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 +1,99 @@
{
"source_file": "CONSULTATION ANESTHESISTE 23076325.pdf",
"total_replacements": 49,
"regex_replacements": 23,
"ner_replacements": 9,
"sweep_replacements": 17,
"entities_found": [
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "10 AVENUE ARRIBE LABOURD N° Tél : [TEL_1]",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "10 AVENUE ARRIBE LABOURD N° Tél : [TEL_1]",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "10 AVENUE ARRIBE LABOURD N° Tél : [TEL_1]",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9931486248970032
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9972968101501465
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9972360730171204
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9965100288391113
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.99688321352005
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971278309822083
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9972590804100037
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9967830777168274
},
{
"original": "Emma CLOT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9841024875640869
}
]
}

View File

@@ -0,0 +1,21 @@
{
"source_file": "CRO 23076325.pdf",
"total_replacements": 8,
"regex_replacements": 6,
"ner_replacements": 2,
"sweep_replacements": 0,
"entities_found": [
{
"original": "JEAN-PIERRE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9123525023460388
},
{
"original": "ARTIGOLLES",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9096448421478271
}
]
}

View File

@@ -0,0 +1,471 @@
{
"source_file": "trackare-99247048-23076325_99247048_23076325.pdf",
"total_replacements": 340,
"regex_replacements": 145,
"ner_replacements": 39,
"sweep_replacements": 156,
"entities_found": [
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "99247048",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23076325",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "CADILLAC",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "ONCOLOGIE - ONCOLOGIE HC\nDossier Patient\nDétails des patients",
"replacement": "[MEDECIN_7]",
"source": "regex",
"category": "patient"
},
{
"original": "10 AVENUE ARRIBE LABOURD Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9855577945709229
},
{
"original": "Thromb Haemost",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8430347442626953
},
{
"original": "Becker",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9957026243209839
},
{
"original": "Jan Steffel",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9987741708755493
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9990929365158081
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9990315437316895
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9980223178863525
},
{
"original": "LANSOPRAZOLE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.93496173620224
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9896462559700012
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.982775092124939
},
{
"original": "Emma",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8820281624794006
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9792396426200867
},
{
"original": "Emma",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8995951414108276
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9740495681762695
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9990929365158081
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9990315437316895
},
{
"original": "Stephanie REGNIER",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9980223178863525
},
{
"original": "Emma",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8743582367897034
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9435345530509949
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9490518569946289
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9425462484359741
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9703429341316223
},
{
"original": "CLOT Emma",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9318487048149109
},
{
"original": "Mathilde",
"replacement": "[MEDECIN_16]",
"source": "ner",
"score": 0.9085547924041748
},
{
"original": "Clémentine TOILETTE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9830829501152039
},
{
"original": "Stephanie SOMMEIL",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9955893158912659
},
{
"original": "Clémentine S",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.8834900856018066
},
{
"original": "Clémentine ENVIRONNEMENT",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9818625450134277
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9921607971191406
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9935626983642578
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9927766919136047
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9911680817604065
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9914994835853577
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9866821765899658
},
{
"original": "Emma CLOT",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.9899351000785828
},
{
"original": "Emma CLOT C",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8499569296836853
},
{
"original": "Emma CLOT GEL",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8680211901664734
},
{
"original": "Emma CLOT GELULE",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8501312136650085
},
{
"original": "ENFORTUMAB VEDOTIN",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9431033134460449
}
]
}