Files
anonymisation/regression_tests/baseline/CRH 23127286.audit.jsonl
Domi31tls bc2fe667a0 fix: Corrections qualité Phase 1 — 261 fuites en moins, 0 régression
Audit sur 30 fichiers aléatoires (OGC 12-690) révélant un overfitting
sur les 59 premiers OGC. Corrections appliquées avec test de non-régression
à chaque étape :

- NDA pieds de page Trackare : regex Episode N. (227→0 fuites)
- ONDANSETRON : word boundary \b sur RE_NUMERO_DOSSIER (32→0)
- RPPS isolés : détection 11 chiffres dans docs Trackare (3→0)
- Stop words : retrait noms réels (ute, dogue, cambo, bains), ajout
  termes médicaux (AINS, ponction, hanche, burkitt, ORL, GDS, OAP...)
- Pattern DR. Prénom NOM : capture prénoms médecins (Ute ×19, Tam...)
- force_names : contextes structurés (DR., Signé, Note d'évolution)
  bypassent les stop words pour masquer les vrais noms de soignants
- Phase 2b : PiiHit trackare (EPISODE, RPPS) appliqués au texte .txt
- Framework de non-régression (regression_tests/) + batch audit 30 fichiers

Résultat : 322→61 fuites détectées, 113→109 faux positifs, 0 régression.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 17:32:28 +01:00

65 lines
6.9 KiB
JSON

{"page": 0, "kind": "force_term", "original": "CENTRE HOSPITALIER COTE BASQUE", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 0, "kind": "ETAB", "original": "Pôle Spécialités Médicales", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 0, "kind": "ETAB", "original": "Service de Gastro-Entérologie - Oncologie Digestive", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Christelle Béraut", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Thomas Grellety", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "faudemar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "BOUBE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "mboube@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "BRUGEL", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "mcboudier@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "GOUTORBE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Absce", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "fgoutorbe@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "aguilngar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "tkhuong-huu@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "dnivet@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "oui@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "RPPS", "original": "10100532760", "placeholder": "[RPPS]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "fprevost@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "IPP", "original": "21020800", "placeholder": "[IPP]", "bbox_hint": null}
{"page": 0, "kind": "EPISODE", "original": "N° Episode 23127286", "placeholder": "[EPISODE]", "bbox_hint": null}
{"page": 1, "kind": "force_term", "original": "CENTRE HOSPITALIER COTE BASQUE", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 1, "kind": "ETAB", "original": "Pôle Spécialités Médicales", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 1, "kind": "ETAB", "original": "Service de Gastro-Entérologie - Oncologie Digestive", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "Christelle Béraut", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "PELLERIN-GUIGNARD Aude", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "audemar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "BOUBE Anthibiothérapie", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "mboube@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "BRUGEL ATB", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "brugel@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "mcboudier@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "fgoutorbe@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "PUJOS", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "aguilngar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "tkhuong-huu@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "dnivet@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "boui@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "RPPS", "original": "10100532760", "placeholder": "[RPPS]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "fprevost@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "PUJOS Marion", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "IPP", "original": "21020800", "placeholder": "[IPP]", "bbox_hint": null}
{"page": 1, "kind": "EPISODE", "original": "N° Episode 23127286", "placeholder": "[EPISODE]", "bbox_hint": null}
{"page": 2, "kind": "force_term", "original": "CENTRE HOSPITALIER COTE BASQUE", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 2, "kind": "ETAB", "original": "Pôle Spécialités Médicales", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 2, "kind": "ETAB", "original": "Service de Gastro-Entérologie - Oncologie Digestive", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 2, "kind": "NOM", "original": "Christelle Béraut", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 2, "kind": "NOM", "original": "Thomas Grellety", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 2, "kind": "NOM", "original": "AUDEMAR Franck", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "faudemar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "NOM", "original": "BOUBE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "mboube@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "NOM", "original": "BRUGEL Rédigé", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "mbrugel@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "mcboudier@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "fgoutorbe@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "aguilngar@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "tkhuong-huu@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "dnivet@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "boui@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "RPPS", "original": "10100532760", "placeholder": "[RPPS]", "bbox_hint": null}
{"page": 2, "kind": "EMAIL", "original": "fprevost@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 2, "kind": "IPP", "original": "21020800", "placeholder": "[IPP]", "bbox_hint": null}
{"page": 2, "kind": "EPISODE", "original": "N° Episode 23127286", "placeholder": "[EPISODE]", "bbox_hint": null}