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 +1,111 @@
{
"source_file": "CRH 23104930.pdf",
"total_replacements": 260,
"regex_replacements": 229,
"ner_replacements": 9,
"sweep_replacements": 22,
"entities_found": [
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "10100673481",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10100673481",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "COUECOU",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9347784519195557
},
{
"original": "LATASTE Philippe",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9790590405464172
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9850517511367798
},
{
"original": "DUTHEIL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9912126064300537
},
{
"original": "VAREIL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9351510405540466
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.857990026473999
},
{
"original": "DUTHEIL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9826241135597229
},
{
"original": "LATASTE Philippe",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9832078814506531
},
{
"original": "Ch",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8009895086288452
}
]
}

View File

@@ -0,0 +1,27 @@
{
"source_file": "LETTRE DE SORTIE 23104930.pdf",
"total_replacements": 10,
"regex_replacements": 7,
"ner_replacements": 3,
"sweep_replacements": 0,
"entities_found": [
{
"original": "Consoeur",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9599111080169678
},
{
"original": "PHILIPPE",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.959543764591217
},
{
"original": "LATASTE",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9936079978942871
}
]
}

View File

@@ -0,0 +1,651 @@
{
"source_file": "trackare-BA132287-23104930_BA132287_23104930.pdf",
"total_replacements": 526,
"regex_replacements": 190,
"ner_replacements": 81,
"sweep_replacements": 255,
"entities_found": [
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23104930",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "164076412201856",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64122",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BIARRITZ",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "LATASTE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "LATASTE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PHILIPPE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PHILIPPE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "5 CHEMIN PEMARTIA Ville de résidence: ARBONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "DEROURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9333222508430481
},
{
"original": "Marie GEL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9098491072654724
},
{
"original": "Marie GELULE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.804962694644928
},
{
"original": "Marie GELULE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9781444072723389
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9859614968299866
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.997797429561615
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9977110028266907
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.998440682888031
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9983770251274109
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9983860850334167
},
{
"original": "MAJCHRZAK Camille Marie Signé",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9982272386550903
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9409041404724121
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9979051947593689
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9974719882011414
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9831815361976624
},
{
"original": "COVERSYL",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8377177715301514
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9227828979492188
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9868948459625244
},
{
"original": "MAJCHRZAK Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.985550045967102
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9656076431274414
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9700787663459778
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9639666080474854
},
{
"original": "AJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8992815017700195
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8748804330825806
},
{
"original": "Marie S",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8457901477813721
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9311989545822144
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9837309718132019
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.934281587600708
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9692645072937012
},
{
"original": "MAJCHRZAK Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9971975684165955
},
{
"original": "EZETIMIBE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8244457244873047
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9428368210792542
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9942854046821594
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8199928402900696
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9915275573730469
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9817392230033875
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9957507252693176
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9468691945075989
},
{
"original": "Marie ORALE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9834594130516052
},
{
"original": "Marie GLYCEMIQUE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9943030476570129
},
{
"original": "Marie",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.82159024477005
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9841096997261047
},
{
"original": "SDZ Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9251599311828613
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9958953261375427
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.998702347278595
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.998700737953186
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987160563468933
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9986926317214966
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987126588821411
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987162947654724
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9986305236816406
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987345933914185
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987167119979858
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987069368362427
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9986969232559204
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987156987190247
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987068772315979
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9987294673919678
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.974265456199646
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9505290985107422
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8925602436065674
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.819794774055481
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9289822578430176
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9726780652999878
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9554898738861084
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9653987884521484
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9714852571487427
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8670374155044556
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8634601831436157
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8934236764907837
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8782187700271606
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9028197526931763
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9604161381721497
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9659610986709595
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9732123613357544
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9749950766563416
},
{
"original": "MAJCHRZAK FORXIGA",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.921416163444519
},
{
"original": "Maider",
"replacement": "[MEDECIN_15]",
"source": "ner",
"score": 0.8264182806015015
},
{
"original": "Valerie ELIZALDE",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9957695007324219
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8706313967704773
},
{
"original": "LAGNAOUI",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.862945556640625
}
]
}