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 +1,75 @@
{
"source_file": "CRH 23080179.pdf",
"total_replacements": 24,
"regex_replacements": 6,
"ner_replacements": 11,
"sweep_replacements": 7,
"entities_found": [
{
"original": "LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9943186044692993
},
{
"original": "Anne-Michèle LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9984066486358643
},
{
"original": "Mme LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8995116353034973
},
{
"original": "ANNE-MICHELE VINOUR",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9979786276817322
},
{
"original": "LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9967586398124695
},
{
"original": "Courrier Epi",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9678772687911987
},
{
"original": "Anne-Michèle LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9987366795539856
},
{
"original": "Anne-Michèle LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9973431825637817
},
{
"original": "ANNE-MICHELE VINOUR",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9359608888626099
},
{
"original": "LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.981849730014801
},
{
"original": "ANNE-MICHELE VINOUR",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.982437014579773
}
]
}

View File

@@ -0,0 +1,579 @@
{
"source_file": "trackare-22025894-23080179_22025894_23080179.pdf",
"total_replacements": 786,
"regex_replacements": 265,
"ner_replacements": 44,
"sweep_replacements": 477,
"entities_found": [
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22025894",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080179",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "240058708511983",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "87085",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "LIMOGES",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "regex",
"category": "patient"
},
{
"original": "MEDECINE HEMATOLOGIE CLINIQUE - HEMATOLOGIE CLINIQUE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "LABADIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "VINOUR",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "ANNE-MICHELE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ANNE-MICHELE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "30 RUE DE CHISDITS Ville de résidence: ANGLET",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9833245277404785
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9950487613677979
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9918746948242188
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9844715595245361
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9566398859024048
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9930834770202637
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9910821914672852
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.881481409072876
},
{
"original": "BERNARD Sophie S",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.934429943561554
},
{
"original": "BERNARD Sophie Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8769797682762146
},
{
"original": "FRIAS Loan",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.985953152179718
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9599860906600952
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9896073341369629
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9938000440597534
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9863641262054443
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.977201521396637
},
{
"original": "BERNARD Sophie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.944551408290863
},
{
"original": "BERNARD Sophie S",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9539334177970886
},
{
"original": "BERNARD Sophie S",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9096810221672058
},
{
"original": "BERNARD",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9067584872245789
},
{
"original": "BERNARD OXYNORMORO",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9974762797355652
},
{
"original": "BERNARD OXYCODONE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9948561191558838
},
{
"original": "BERNARD Sachet",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9406601190567017
},
{
"original": "BERNARD KARDEGIC",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9719505906105042
},
{
"original": "BERNARD CORTANCYL",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9417070150375366
},
{
"original": "BERNARD",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9364290833473206
},
{
"original": "Loan FRIAS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9975985288619995
},
{
"original": "Loan FRIAS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9644712209701538
},
{
"original": "Loan FRIAS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9676364660263062
},
{
"original": "BERNARD CORTANCYL",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9828885197639465
},
{
"original": "BERNARD",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9434835314750671
},
{
"original": "ERNARD VALACICLOVIR",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8688501119613647
},
{
"original": "VALACICLOV",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.902192234992981
},
{
"original": "BERNARD",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9682591557502747
},
{
"original": "BERNARD ATORVASTATINE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9672877788543701
},
{
"original": "BERNARD ATENOLOL",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9844626188278198
},
{
"original": "BERNARD AMLODIPINE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9696051478385925
},
{
"original": "Signé AMLODIPINE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8524819016456604
},
{
"original": "BERNARD POCHE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.825637698173523
},
{
"original": "Mateo LANOE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8555725812911987
},
{
"original": "Mme LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.907958984375
},
{
"original": "Mme LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9203176498413086
},
{
"original": "LABADIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9829868078231812
},
{
"original": "Epoux Labadie Pierre",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8760930895805359
}
]
}