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 +1,8 @@
{
"source_file": "CRO 23001083.pdf",
"total_replacements": 13,
"regex_replacements": 9,
"ner_replacements": 0,
"sweep_replacements": 4,
"entities_found": []
}

View File

@@ -0,0 +1,21 @@
{
"source_file": "LETTRE DE SORTIE 23001083.pdf",
"total_replacements": 10,
"regex_replacements": 7,
"ner_replacements": 2,
"sweep_replacements": 1,
"entities_found": [
{
"original": "CLAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.892794132232666
},
{
"original": "CAMY",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9786146283149719
}
]
}

View File

@@ -0,0 +1,747 @@
{
"source_file": "trackare-00274739-23001083_00274739_23001083.pdf",
"total_replacements": 499,
"regex_replacements": 189,
"ner_replacements": 74,
"sweep_replacements": 236,
"entities_found": [
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00274739",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23001083",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "170066444521841",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64445",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "PAU",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "DURANTEAU Ute",
"replacement": "[MEDECIN_3]",
"source": "regex",
"category": "patient"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "CAMY",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "CAMY",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "CLAUDE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "CLAUDE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "[ADRESSE_1]",
"replacement": "[ADRESSE_4]",
"source": "regex",
"category": "adresse"
},
{
"original": "DEROURE GUILLEMAUD BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9946397542953491
},
{
"original": "CURUTCHET",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9373106956481934
},
{
"original": "LASSERRE Astrid",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9962536692619324
},
{
"original": "THOMAS Chloe",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9981050491333008
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9899311065673828
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9851227402687073
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9860036969184875
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9969789981842041
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9967066645622253
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9744393229484558
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9667395949363708
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9571624398231506
},
{
"original": "DUFOURNAUD Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9920870661735535
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9810851216316223
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9544258117675781
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9837192893028259
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9941206574440002
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9896615147590637
},
{
"original": "Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.8070383667945862
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9915463328361511
},
{
"original": "Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.8036342859268188
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9904702305793762
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9706674814224243
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9938693046569824
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9878847002983093
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9030047655105591
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9981234073638916
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9957857131958008
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9955528974533081
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.985990047454834
},
{
"original": "DE MONTAUDOUIN Jean S",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9668697118759155
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9592142105102539
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9746670126914978
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9711618423461914
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9576594233512878
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9350309371948242
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9962248802185059
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9879631996154785
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9751196503639221
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9650893211364746
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9966633319854736
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9962354302406311
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.98811936378479
},
{
"original": "DUFOURNAUD Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9957935214042664
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9632239937782288
},
{
"original": "Jean GEL",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9096024036407471
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9953047633171082
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9859236478805542
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9948150515556335
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9882743954658508
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9947015643119812
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9949286580085754
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9698300361633301
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9162665009498596
},
{
"original": "DE MONTAUDOUIN Jean S",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9612419009208679
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.987713634967804
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9977336525917053
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9979714751243591
},
{
"original": "DE MONTAUDOUIN Jean Signé",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.996894896030426
},
{
"original": "DE MONTAUDOUIN Jean",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9646070003509521
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9797576069831848
},
{
"original": "DE MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9718623161315918
},
{
"original": "DE MONTAUDOUIN Signé",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9286496043205261
},
{
"original": "DE MONTAUDOUIN S",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9192182421684265
},
{
"original": "Aurélie S",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8076180815696716
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8992579579353333
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9795466661453247
},
{
"original": "Anaïs CARRAZÉ",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9977016448974609
},
{
"original": "Anaïs CARRAZÉ",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9978857040405273
},
{
"original": "Alexandre BLANCO",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.990678608417511
},
{
"original": "MONTAUDOUIN",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9751584529876709
},
{
"original": "Anaîs",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.981334388256073
},
{
"original": "A.Douard",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.933455765247345
},
{
"original": "U.Duranteau",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9976765513420105
}
]
}