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 +1,231 @@
{
"source_file": "CRH 23128579.pdf",
"total_replacements": 115,
"regex_replacements": 111,
"ner_replacements": 4,
"sweep_replacements": 0,
"entities_found": [
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.9983623027801514
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.9985945224761963
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.9792216420173645
},
{
"original": "MAQUE Rosine",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.987761914730072
}
]
}

View File

@@ -0,0 +1,333 @@
{
"source_file": "trackare-98213116-23128579_98213116_23128579.pdf",
"total_replacements": 299,
"regex_replacements": 127,
"ner_replacements": 26,
"sweep_replacements": 146,
"entities_found": [
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98213116",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23128579",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "AGEN",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "MEDECINE PNEUMOLOGIE - PNEUMOLOGIE PHTISIOLOGIE HC\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "29 CHEMIN LARRONDOA Ville de résidence: ARBONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9791551232337952
},
{
"original": "Laure CURUTCHET",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9982703328132629
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9892950057983398
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9903517961502075
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9904323816299438
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9885579943656921
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9913236498832703
},
{
"original": "RIGAUD Pierre",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9842896461486816
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9892628788948059
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9915714859962463
},
{
"original": "Michèle Danielle",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9789648056030273
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9973495006561279
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9802982807159424
},
{
"original": "RIGAUD Pierre Signé",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9422356486320496
},
{
"original": "Leslie",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.862275242805481
},
{
"original": "Sylvie",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.8037781119346619
},
{
"original": "Leslie CHANGES",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9563075304031372
},
{
"original": "Isabelle CHAISE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9707813262939453
},
{
"original": "Sheila PELAEZ DEL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9886718392372131
},
{
"original": "DICASTILLO-",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9107702374458313
},
{
"original": "Olatz LOPEZ-DE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9955052137374878
},
{
"original": "MV DICASTILLO-",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8949997425079346
},
{
"original": "Olatz LOPEZ-DE-",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9683552980422974
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9927632808685303
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9931846261024475
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9925909638404846
}
]
}