraded": 1,
|
||||
"downgrade_rate": 0.05,
|
||||
"codes_uniques": [
|
||||
"D64.9",
|
||||
"E66.04",
|
||||
"E78.5",
|
||||
"E87.8",
|
||||
"F10.1",
|
||||
"G44.8",
|
||||
"I10",
|
||||
"K66.0",
|
||||
"K71.8",
|
||||
"K80.0",
|
||||
"K80.1",
|
||||
"K80.2",
|
||||
"K83.0",
|
||||
"N19",
|
||||
"N85.7",
|
||||
"R19",
|
||||
"R52.10",
|
||||
"R73.9",
|
||||
"R82.4",
|
||||
"Z00.0"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 20,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "NEED_INFO",
|
||||
"score": 68,
|
||||
"issues_count": 6,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": "07",
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 6
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 19,
|
||||
"anomalies": 16
|
||||
},
|
||||
"invalid_codes": []
|
||||
},
|
||||
{
|
||||
"dossier_id": "183_23087212",
|
||||
"processing_time_s": 196.5,
|
||||
"success": true,
|
||||
"dp": {
|
||||
"texte": "",
|
||||
"code_suggestion": "",
|
||||
"code_final": "",
|
||||
"confidence": "",
|
||||
"has_code": false,
|
||||
"valid_code": false,
|
||||
"downgraded": false
|
||||
},
|
||||
"das": {
|
||||
"total": 9,
|
||||
"with_code": 9,
|
||||
"no_code": 0,
|
||||
"valid": 9,
|
||||
"validity_rate": 1.0,
|
||||
"confidence": {
|
||||
"high": 5,
|
||||
"medium": 3,
|
||||
"low": 1
|
||||
},
|
||||
"downgraded": 0,
|
||||
"downgrade_rate": 0.0,
|
||||
"codes_uniques": [
|
||||
"E66.04",
|
||||
"I10",
|
||||
"N10",
|
||||
"N19",
|
||||
"N20.0",
|
||||
"R35",
|
||||
"T83.1",
|
||||
"T83.5",
|
||||
"Z43.3"
|
||||
]
|
||||
},
|
||||
"metrics": {
|
||||
"das_active": 9,
|
||||
"das_removed": 0,
|
||||
"das_ruled_out": 0
|
||||
},
|
||||
"veto": {
|
||||
"verdict": "PASS",
|
||||
"score": 91,
|
||||
"issues_count": 3,
|
||||
"hard_count": 0,
|
||||
"top_issues": [
|
||||
"VETO-03",
|
||||
"VETO-03",
|
||||
"VETO-03"
|
||||
]
|
||||
},
|
||||
"ghm": {
|
||||
"estimated": true,
|
||||
"cmd": null,
|
||||
"severity": null,
|
||||
"ghm": null
|
||||
},
|
||||
"cpam": {
|
||||
"controls_count": 1,
|
||||
"has_response": true,
|
||||
"sources_count": 0
|
||||
},
|
||||
"biologie": {
|
||||
"tests_count": 6,
|
||||
"anomalies": 0
|
||||
},
|
||||
"invalid_codes": []
|
||||
}
|
||||
]
|
||||
}
|
||||
72
output/benchmarks/20260220_005803_parallel_test/report.txt
Normal file
72
output/benchmarks/20260220_005803_parallel_test/report.txt
Normal file
@@ -0,0 +1,72 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260220_005803_parallel_test
|
||||
==================================================================
|
||||
Date : 2026-02-20T00:58:03.899793
|
||||
