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": "CONSULTATION ANESTHESISTE 23057452.pdf",
"total_replacements": 19,
"regex_replacements": 18,
"ner_replacements": 0,
"sweep_replacements": 1,
"entities_found": [
{
"original": "23602122",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23602122",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "12 RUE DE LA VIGNE C6-1 N° Tél : [TEL_1]",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "12 RUE DE LA VIGNE C6-1 N° Tél : [TEL_1]",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
}
]
}

View File

@@ -0,0 +1,963 @@
{
"source_file": "trackare-00260062-23057452_00260062_23057452.pdf",
"total_replacements": 1191,
"regex_replacements": 474,
"ner_replacements": 82,
"sweep_replacements": 635,
"entities_found": [
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00260062",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23057452",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "160106444513695",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64445",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "PAU",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CAILLAUD Philippe",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "NEURO CHIRURGIE - NEURO-CHIRURGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "FILBET",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "FILBET",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MICHEL",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MICHEL",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "12 RUE DE LA VIGNE C6-1 Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9976913928985596
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8785708546638489
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9945177435874939
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9948644638061523
},
{
"original": "Elysa Glyc",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9717215895652771
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9959219694137573
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.993424117565155
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.895947277545929
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9224967956542969
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9797381162643433
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9699846506118774
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9879494905471802
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9846400022506714
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9935542941093445
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9373266100883484
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9297730326652527
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9268823266029358
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9137579798698425
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9079095721244812
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8821983337402344
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8824493288993835
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8603456616401672
},
{
"original": "Admin",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8908118605613708
},
{
"original": "SANGLA Christophe",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.975037693977356
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9086807370185852
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9933961033821106
},
{
"original": "GANFORT",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.873101532459259
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9967657327651978
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9958779215812683
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9938004016876221
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9943928718566895
},
{
"original": "AVIER Elysa Glyc",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.8653135895729065
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9959219694137573
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.993424117565155
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.895947277545929
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9233528971672058
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9797381162643433
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9699846506118774
},
{
"original": "Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9884617924690247
},
{
"original": "AVIER Elysa SURV",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.8637639284133911
},
{
"original": "FAVIER Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9939181208610535
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9373266100883484
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9297730326652527
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9268823266029358
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9137579798698425
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9079095721244812
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8821983337402344
},
{
"original": "BASSIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8824493288993835
},
{
"original": "URINAL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8603456616401672
},
{
"original": "Admin",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.870762288570404
},
{
"original": "SANGLA Christophe",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.973049521446228
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9147738814353943
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9912863373756409
},
{
"original": "CAILLAUD",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9346441626548767
},
{
"original": "CAILLAUD",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8624403476715088
},
{
"original": "CAILLAUD",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9078077673912048
},
{
"original": "CAILLAUD GANFORT",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9320559501647949
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.95980304479599
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.948025107383728
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9808709025382996
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9984903335571289
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9975500106811523
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9931644797325134
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9973407983779907
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9627251625061035
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.977456271648407
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9531542658805847
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9973878860473633
},
{
"original": "Christophe URINAL",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9864633679389954
},
{
"original": "Christophe Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9924430847167969
},
{
"original": "Christophe SOMMEIL",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.991442084312439
},
{
"original": "Sandrine SOMMEIL",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9922197461128235
},
{
"original": "Christophe",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.8465650677680969
},
{
"original": "Christophe Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.8695938587188721
},
{
"original": "Elysa Signé",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9896430969238281
},
{
"original": "Christophe",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.8820890784263611
},
{
"original": "Elysa",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9708137512207031
},
{
"original": "DR.",
"replacement": "[MEDECIN_12]",
"source": "ner",
"score": 0.8003078699111938
},
{
"original": "Christophe Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.8203422427177429
},
{
"original": "LAGARRIGUE",
"replacement": "[SOIGNANT_18]",
"source": "ner",
"score": 0.9930512309074402
},
{
"original": "Sortie CAILLAUD",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9620526432991028
},
{
"original": "DURANTEAU",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.959202229976654
}
]
}