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 +1,33 @@
{
"source_file": "CRO 23065570.pdf",
"total_replacements": 11,
"regex_replacements": 6,
"ner_replacements": 4,
"sweep_replacements": 1,
"entities_found": [
{
"original": "Glycocolle",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9711918830871582
},
{
"original": "Storz",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9902713894844055
},
{
"original": "GERARD",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9629125595092773
},
{
"original": "WAGUET",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9921252131462097
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "LETTRE DE SORTIE 23065570.pdf",
"total_replacements": 16,
"regex_replacements": 12,
"ner_replacements": 4,
"sweep_replacements": 0,
"entities_found": [
{
"original": "GERARD",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8710376620292664
},
{
"original": "WAGUET",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9843478798866272
},
{
"original": "GERARD",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9353766441345215
},
{
"original": "WAGUET",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9919029474258423
}
]
}

View File

@@ -0,0 +1,459 @@
{
"source_file": "trackare-23007148-23065570_23007148_23065570.pdf",
"total_replacements": 218,
"regex_replacements": 129,
"ner_replacements": 45,
"sweep_replacements": 44,
"entities_found": [
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23007148",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23065570",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "WATTIGNIES",
"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": "74, RUE HARGUIN ETCHEBERRY - LES PINS Ville de résidence: BIDART",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9630381464958191
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9984448552131653
},
{
"original": "DI LULLO Emilie S",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9534053802490234
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9947584271430969
},
{
"original": "Myriam MAIA S",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8563017249107361
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9980742335319519
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9979953765869141
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.996781587600708
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9488359093666077
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9613009691238403
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8460174202919006
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9890807271003723
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9809007048606873
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9971714615821838
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9926031231880188
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9786313772201538
},
{
"original": "KT COURT",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9741876125335693
},
{
"original": "KT COURT",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9419488906860352
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9624984860420227
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9878983497619629
},
{
"original": "DI LULLO Emilie Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9847502112388611
},
{
"original": "DI LULLO Emilie S",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9864276051521301
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9987573623657227
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9984368681907654
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.99629145860672
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9940854907035828
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9959774017333984
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9967062473297119
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9851195812225342
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9897370338439941
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9914687275886536
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9784114360809326
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9931516647338867
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.986736536026001
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8777607083320618
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8134344816207886
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8414351940155029
},
{
"original": "Myriam TOILETTE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9900498986244202
},
{
"original": "Emilie DI SOMMEIL",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9960965514183044
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8774508237838745
},
{
"original": "C.Klein Stephanie",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9933465719223022
},
{
"original": "Y.Lammertyn",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9985957145690918
},
{
"original": "Dufour",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8024475574493408
},
{
"original": "Y.Lammertyn",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.992201566696167
},
{
"original": "Fils waguet vincent",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9795106649398804
}
]
}