Modèles : coding=gemma3:27b-cloud cpam=gemma3:27b-cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 10/10 traités (0 échecs)
|
||||
Durée : 2396s (239.6s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ██████████████░░░░░░ 70.0%
|
||||
Code CIM-10 valide : ██████████████░░░░░░ 70.0%
|
||||
Confiance high : 5/10 medium: 2 low: 0
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 147 (moy 14.7/dossier)
|
||||
Avec code : 147/147
|
||||
Codes valides : ████████████████████ 100.0%
|
||||
Confiance : high=71 medium=63 low=13
|
||||
Confiance high : █████████░░░░░░░░░░░ 48.3%
|
||||
Downgrades : 4 (2.7%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NEED_INFO : 8
|
||||
PASS : 2
|
||||
Issues HARD : 0 (dans 0 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ████████████████████ 100.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 10
|
||||
Avec réponse : 10
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 239.6s
|
||||
Médian : 222.4s
|
||||
P90 : 317.7s
|
||||
Total : 2396s
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
116_23065570 N17.9✓ 9 100% NEED_INFO 222s
|
||||
132_23080179 R59.0✓ 22 100% NEED_INFO 318s
|
||||
134_23050890 Q64.0✓ 13 100% NEED_INFO 250s
|
||||
143_23096917 K35.8✓ 14 100% NEED_INFO 194s
|
||||
145_23057452 Z00.8✓ 11 100% NEED_INFO 201s
|
||||
153_23102610 -✗ 15 100% NEED_INFO 222s
|
||||
170_23077016 -✗ 11 100% PASS 200s
|
||||
176_23124187 I10✓ 23 100% NEED_INFO 294s
|
||||
17_23100690 K85.9✓ 20 100% NEED_INFO 299s
|
||||
183_23087212 -✗ 9 100% PASS 196s
|
||||
|
||||
==================================================================
|
||||
==================================================================
|
||||
COMPARAISON avec 20260220_005758_baseline_pre_parallel
|
||||
==================================================================
|
||||
Métrique Baseline Actuel Delta
|
||||
------------------------ ---------- ---------- ----------
|
||||
DP code valide 70.0% 70.0% +0.0%
|
||||
DAS validité 100.0% 100.0% +0.0%
|
||||
DAS confiance high 53.7% 48.3% -5.4%
|
||||
DAS downgrade 2.7% 2.7% +0.0%
|
||||
GHM estimé 100.0% 100.0% +0.0%
|
||||
DAS moy/dossier 14.9 14.7 -0.2
|
||||
Temps moyen (s) 0.0 239.6 +239.6
|
||||
==================================================================
|
||||
172
output/benchmarks/20260220_013412_150d_parallel/config.json
Normal file
172
output/benchmarks/20260220_013412_150d_parallel/config.json
Normal file
@@ -0,0 +1,172 @@
|
||||
{
|
||||
"models": {
|
||||
"coding": "gemma3:27b-cloud",
|
||||
"cpam": "gemma3:27b-cloud",
|
||||
"validation": "deepseek-v3.2:cloud",
|
||||
"qc": "gemma3:12b"
|
||||
},
