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 +1,39 @@
{
"source_file": "CRO 23041413.pdf",
"total_replacements": 20,
"regex_replacements": 12,
"ner_replacements": 5,
"sweep_replacements": 3,
"entities_found": [
{
"original": "STEPHANIE PETITBERGHIEN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9941082000732422
},
{
"original": "CROp Epi",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8754720687866211
},
{
"original": "Ma DAMESTOY",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9694178700447083
},
{
"original": "STEPHANIE PETITBERGHIEN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9925380349159241
},
{
"original": "DAMESTOY",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9435997605323792
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "LETTRE DE SORTIE 23041413.pdf",
"total_replacements": 13,
"regex_replacements": 7,
"ner_replacements": 4,
"sweep_replacements": 2,
"entities_found": [
{
"original": "Madame D.",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8479330539703369
},
{
"original": "Madame D.",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9781109690666199
},
{
"original": "STEPHANIE PETITBERGHIEN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9964137673377991
},
{
"original": "DAMESTOY",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9852885603904724
}
]
}

View File

@@ -0,0 +1,555 @@
{
"source_file": "trackare-98215606-23041413_98215606_23041413.pdf",
"total_replacements": 713,
"regex_replacements": 320,
"ner_replacements": 31,
"sweep_replacements": 362,
"entities_found": [
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98215606",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23041413",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "ST CALAIS",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "LAGUERRE Daniel",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "NEURO CHIRURGIE - NEURO-CHIRURGIE\nDossier Patient\nDétails des patients",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "DAMESTOY",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PETITBERGHIEN",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "STEPHANIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "STEPHANIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "54 RUE DE GASCOGNE Ville de résidence: URT",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "DEROURE BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9965466856956482
},
{
"original": "ETCHEVERRY Ximun S",
"replacement": "[MEDECIN_14]",
"source": "ner",
"score": 0.9475589990615845
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9829630851745605
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9569810628890991
},
{
"original": "ETCHEVERRY Ximun",
"replacement": "[MEDECIN_14]",
"source": "ner",
"score": 0.9704467058181763
},
{
"original": "Romain",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8906518220901489
},
{
"original": "Romain Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8334322571754456
},
{
"original": "Sabrina",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8857340216636658
},
{
"original": "Sabrina PEZOINBOURE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.998859703540802
},
{
"original": "Sabrina PEZOINBOURE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9988092184066772
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9811673164367676
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9793208241462708
},
{
"original": "LAGUERRE Daniel",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9779546856880188
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9952855706214905
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.99317467212677
},
{
"original": "ETCHEVERRY Ximun",
"replacement": "[MEDECIN_14]",
"source": "ner",
"score": 0.9417867660522461
},
{
"original": "Romain Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9968351721763611
},
{
"original": "Romain Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.996618926525116
},
{
"original": "Romain Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.96902996301651
},
{
"original": "Sabrina PEZOINBOURE Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.948182225227356
},
{
"original": "Sabrina PEZOINBOURE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9985249638557434
},
{
"original": "Sabrina PEZOINBOURE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9984105229377747
},
{
"original": "Sabrina PEZOINBOURE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9982220530509949
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9818947911262512
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9798343181610107
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9498174786567688
},
{
"original": "Mayalen",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.853813648223877
},
{
"original": "Ximun",
"replacement": "[MEDECIN_14]",
"source": "ner",
"score": 0.8196828365325928
},
{
"original": "Ximun",
"replacement": "[MEDECIN_14]",
"source": "ner",
"score": 0.8030533790588379
},
{
"original": "Emeline",
"replacement": "[MEDECIN_13]",
"source": "ner",
"score": 0.894724428653717
},
{
"original": "D Laguerre",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9174952507019043
}
]
}