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 +1,15 @@
{
"source_file": "CRO 23070126.pdf",
"total_replacements": 19,
"regex_replacements": 12,
"ner_replacements": 1,
"sweep_replacements": 6,
"entities_found": [
{
"original": "Valsalva",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9223096966743469
}
]
}

View File

@@ -0,0 +1,15 @@
{
"source_file": "LETTRE DE SORTIE 23070126.pdf",
"total_replacements": 12,
"regex_replacements": 7,
"ner_replacements": 1,
"sweep_replacements": 4,
"entities_found": [
{
"original": "MARIE BARETS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9961349368095398
}
]
}

View File

@@ -0,0 +1,507 @@
{
"source_file": "trackare-23008053-23070126_23008053_23070126.pdf",
"total_replacements": 767,
"regex_replacements": 281,
"ner_replacements": 30,
"sweep_replacements": 456,
"entities_found": [
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23008053",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23070126",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BAYONNE",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "NEURO CHIRURGIE - NEURO-CHIRURGIE\nDossier Patient\nDétails des patients",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "BARETS",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PRIGENT",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "MARIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MARIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "SOULT",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9692749977111816
},
{
"original": "ETRILLARD Joelle",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9935629367828369
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9717162251472473
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9958847165107727
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9944761395454407
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9444796442985535
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9258204698562622
},
{
"original": "DUFOUR Eric",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9766880869865417
},
{
"original": "ETRILLARD Joelle",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9781767725944519
},
{
"original": "8MG LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9902812838554382
},
{
"original": "SETOFILM",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.946992039680481
},
{
"original": "8MG LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9561477303504944
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9128543734550476
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9322282671928406
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9940226674079895
},
{
"original": "OXYNORMORO 5MG",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9142409563064575
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9903768301010132
},
{
"original": "DUFOUR Eric",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8592327237129211
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9475989937782288
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9035035371780396
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.847119927406311
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8393056392669678
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9501321315765381
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9578136205673218
},
{
"original": "BILLON",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9491001963615417
},
{
"original": "Ximun DOULEUR",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.8975906372070312
},
{
"original": "Mayalen SOMMEIL",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.8435786366462708
},
{
"original": "Anne Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.902783215045929
},
{
"original": "Emeline",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8793916702270508
},
{
"original": "Anne Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9036868214607239
}
]
}