|
||||
"ollama_model": "gemma3:27b-cloud",
|
||||
"ollama_url": "http://localhost:11434",
|
||||
"timestamp": "2026-02-20T01:34:12.864264",
|
||||
"run_id": "20260220_013412_150d_parallel",
|
||||
"dossiers": [
|
||||
"140_23090475",
|
||||
"18_23103327",
|
||||
"40_23168633",
|
||||
"211_23155556",
|
||||
"20_23108737",
|
||||
"25_23127187",
|
||||
"109_23028431",
|
||||
"33_23150352",
|
||||
"52_23223407",
|
||||
"202_23151035",
|
||||
"103_23056749",
|
||||
"147_23067572",
|
||||
"114_23060661",
|
||||
"181_23127286",
|
||||
"63_23001636",
|
||||
"178_23124458",
|
||||
"204_23142660",
|
||||
"11_23082513",
|
||||
"194_23142891",
|
||||
"196_ 23140080",
|
||||
"55_23246490",
|
||||
"94_23000519",
|
||||
"156_23104564",
|
||||
"127_23048705",
|
||||
"214_23148798",
|
||||
"75_23181227",
|
||||
"166_23113695",
|
||||
"141_23090597",
|
||||
"31_23142976",
|
||||
"67_23001636",
|
||||
"195_23144210",
|
||||
"187_23133268",
|
||||
"160_23099448",
|
||||
"249_23196688",
|
||||
"99_23033146",
|
||||
"54_23230165",
|
||||
"171_23108560",
|
||||
"172_23119469",
|
||||
"111_23061304",
|
||||
"51_23222062",
|
||||
"235_23143706",
|
||||
"125_23074494",
|
||||
"174_23080042",
|
||||
"190_23139234",
|
||||
"86_23221334",
|
||||
"10_23079252",
|
||||
"220_23159566",
|
||||
"212_23155836",
|
||||
"139_23087691",
|
||||
"76_23165648",
|
||||
"200_23149959",
|
||||
"209_23154576",
|
||||
"239_23188240",
|
||||
"218_23164383",
|
||||
"104_23001083",
|
||||
"148_23018396",
|
||||
"92_23049455",
|
||||
"167_23104446",
|
||||
"71_23135194",
|
||||
"105_23052612",
|
||||
"155_23096278",
|
||||
"222_23139653",
|
||||
"225_23160703",
|
||||
"213_23156193",
|
||||
"83_23187785",
|
||||
"128_23076141",
|
||||
"59_23088959",
|
||||
"142_23093202",
|
||||
"74_23141536",
|
||||
"102_23056463",
|
||||
"241_23188038",
|
||||
"244_23193317",
|
||||
"57_23003949",
|
||||
"197_23149133",
|
||||
"238_23188172",
|
||||
"9_23077394",
|
||||
"143_23096917",
|
||||
"65_23001636",
|
||||
"29_23137897",
|
||||
"170_23077016",
|
||||
"177_23110276",
|
||||
"135_23036651",
|
||||
"242_23192524",
|
||||
"112_23065936",
|
||||
"56_23248174",
|
||||
"87_23236926",
|
||||
"159_23107113",
|
||||
"130_23077240",
|
||||
"100_23054899",
|
||||
"37_23158940",
|
||||
"26_23127395",
|
||||
"58_23084901",
|
||||
"134_23050890",
|
||||
"191_23140698",
|
||||
"39_23167029",
|
||||
"175_23116191",
|
||||
"131_23079402",
|
||||
"210_23155084",
|
||||
"77_23194611",
|
||||
"7_23066992",
|
||||
"208_23151988",
|
||||
"216_23159905",
|
||||
"6_23066847",
|
||||
"66_23001636",
|
||||
"96_23044463",
|
||||
"12_23084754",
|
||||
