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 +1,39 @@
{
"source_file": "CONSULTATION ANESTHESISTE 23105969.pdf",
"total_replacements": 19,
"regex_replacements": 16,
"ner_replacements": 1,
"sweep_replacements": 2,
"entities_found": [
{
"original": "23657504",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23657504",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Crestor",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8440092206001282
}
]
}

View File

@@ -0,0 +1,27 @@
{
"source_file": "CRO 23105969.pdf",
"total_replacements": 12,
"regex_replacements": 8,
"ner_replacements": 3,
"sweep_replacements": 1,
"entities_found": [
{
"original": "CABANNES",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.8035020232200623
},
{
"original": "LAURENT",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.8547818064689636
},
{
"original": "CABANNES",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.954921543598175
}
]
}

View File

@@ -0,0 +1,777 @@
{
"source_file": "trackare-22007584-23105969_22007584_23105969.pdf",
"total_replacements": 497,
"regex_replacements": 180,
"ner_replacements": 90,
"sweep_replacements": 227,
"entities_found": [
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22007584",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23105969",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "REIMS",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "17 CHEMIN DE L HYDRO Ville de résidence: ARCANGUES",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Douard",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9620393514633179
},
{
"original": "Thromb Haemost",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9880841374397278
},
{
"original": "Becker",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9965289831161499
},
{
"original": "Jan Steffel",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9981919527053833
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9975678324699402
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9170476794242859
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9973927736282349
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9738216400146484
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9954879283905029
},
{
"original": "DE MONTAUDOUIN S",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9272499680519104
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9932386875152588
},
{
"original": "DE MONTAUDOUIN S",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9208526611328125
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.990057647228241
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.989109992980957
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9689285159111023
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9645036458969116
},
{
"original": "Aurélie",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.881074845790863
},
{
"original": "Aurélie PATIENT",
"replacement": "[PATIENT_2]",
"source": "ner",
"score": 0.9746572971343994
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9940195083618164
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9739658236503601
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9889624714851379
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9833499789237976
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9902847409248352
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9890732765197754
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9938098788261414
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9795359373092651
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9267356395721436
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8367420434951782
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8902173638343811
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9782821536064148
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9612898826599121
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9885973930358887
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9885276556015015
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9940003156661987
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.991439938545227
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9897788763046265
},
{
"original": "DE MONTAUDOUIN Jean S",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9596696496009827
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9052961468696594
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8345298767089844
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9823259115219116
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8175328373908997
},
{
"original": "Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9328702092170715
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9834707379341125
},
{
"original": "Jean Glyc",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9858918190002441
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9582907557487488
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9767048954963684
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9901256561279297
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9893426895141602
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9401918649673462
},
{
"original": "DUFOURNAUD",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9647955894470215
},
{
"original": "DESINFECTION EN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8180096745491028
},
{
"original": "DE MONTAUDOUIN Jean S",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9326297044754028
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.994103729724884
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9941022992134094
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9482848644256592
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9910933375358582
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9901430010795593
},
{
"original": "DE MONTAUDOUIN Jean S",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9586283564567566
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9715147018432617
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8865697979927063
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9271242618560791
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8430279493331909
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9701135754585266
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9590247869491577
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9838911294937134
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9819437265396118
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.990431010723114
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9909369349479675
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.95607590675354
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9585402011871338
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9395095109939575
},
{
"original": "Aurélie S",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8020205497741699
},
{
"original": "Aurélie VESSIE DE GLACE",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9076415300369263
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9807174801826477
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9823536276817322
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9600646495819092
},
{
"original": "Aurélie SOMMEIL",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9390555620193481
},
{
"original": "Aurélie REPAS",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9544067978858948
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9923587441444397
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9917306303977966
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9948804974555969
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8158547282218933
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9958683848381042
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9971088767051697
},
{
"original": "L.Hunou",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9759466648101807
},
{
"original": "A.Douard",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.956194281578064
},
{
"original": "U.Duranteau",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9967614412307739
},
{
"original": "Stephanie",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9214686155319214
},
{
"original": "A.Douard",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9952045679092407
},
{
"original": "Henri Rénéric",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9676961302757263
}
]
}