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 +1,57 @@
{
"source_file": "CRH 23090475.pdf",
"total_replacements": 25,
"regex_replacements": 13,
"ner_replacements": 8,
"sweep_replacements": 4,
"entities_found": [
{
"original": "Mr L.",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9072750210762024
},
{
"original": "L.",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9236044883728027
},
{
"original": "Mr L.",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8180763125419617
},
{
"original": "CHRISTIAN",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.916247546672821
},
{
"original": "LAULHE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.978818416595459
},
{
"original": "LAULHE Christian",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.994265079498291
},
{
"original": "CHRISTIAN",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9624900221824646
},
{
"original": "LAULHE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.983837902545929
}
]
}

View File

@@ -0,0 +1,669 @@
{
"source_file": "trackare-BA112518-23090475_BA112518_23090475.pdf",
"total_replacements": 980,
"regex_replacements": 312,
"ner_replacements": 82,
"sweep_replacements": 586,
"entities_found": [
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23090475",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "MONTFORT",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "NEURO CHIRURGIE - NEURO-CHIRURGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "1107 ROUTE DES AUGAS Ville de résidence: OSSERAIN RIVAREYTE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Signé — DOULEUR",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8741652965545654
},
{
"original": "PONTIER Bénédicte Signé",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9415544867515564
},
{
"original": "KOZLOWSKI Mylène",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9981435537338257
},
{
"original": "BASSIN : VIDER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8891696929931641
},
{
"original": "URINAL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9523868560791016
},
{
"original": "Mayalen FOURCADE S",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9737729430198669
},
{
"original": "VIDER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9269788861274719
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9430797696113586
},
{
"original": "URINAL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.90777188539505
},
{
"original": "Mayalen FOURCADE S",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.930924117565155
},
{
"original": "VIDER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9872562289237976
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9934136271476746
},
{
"original": "URINAL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.992556095123291
},
{
"original": "Mayalen FOURCADE Signé",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9941105842590332
},
{
"original": "BASSIN : VIDER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9092208743095398
},
{
"original": "URINAL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9896299839019775
},
{
"original": "Mayalen FOURCADE Signé",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9887235164642334
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9991078972816467
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9991030097007751
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988216161727905
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988480806350708
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9979992508888245
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990430474281311
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990350604057312
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9457171559333801
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9531763792037964
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9034131765365601
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9946664571762085
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9943197965621948
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.994903564453125
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9943469762802124
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9017019271850586
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9794742465019226
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9662227630615234
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9811542630195618
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9347708821296692
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9558764696121216
},
{
"original": "PONTIER Bénédicte S",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9907594919204712
},
{
"original": "PONTIER Bénédicte Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9768101572990417
},
{
"original": "KOZLOWSKI Mylène",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9983136057853699
},
{
"original": "KOZLOWSKI Mylène",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9983606338500977
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9978473782539368
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9989219307899475
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990694522857666
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990355372428894
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990786910057068
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9991047978401184
},
{
"original": "Nathalie Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9763968586921692
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9989910125732422
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9989966154098511
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990493655204773
},
{
"original": "Mayalen FOURCADE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9990814328193665
},
{
"original": "Admin",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.821452260017395
},
{
"original": "LARROUY",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.935584306716919
},
{
"original": "LANSOPRAZOLE",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9155872464179993
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9116268157958984
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9255687594413757
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8980957269668579
},
{
"original": "ACTISKENAN 10MG GELULE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8569947481155396
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9872633814811707
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9944052696228027
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9827243089675903
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.991448700428009
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9964339137077332
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.996141791343689
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9957555532455444
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9958289861679077
},
{
"original": "PONTIER Bénédicte",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.990580141544342
},
{
"original": "PONTIER Bénédicte",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9926777482032776
},
{
"original": "PONTIER Bénédicte Signé",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9744523167610168
},
{
"original": "Mylène Signé",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9598440527915955
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9928697347640991
},
{
"original": "Mayalen Signé",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9969948530197144
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9951748847961426
},
{
"original": "Nathalie",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9248294234275818
},
{
"original": "Céline",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9401717185974121
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9955676198005676
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9961851835250854
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9967508316040039
},
{
"original": "Bénédicte",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9382105469703674
},
{
"original": "Rachis Lombaire F P",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9842202663421631
},
{
"original": "Rachis Lombaire F P",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9699997305870056
}
]
}