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 +1,795 @@
{
"source_file": "trackare-12007654-23080042_12007654_23080042.pdf",
"total_replacements": 565,
"regex_replacements": 282,
"ner_replacements": 81,
"sweep_replacements": 202,
"entities_found": [
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12007654",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23080042",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "MONT DE MARSAN",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE VISCERALE - CHIRURGIE VISCERALE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "220 AVE DU CAMPON RES KARINA B RDC Ville de résidence: LE CANNET",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8804223537445068
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9713303446769714
},
{
"original": "DEROURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8409835696220398
},
{
"original": "GENETET Johanna",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9154857397079468
},
{
"original": "FALZON Loic Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9968885779380798
},
{
"original": "FALZON Loic Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9972678422927856
},
{
"original": "FALZON Loic Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8512464761734009
},
{
"original": "Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8511970639228821
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8019322752952576
},
{
"original": "REY Juliette S",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8687986135482788
},
{
"original": "HIRIGARAY Mirentxu",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.998794674873352
},
{
"original": "REY Juliette Semaine",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.834366500377655
},
{
"original": "Mirentxu",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9794068336486816
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9462825655937195
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9866729378700256
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9804666638374329
},
{
"original": "Jean S",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9012497663497925
},
{
"original": "Jean S",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9746462106704712
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9663000702857971
},
{
"original": "SIGNES VITAUX",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9684737324714661
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9738211035728455
},
{
"original": "Miction",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8523885011672974
},
{
"original": "Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9830616116523743
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9811292290687561
},
{
"original": "Glyc",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8542740941047668
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.841193437576294
},
{
"original": "REY Juliette Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9125661849975586
},
{
"original": "HIRIGARAY Mirentxu",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9968001842498779
},
{
"original": "Jean S",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.974478006362915
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9793832302093506
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.957490861415863
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9957448840141296
},
{
"original": "FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9939848780632019
},
{
"original": "Jean Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9977331161499023
},
{
"original": "Jean Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9973533749580383
},
{
"original": "Jean Signé",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8453958630561829
},
{
"original": "Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8881639242172241
},
{
"original": "MG FALZON Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8774995803833008
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.981696605682373
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9401324391365051
},
{
"original": "Paul Jean TOGD",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9936658143997192
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9850299954414368
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9699150919914246
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9872837066650391
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9844379425048828
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9662059545516968
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9877303838729858
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9648743867874146
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9968931078910828
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9609737396240234
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9973457455635071
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9877133369445801
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8088852167129517
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9853142499923706
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8344268798828125
},
{
"original": "Mirentxu",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9821875691413879
},
{
"original": "Loic",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9630187749862671
},
{
"original": "Johanna",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9749830961227417
},
{
"original": "Johanna PLAIE-COLLE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.995786190032959
},
{
"original": "Johanna Signé",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.8930474519729614
},
{
"original": "DR.",
"replacement": "[MEDECIN_8]",
"source": "ner",
"score": 0.9352737665176392
},
{
"original": "Loic DOUL",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9271126985549927
},
{
"original": "Mirentxu S",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9806262254714966
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.998665452003479
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9989694952964783
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9769420623779297
},
{
"original": "Paul Jean SERING",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.8986093997955322
},
{
"original": "SERINGUE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8505897521972656
},
{
"original": "Loic FALZON",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9967644214630127
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.929777979850769
},
{
"original": "Loic FALZON",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9922017455101013
},
{
"original": "Loic FALZON DISP",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9023014307022095
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9475648403167725
},
{
"original": "Paul Jean",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9615768790245056
},
{
"original": "Loic FALZON",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9987338185310364
},
{
"original": "Loic FALZON",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9981107115745544
},
{
"original": "Nolwenn BARRE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9968135356903076
},
{
"original": "Kattina ARTOLA",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.957312285900116
},
{
"original": "Nolwenn BARRE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.994501531124115
},
{
"original": "Kattina ARTOLA",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9958909749984741
},
{
"original": "Nolwenn BARRE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9982240796089172
}
]
}