Files
anonymisation/regression_tests/baseline/CRH 23173599.audit.jsonl
Domi31tls e967a67052 feat(phase2): Extraction layout-aware multi-colonnes — 322 fuites → 0, -103 FP
Phase 2 de l'amélioration qualité anonymisation :

1. Extraction multi-colonnes (PyMuPDF layout-aware) :
   - Nouvelle fonction _extract_page_layout_aware() détecte les layouts
     sidebar+corps (typiques des CRH/CRO hospitaliers)
   - Remplace pdfplumber comme extraction primaire (PyMuPDF blocks)
   - Élimine l'entrelacement de texte entre sidebar et corps médical
   - pdfplumber conservé pour les tables et comme fallback

2. Masquage FINESS multiline :
   - Détection "N° Finess\n[...]\n640000162" (label et numéro séparés)
   - Propagation globale du numéro FINESS sur toutes les pages
   - Gestion du format *640000162* (avec astérisques Trackare)

3. Masquage URLs hospitalières (www.ch-xxx.fr)

4. Nettoyage crochets doubles [[PLACEHOLDER]] → [PLACEHOLDER]

Résultats non-régression (30 fichiers audit) :
- Fuites : 322 → 0 (-100%)
- Faux positifs : 113 → 10 (-91%)
- 0 régression fonctionnelle
- OGC 1-59 : 0 fuite soignant, 0 FINESS, 0 lieu de naissance

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 18:19:08 +01:00

30 lines
3.2 KiB
JSON

{"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": "secr.onco@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "secr.oncogenetique@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 0, "kind": "EMAIL", "original": "secr.hdjcancero@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"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 d'Oncologie Médicale et Oncogénétique", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "LASSERRE SENNE BRIGITTE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "ADRESSE", "original": "150 ALLEE DE BIELLENAVE", "placeholder": "[ADRESSE]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64200 BASSUSSARRY", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "DATE_NAISSANCE", "original": "née le 01/02/1980", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "MAJOUFRE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Toulmonde", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "IPP", "original": "23018342", "placeholder": "[IPP]", "bbox_hint": null}
{"page": 0, "kind": "EPISODE", "original": "23173599", "placeholder": "[EPISODE]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "Christelle Béraut", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "Thomas Grellety", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "secr.onco@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "secr.oncogenetique@ch-cotebasque.fr", "placeholder": "[EMAIL]", "bbox_hint": null}
{"page": 1, "kind": "EMAIL", "original": "secr.hdjcancero@ch-cotebasque.fr", "placeholder": "[EMAIL]", "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 d'Oncologie Médicale et Oncogénétique", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "DA SILVA Fabio", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "FRANCOIS Louis", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "NOM", "original": "LASSERRE SENNE Brigitte", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 1, "kind": "IPP", "original": "23018342", "placeholder": "[IPP]", "bbox_hint": null}
{"page": 1, "kind": "EPISODE", "original": "23173599", "placeholder": "[EPISODE]", "bbox_hint": null}