chore: mise à jour output pipeline (anonymized + structured)

Résultats de re-traitement pipeline v2 sur 261 dossiers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-03-07 23:14:42 +01:00
parent c73515ac89
commit 13fe9fa666
734 changed files with 157158 additions and 304963 deletions

View File

@@ -0,0 +1,27 @@
{
"source_file": "CRO 23089771.pdf",
"total_replacements": 14,
"regex_replacements": 9,
"ner_replacements": 3,
"sweep_replacements": 2,
"entities_found": [
{
"original": "CAZENAVE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8503903150558472
},
{
"original": "Foley",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9017308354377747
},
{
"original": "CAZENAVE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9300785064697266
}
]
}

View File

@@ -0,0 +1,267 @@
{
"source_file": "trackare--23089771__23089771.pdf",
"total_replacements": 446,
"regex_replacements": 181,
"ner_replacements": 23,
"sweep_replacements": 242,
"entities_found": [
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089771",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "LAY LAMIDOU",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "2 CAMIN DE LINGORS Ville de résidence: PRECHACQ NAVARRENX",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Urée",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8285486698150635
},
{
"original": "KARAM Lydia S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9321727752685547
},
{
"original": "Patricia LADEVESE",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.996423602104187
},
{
"original": "Patricia LADEVESE",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988711476325989
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9982078671455383
},
{
"original": "Patricia LADEVESE",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9975780248641968
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9799923896789551
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9819852709770203
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9875752329826355
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9809640049934387
},
{
"original": "KARAM Lydia Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9039734601974487
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9938808679580688
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.995265781879425
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9929607510566711
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9582460522651672
},
{
"original": "Patricia TOILETTE",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9885894060134888
},
{
"original": "Sandrine SOMMEIL",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9851348996162415
},
{
"original": "Sandrine POCHE A URINE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9145822525024414
},
{
"original": "Patricia S",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9812343120574951
},
{
"original": "Myriam LEVER",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9824754595756531
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9986081719398499
},
{
"original": "V.Comat",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9704047441482544
},
{
"original": "V.Comat",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8158491849899292
}
]
}