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 +1,495 @@
{
"source_file": "trackare-00255524-23101667_00255524_23101667.pdf",
"total_replacements": 423,
"regex_replacements": 174,
"ner_replacements": 40,
"sweep_replacements": 209,
"entities_found": [
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00255524",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23101667",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "190014008803843",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "40088",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "DAX",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "EJNAINI Cecilia",
"replacement": "[MEDECIN_3]",
"source": "regex",
"category": "patient"
},
{
"original": "MEDECINE PNEUMOLOGIE - PNEUMOLOGIE PHTISIOLOGIE HC\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "LAUGA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "LAUGA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ALEXANDRE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ALEXANDRE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "18 RUE SANTOS SUARES Ville de résidence: ANGLET",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "MOUZA Virgile",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9775162935256958
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9232155084609985
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9458649754524231
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9849100708961487
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.983391284942627
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9777557849884033
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9819741249084473
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8237936496734619
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9729884266853333
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8970725536346436
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.978377640247345
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9981799125671387
},
{
"original": "Cécilia G",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.983119785785675
},
{
"original": "Cécilia G",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9718755483627319
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.996579647064209
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9954967498779297
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9914305806159973
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9726717472076416
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9717128276824951
},
{
"original": "Francois",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9486550688743591
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8921898007392883
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9218671321868896
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9302792549133301
},
{
"original": "Francois Réalisé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.908928394317627
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9949730038642883
},
{
"original": "ise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9818742871284485
},
{
"original": "Elise ABRAHAM 50MG",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8564846515655518
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9983744621276855
},
{
"original": "MG NOCENT-EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.805498480796814
},
{
"original": "Cécilia G",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8735436201095581
},
{
"original": "G NOCENT-EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8625345230102539
},
{
"original": "Cécilia G",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8379915356636047
},
{
"original": "1000 MG NOCENT-EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9419592022895813
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8695545792579651
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9970526695251465
},
{
"original": "Elise ABRAHAM",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9980584979057312
},
{
"original": "NOCENT-EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9718979597091675
},
{
"original": "Pelvien EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9972524642944336
},
{
"original": "Jeanne LEMOINE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.854840874671936
},
{
"original": "NOCENT-EJNAINI",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9959381818771362
}
]
}