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 23030611.pdf",
"total_replacements": 13,
"regex_replacements": 9,
"ner_replacements": 4,
"sweep_replacements": 0,
"entities_found": [
{
"original": "CHRISTINE GILSOUL",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9875739812850952
},
{
"original": "Clara GUINARD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9970749020576477
},
{
"original": "AZCARATE Céline",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9884445071220398
},
{
"original": "CHRISTINE GILSOUL",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9946831464767456
}
]
}

View File

@@ -0,0 +1,579 @@
{
"source_file": "trackare-22023521-23030611_22023521_23030611.pdf",
"total_replacements": 458,
"regex_replacements": 218,
"ner_replacements": 53,
"sweep_replacements": 187,
"entities_found": [
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22023521",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23030611",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "RETY",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GYNECOLOGIE BAYONNE - GYNECOLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "48 ZERRANTEIKO BIDEA Ville de résidence: ANHAUX",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "DEROURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9824236035346985
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8346258997917175
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9612391591072083
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9578873515129089
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.971788227558136
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9712385535240173
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8614463210105896
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9134103655815125
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9923645853996277
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9930108189582825
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9962250590324402
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9612391591072083
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9579647183418274
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.971788227558136
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9712385535240173
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8614463210105896
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9086647033691406
},
{
"original": "Clara",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.8308969736099243
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8184829354286194
},
{
"original": "Bastien S",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8316471576690674
},
{
"original": "PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8182104229927063
},
{
"original": "Bastien DOULEUR",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9955763816833496
},
{
"original": "David SOMMEIL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9759637713432312
},
{
"original": "Myriam S",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9399369955062866
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.816950261592865
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8463504314422607
},
{
"original": "Myriam A JEUN",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.806351900100708
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9983677268028259
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9980495572090149
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.99885493516922
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9988800883293152
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9988966584205627
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9988239407539368
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9986073970794678
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9986230731010437
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.998491108417511
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.997871458530426
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9979189038276672
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9820654392242432
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9670761227607727
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9547212719917297
},
{
"original": "Agnes SAINT-",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9820276498794556
},
{
"original": "Agnes SAINT-",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9382228255271912
},
{
"original": "Dr SG",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9035184979438782
},
{
"original": "Dr SG",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9574193358421326
},
{
"original": "Apyrétique",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9492278695106506
},
{
"original": "S.Gheck",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9985486268997192
},
{
"original": "S.Barbe",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9985048174858093
},
{
"original": "S.Barbe",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9819813966751099
},
{
"original": "S.Barbe",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9916728138923645
},
{
"original": "Dr SG",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8128250241279602
},
{
"original": "SG",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9238499402999878
},
{
"original": "SG",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8714911937713623
}
]
}