"219_23164660",
|
||||
"2_23044104",
|
||||
"201_23149994",
|
||||
"144_23097531",
|
||||
"73_23139637",
|
||||
"232_23183311",
|
||||
"16_23098082",
|
||||
"72_23068111",
|
||||
"64_23001636",
|
||||
"8_23074520",
|
||||
"90_23011562",
|
||||
"227_23173599",
|
||||
"118_23042633",
|
||||
"234_23174515",
|
||||
"1_23042753",
|
||||
"78_23187785",
|
||||
"43_23177057",
|
||||
"34_23153510",
|
||||
"21_23111304",
|
||||
"15_23096332",
|
||||
"62_23001636",
|
||||
"69_23046068",
|
||||
"38_23162619",
|
||||
"230_23167769",
|
||||
"19_23103383",
|
||||
"221_23167859",
|
||||
"158_23105874",
|
||||
"93_23050151",
|
||||
"49_23217289",
|
||||
"133_23056022",
|
||||
"46_23187081",
|
||||
"192_23132490",
|
||||
"215_23158603",
|
||||
"41_23170176",
|
||||
"231_23159944",
|
||||
"14_23089947",
|
||||
"115_23066188",
|
||||
"246_23193699",
|
||||
"193_23123388",
|
||||
"173_23069373",
|
||||
"84_23215994",
|
||||
"32_23143161",
|
||||
"113_23065949",
|
||||
"176_23124187"
|
||||
],
|
||||
"args": {
|
||||
"n": 150,
|
||||
"gold_standard": false,
|
||||
"clean": true,
|
||||
"no_reprocess": false,
|
||||
"seed": 42,
|
||||
"label": "150d_parallel"
|
||||
}
|
||||
}
|
||||
10927
output/benchmarks/20260220_013412_150d_parallel/metrics.json
Normal file
10927
output/benchmarks/20260220_013412_150d_parallel/metrics.json
Normal file
File diff suppressed because it is too large
Load Diff
213
output/benchmarks/20260220_013412_150d_parallel/report.txt
Normal file
213
output/benchmarks/20260220_013412_150d_parallel/report.txt
Normal file
@@ -0,0 +1,213 @@
|
||||
==================================================================
|
||||
BENCHMARK QUALITÉ T2A — 20260220_013412_150d_parallel
|
||||
==================================================================
|
||||
Date : 2026-02-20T01:34:12.864264
|
||||
Modèles : coding=gemma3:27b-cloud cpam=gemma3:27b-cloud
|
||||
validation=deepseek-v3.2:cloud qc=gemma3:12b
|
||||
Dossiers : 149/150 traités (1 échecs)
|
||||
Durée : 21029s (141.1s/dossier)
|
||||
------------------------------------------------------------------
|
||||
|
||||
DIAGNOSTIC PRINCIPAL (DP)
|
||||
Code obtenu : ███████████████░░░░░ 78.5%
|
||||
Code CIM-10 valide : ███████████████░░░░░ 76.5%
|
||||
Confiance high : 78/149 medium: 25 low: 14
|
||||
Downgrades : 0
|
||||
|
||||
DIAGNOSTICS ASSOCIÉS (DAS)
|
||||
Total : 1538 (moy 10.3/dossier)
|
||||
Avec code : 1538/1538
|
||||
Codes valides : ███████████████████░ 99.5%
|
||||
Confiance : high=759 medium=624 low=155
|
||||
Confiance high : █████████░░░░░░░░░░░ 49.3%
|
||||
Downgrades : 34 (2.2%)
|
||||
|
||||
VETOS / QUALITÉ
|
