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 +1,45 @@
{
"source_file": "CONSULTATION ANESTHESISTE 23051225.pdf",
"total_replacements": 38,
"regex_replacements": 36,
"ner_replacements": 0,
"sweep_replacements": 2,
"entities_found": [
{
"original": "23593854",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23593854",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23593854",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "75 BIS XERRI KARRIKA N° Tél :",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "75 BIS XERRI KARRIKA N° Tél :",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "75 BIS XERRI KARRIKA N° Tél :",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
}
]
}

View File

@@ -0,0 +1,39 @@
{
"source_file": "CRO 23051225.pdf",
"total_replacements": 13,
"regex_replacements": 8,
"ner_replacements": 5,
"sweep_replacements": 0,
"entities_found": [
{
"original": "JEAN-MICHEL",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8616263270378113
},
{
"original": "SOUBELET",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.934912383556366
},
{
"original": "Charles DERUY",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9975725412368774
},
{
"original": "JEAN-MICHEL",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9688763618469238
},
{
"original": "SOUBELET",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.99534010887146
}
]
}

View File

@@ -0,0 +1,765 @@
{
"source_file": "trackare-00269826-23051225_00269826_23051225.pdf",
"total_replacements": 1025,
"regex_replacements": 421,
"ner_replacements": 62,
"sweep_replacements": 542,
"entities_found": [
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00269826",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23051225",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "SALIES DE BEARN",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE ORTHOPEDIQUE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "75 BIS XERRI KARRIKA Ville de résidence: ESPELETTE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "HANNEQUIN Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9664341807365417
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9947840571403503
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.99884432554245
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9986239671707153
},
{
"original": "Stéphanie GARBISU",
"replacement": "[SOIGNANT_23]",
"source": "ner",
"score": 0.9984413385391235
},
{
"original": "SETOFILM",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8253501653671265
},
{
"original": "SETOFILM",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.858121931552887
},
{
"original": "Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8395334482192993
},
{
"original": "HANNEQUIN Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9947517514228821
},
{
"original": "Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9279054999351501
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9912790060043335
},
{
"original": "CASTETS Sophie",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.876224935054779
},
{
"original": "HANNEQUIN Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9278066158294678
},
{
"original": "CHISNE Karine",
"replacement": "[SOIGNANT_20]",
"source": "ner",
"score": 0.9426907300949097
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9914239048957825
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9929310083389282
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9948533773422241
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.994970440864563
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9949768781661987
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9916471242904663
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9967949986457825
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9966718554496765
},
{
"original": "Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9973052740097046
},
{
"original": "Stéphanie GARBISU",
"replacement": "[SOIGNANT_23]",
"source": "ner",
"score": 0.9961262941360474
},
{
"original": "Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8468128442764282
},
{
"original": "Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8056780099868774
},
{
"original": "HANNEQUIN Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9942958354949951
},
{
"original": "Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.926867663860321
},
{
"original": "Charles SOUS- S",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.849555492401123
},
{
"original": "Sophie REDON",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9810984134674072
},
{
"original": "Sophie PANSEMENT",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9909740090370178
},
{
"original": "Charlène PÉRINERVEUX",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8368111848831177
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9924529790878296
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9922135472297668
},
{
"original": "Fabienne REPAS",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.9839556217193604
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9969227910041809
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9964041709899902
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.996652364730835
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.993744432926178
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9959303736686707
},
{
"original": "Emilie DI Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9838149547576904
},
{
"original": "Emilie DI",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9941716194152832
},
{
"original": "Emilie DI Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9577271938323975
},
{
"original": "Emilie DI Signé",
"replacement": "[SOIGNANT_21]",
"source": "ner",
"score": 0.9937264323234558
},
{
"original": "Signé Charlène",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9250510334968567
},
{
"original": "HANNEQUIN",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9827094674110413
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9915514588356018
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9958180785179138
},
{
"original": "Charles DERUY S",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9656512141227722
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9931959509849548
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.998028576374054
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.998616635799408
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9982843399047852
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9889280796051025
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9983735084533691
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9981977939605713
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.997733473777771
},
{
"original": "Charles DERUY DE SODIUM",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9783065319061279
},
{
"original": "Charles DERUY",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9846073389053345
},
{
"original": "bruneteau",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9865862727165222
},
{
"original": "Soignante Fabienne ETCHART",
"replacement": "[SOIGNANT_22]",
"source": "ner",
"score": 0.807198703289032
},
{
"original": "rie HAMEL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8483129143714905
}
]
}