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 +1,705 @@
{
"source_file": "trackare-BA091887-23067053_BA091887_23067053.pdf",
"total_replacements": 700,
"regex_replacements": 263,
"ner_replacements": 79,
"sweep_replacements": 358,
"entities_found": [
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23067053",
"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": "VERDOUX",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "VERDOUX",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "VERDOUX",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "SACHA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "SACHA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "SACHA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "2 BIS RUE DES BASQUES Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "VERDOUX SACHA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9629415273666382
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9205490946769714
},
{
"original": "SCANNER ABDOMINO-PELVIEN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9116669297218323
},
{
"original": "REDON",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8052939176559448
},
{
"original": "PAUCHET Marine",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9906409978866577
},
{
"original": "REDON",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8885617852210999
},
{
"original": "DALIA Amaïa",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.996063232421875
},
{
"original": "VIDER",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9062470197677612
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9636437296867371
},
{
"original": "URINAL",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9543399810791016
},
{
"original": "VIDER",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8384034633636475
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9584279656410217
},
{
"original": "URINAL",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9401583671569824
},
{
"original": "PUJOS Marion",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.8946358561515808
},
{
"original": "PUJOS Marion 50MG",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.8613441586494446
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.8934946656227112
},
{
"original": "SP PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.8703517317771912
},
{
"original": "DISP PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.818459689617157
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9378890991210938
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9514188170433044
},
{
"original": "LANSOPRAZOLE",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9079835414886475
},
{
"original": "DIAZEPAM",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.8853098750114441
},
{
"original": "Ttes PAUCHET Marine",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9851967692375183
},
{
"original": "PAUCHET Marine",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9863231778144836
},
{
"original": "DALIA Amaïa S",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9789600372314453
},
{
"original": "VIDER",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8486316204071045
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.939128577709198
},
{
"original": "URINAL",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9201362133026123
},
{
"original": "PUJOS Marion",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.8797610402107239
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.885847270488739
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9079437255859375
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9627523422241211
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.8984573483467102
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9780623912811279
},
{
"original": "PETIT Bastien",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9717583656311035
},
{
"original": "LANSOPRAZOLE BGA",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.8847426176071167
},
{
"original": "LANSOPRAZOLE BGA",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.930950939655304
},
{
"original": "Lucie Signé",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8633708953857422
},
{
"original": "Marion Signé",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.8712155222892761
},
{
"original": "Lucie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.92759108543396
},
{
"original": "Marion ME",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.8040288686752319
},
{
"original": "Lucie S",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8608745336532593
},
{
"original": "LOUIS LANSOPRAZOLE",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9072945713996887
},
{
"original": "Lucie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9274798035621643
},
{
"original": "Bastien TA",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9632818102836609
},
{
"original": "Bastien DOULEUR",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9974149465560913
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.894702136516571
},
{
"original": "Amaïa URINAL",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9961187839508057
},
{
"original": "Amaïa TOILETTE",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9980056881904602
},
{
"original": "Karine SOMMEIL",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9963452219963074
},
{
"original": "Amaïa S",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9628382325172424
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9825844168663025
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.989147424697876
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9875215888023376
},
{
"original": "Baptiste SAUDE",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9972168803215027
},
{
"original": "Anaïs CARRAZÉ",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9930578470230103
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.998643696308136
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9988221526145935
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9988806843757629
},
{
"original": "Lucie LOUIS",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9977446794509888
},
{
"original": "Lucie LOUIS",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9970213174819946
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9987432360649109
},
{
"original": "Lucie LOUIS",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9986998438835144
},
{
"original": "Lucie LOUIS",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9987237453460693
},
{
"original": "Baptiste SAUDE",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.8621145486831665
},
{
"original": "Lucie LOUIS",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9889270067214966
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9680245518684387
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.8209328651428223
},
{
"original": "Baptiste SAUDE",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9842292070388794
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9902257323265076
},
{
"original": "Anaïs CARRAZÉ",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9498961567878723
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.997784435749054
},
{
"original": "ACUPAN NEFOPAM",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8074590563774109
},
{
"original": "Baptiste SAUDE",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9974888563156128
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9971795082092285
},
{
"original": "Bastien PETIT",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.996944010257721
},
{
"original": "Fatiha CHABANE",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9981034398078918
},
{
"original": "Nolwenn BARRE",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9974069595336914
},
{
"original": "Baptiste SAUDE",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9953290820121765
}
]
}