||||
NEED_INFO : 96
|
||||
PASS : 46
|
||||
FAIL : 7
|
||||
Issues HARD : 7 (dans 7 dossiers)
|
||||
|
||||
GHM
|
||||
Estimé : ████████████████████ 100.0%
|
||||
|
||||
CPAM
|
||||
Contrôles : 14
|
||||
Avec réponse : 12
|
||||
|
||||
TEMPS DE TRAITEMENT
|
||||
Moyen : 141.1s
|
||||
Médian : 127.7s
|
||||
P90 : 224.9s
|
||||
Total : 21029s
|
||||
|
||||
CODES CIM-10 INVALIDES (11)
|
||||
DAS:R33
|
||||
DAS:R33
|
||||
DAS:F17.2
|
||||
DAS:R33
|
||||
DAS:R29.1
|
||||
DAS:D20.0
|
||||
DP:S22.31
|
||||
DP:X20.13
|
||||
DP:S22.31
|
||||
DAS:S92.21
|
||||
DAS:S82.81
|
||||
|
||||
------------------------------------------------------------------
|
||||
DÉTAIL PAR DOSSIER
|
||||
------------------------------------------------------------------
|
||||
Dossier DP DAS Valid% Veto Temps
|
||||
------------------------- ------ ---- ------- ---------- ------
|
||||
100_23054899 H70.0✓ 8 100% PASS 107s
|
||||
102_23056463 M45✓ 10 100% NEED_INFO 106s
|
||||
103_23056749 F06.0✓ 20 100% NEED_INFO 148s
|
||||
104_23001083 F41.00✓ 16 100% PASS 133s
|
||||
105_23052612 M35.2✓ 17 100% NEED_INFO 113s
|
||||
109_23028431 K83.5✓ 7 100% NEED_INFO 167s
|
||||
10_23079252 K81.0✓ 11 100% NEED_INFO 133s
|
||||
111_23061304 -✗ 3 100% PASS 58s
|
||||
112_23065936 -✗ 8 100% PASS 176s
|
||||
113_23065949 K57.5✓ 7 100% NEED_INFO 82s
|
||||
114_23060661 N23✓ 16 100% NEED_INFO 182s
|
||||
115_23066188 A87.0✓ 5 100% PASS 87s
|
||||
118_23042633 X20.13✗ 8 100% PASS 99s
|
||||
11_23082513 K80.0✓ 10 100% NEED_INFO 85s
|
||||
125_23074494 S72.1✓ 11 100% FAIL 187s
|
||||
127_23048705 M17.9✓ 14 100% NEED_INFO 260s
|
||||
128_23076141 E11.0✓ 17 100% NEED_INFO 214s
|
||||
12_23084754 K81.9✓ 8 100% NEED_INFO 126s
|
||||
130_23077240 J90✓ 18 100% NEED_INFO 192s
|
||||
131_23079402 R06.0✓ 18 100% NEED_INFO 138s
|
||||
133_23056022 H33.2✓ 8 100% PASS 101s
|
||||
134_23050890 Q64.0✓ 13 100% NEED_INFO 208s
|
||||
135_23036651 R04.0✓ 8 100% NEED_INFO 133s
|
||||
139_23087691 -✗ 17 100% NEED_INFO 226s
|
||||
140_23090475 -✗ 7 100% PASS 81s
|
||||
141_23090597 K85.9✓ 27 100% NEED_INFO 291s
|
||||
142_23093202 K83.0✓ 10 100% NEED_INFO 106s
|
||||
143_23096917 K35.8✓ 14 100% NEED_INFO 225s
|
||||
144_23097531 D86✓ 8 100% NEED_INFO 121s
|
||||
147_23067572 K40.9✓ 19 100% NEED_INFO 174s
|
||||
148_23018396 -✗ 4 100% PASS 119s
|
||||
14_23089947 K85.1✓ 2 100% PASS 84s
|
||||
155_23096278 J45.9✓ 15 100% NEED_INFO 177s
|
||||
156_23104564 Z51.1✓ 14 100% NEED_INFO 232s
|
||||
158_23105874 A41.3✓ 17 100% NEED_INFO 161s
|
||||
159_23107113 -✗ 21 100% NEED_INFO 171s
|
||||
15_23096332 K81.9✓ 7 100% PASS 124s
|
||||
160_23099448 -✗ 11 100% NEED_INFO 167s
|
||||
166_23113695 N17.9✓ 7 100% PASS 124s
|
||||
167_23104446 I10✓ 9 100% PASS 165s
|
||||
16_23098082 K85.9✓ 16 100% FAIL 115s
|
||||
170_23077016 -✗ 11 100% PASS 165s
|
||||
171_23108560 N17.9✓ 7 86% PASS 155s
|
||||
172_23119469 J90✓ 12 100% NEED_INFO 193s
|
||||
173_23069373 E04.2✓ 9 100% NEED_INFO 123s
|
||||
174_23080042 -✗ 7 100% PASS 121s
|
||||
175_23116191 J45.9✓ 13 100% NEED_INFO 152s
|
||||
176_23124187 I10✓ 24 100% NEED_INFO 247s
|
||||
177_23110276 N82.9✓ 8 100% PASS 119s
|
||||
178_23124458 J01.2✓ 14 100% NEED_INFO 250s
|
||||
181_23127286 R30.0✓ 20 95% NEED_INFO 202s
|
||||
187_23133268 Z00.8✓ 21 100% NEED_INFO 243s
|
||||
18_23103327 K80.0✓ 11 100% NEED_INFO 128s
|
||||
190_23139234 J18.0✓ 12 100% NEED_INFO 110s
|
||||
191_23140698 R06.0✓ 8 100% NEED_INFO 101s
|
||||
192_23132490 -✗ 8 100% NEED_INFO 109s
|
||||
193_23123388 G35✓ 6 100% PASS 150s
|
||||
194_23142891 R93.1✓ 11 100% FAIL 165s
|
||||
195_23144210 K85.9✓ 17 100% NEED_INFO 157s
|
||||
196_ 23140080 K85.9✓ 16 100% NEED_INFO 236s
|
||||
197_23149133 M25.5✓ 23 96% FAIL 192s
|
||||
19_23103383 K80.1✓ 12 100% NEED_INFO 101s
|
||||
1_23042753 ÉCHEC
|
||||
200_23149959 -✗ 21 100% NEED_INFO 218s
|
||||
201_23149994 G82.4✓ 4 100% PASS 91s
|
||||
202_23151035 -✗ 3 100% PASS 72s
|
||||
204_23142660 -✗ 3 100% PASS 110s
|
||||
208_23151988 K81.0✓ 8 100% NEED_INFO 155s
|
||||
209_23154576 S72.3✓ 11 100% PASS 288s
|
||||
20_23108737 K81.0✓ 18 100% NEED_INFO 174s
|
||||
210_23155084 K35.8✓ 1 100% PASS 62s
|
||||
211_23155556 M10.9✓ 11 100% NEED_INFO 163s
|
||||
212_23155836 K85.9✓ 14 100% NEED_INFO 206s
|
||||
213_23156193 N23✓ 3 100% NEED_INFO 60s
|
||||
214_23148798 Z03.8✓ 12 100% NEED_INFO 206s
|
||||
215_23158603 Z31.5✓ 5 100% PASS 85s
|
||||
216_23159905 G82.4✓ 7 100% NEED_INFO 103s
|
||||
218_23164383 H81.2✓ 9 100% NEED_INFO 105s
|
||||
219_23164660 R06.0✓ 8 100% PASS 106s
|
||||
21_23111304 K85.1✓ 7 100% NEED_INFO 273s
|
||||
220_23159566 Z01.4✓ 8 100% PASS 153s
|
||||
221_23167859 I62.0✓ 14 100% NEED_INFO 116s
|
||||
222_23139653 Z43.3✓ 13 100% PASS 125s
|
||||
225_23160703 -✗ 6 100% PASS 292s
|
||||
227_23173599 Z51.1✓ 6 100% NEED_INFO 95s
|
||||
230_23167769 R06.0✓ 10 100% NEED_INFO 173s
|
||||
231_23159944 N85.7✓ 6 100% NEED_INFO 97s
|
||||
232_23183311 S22.31✗ 8 100% NEED_INFO 95s
|
||||
234_23174515 G40.9✓ 4 100% NEED_INFO 142s
|
||||
235_23143706 N76✓ 5 100% PASS 124s
|
||||
238_23188172 T88.7✓ 31 100% NEED_INFO 209s
|
||||
239_23188240 T81.38✓ 15 100% PASS 102s
|
||||
241_23188038 Z51.5✓ 9 100% NEED_INFO 190s
|
||||
242_23192524 S32.3✓ 10 100% PASS 95s
|
||||
244_23193317 E78.0✓ 18 100% NEED_INFO 273s
|
||||
246_23193699 S22.31✗ 4 50% NEED_INFO 129s
|
||||
249_23196688 R06.0✓ 16 100% PASS 252s
|
||||
25_23127187 -✗ 8 100% NEED_INFO 109s
|
||||
26_23127395 K85.1✓ 12 100% NEED_INFO 112s
|
||||
29_23137897 -✗ 8 100% PASS 151s
|
||||
2_23044104 K80.0✓ 6 100% NEED_INFO 98s
|
||||
31_23142976 K81.0✓ 7 100% NEED_INFO 99s
|
||||
32_23143161 K81.9✓ 8 100% NEED_INFO 82s
|
||||
33_23150352 K81.0✓ 13 100% NEED_INFO 118s
|
||||
34_23153510 K81.9✓ 6 100% NEED_INFO 83s
|
||||
37_23158940 K81.0✓ 9 100% NEED_INFO 188s
|
||||
38_23162619 K81.9✓ 11 100% FAIL 91s
|
||||
39_23167029 Z29.2✓ 10 100% NEED_INFO 113s
|
||||
40_23168633 K81.0✓ 11 100% NEED_INFO 128s
|
||||
41_23170176 -✗ 8 100% FAIL 149s
|
||||
43_23177057 K81.0✓ 9 100% NEED_INFO 107s
|
||||
46_23187081 K85.9✓ 7 100% NEED_INFO 136s
|
||||
49_23217289 K81.9✓ 5 100% PASS 151s
|
||||
51_23222062 K85.9✓ 20 100% NEED_INFO 158s
|
||||
52_23223407 Z35.9✓ 13 100% NEED_INFO 130s
|
||||
54_23230165 K81.1✓ 16 100% NEED_INFO 306s
|
||||
55_23246490 K81.0✓ 7 100% NEED_INFO 164s
|
||||
56_23248174 K81.0✓ 10 100% NEED_INFO 203s
|
||||
57_23003949 I10✓ 8 100% NEED_INFO 136s
|
||||
58_23084901 R06.0✓ 13 92% NEED_INFO 130s
|
||||
59_23088959 R27.0✓ 2 100% NEED_INFO 104s
|
||||
62_23001636 -✗ 7 100% NEED_INFO 80s
|
||||
63_23001636 -✗ 7 100% NEED_INFO 78s
|
||||
64_23001636 -✗ 7 100% NEED_INFO 74s
|
||||
65_23001636 -✗ 7 100% NEED_INFO 78s
|
||||
66_23001636 -✗ 7 100% NEED_INFO 75s
|
||||
67_23001636 F43.28✓ 15 100% NEED_INFO 208s
|
||||
69_23046068 B96.80✓ 7 100% PASS 81s
|
||||
6_23066847 K81.0✓ 11 82% NEED_INFO 100s
|
||||
71_23135194 -✗ 0 - PASS 28s
|
||||
72_23068111 -✗ 2 100% PASS 72s
|
||||
73_23139637 -✗ 1 100% PASS 55s
|
||||
74_23141536 -✗ 3 100% PASS 68s
|
||||
75_23181227 R21✓ 6 100% NEED_INFO 101s
|
||||
76_23165648 -✗ 6 100% PASS 151s
|
||||
77_23194611 -✗ 7 100% PASS 82s
|
||||
78_23187785 B96.80✓ 7 100% PASS 78s
|
||||
7_23066992 K81.0✓ 16 100% NEED_INFO 142s
|
||||
83_23187785 B96.80✓ 11 100% NEED_INFO 191s
|
||||
84_23215994 L50✓ 4 100% NEED_INFO 66s
|
||||
86_23221334 Z51.30✓ 7 100% NEED_INFO 73s
|
||||
87_23236926 R06.0✓ 13 100% NEED_INFO 154s
|
||||
8_23074520 K80.5✓ 12 100% NEED_INFO 107s
|
||||
90_23011562 -✗ 5 100% PASS 74s
|
||||
92_23049455 S52✓ 18 100% NEED_INFO 203s
|
||||
93_23050151 -✗ 9 100% NEED_INFO 124s
|
||||
94_23000519 -✗ 4 100% PASS 159s
|
||||
96_23044463 K85.1✓ 15 100% PASS 116s
|
||||
99_23033146 -✗ 4 100% PASS 193s
|
||||
9_23077394 K81.8✓ 9 100% FAIL 119s
|
||||
|
||||
==================================================================
|
||||
Reference in New Issue
Block a user