Dom/anonymisation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Annotation automatique et évaluation qualité baseline - Rappel 100%, Précision 18.97%

Browse Source
This commit is contained in:
Domi31tls
2026-03-02 10:51:38 +01:00
parent 99b6e7f1d1
commit 0ba5424eb0
56 changed files with 9770 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
tests/ground_truth/annotations/001_simple_unknown_BACTERIO_23018396.json Normal file
View File

@@ -0,0 +1,31 @@
{
"pdf_path": "001_simple_unknown_BACTERIO_23018396.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ETABLISSEMENT": [
"Centre Hospitalier de la Côte Basque"
],
"TEL": [
"0559443674"
],
"NOM": [
"JAOUEN Anne-Christine",
"MENARD-DEROURE Fanny",
"LEYSSENE David Dr",
"CURUTCHET-BURTIN Marie-Laure Dr",
"SEGUES Rémi Dr",
"SABATIER Pierre Dr",
"Pierre SABATIER ACCRED"
],
"IPP": [
"23000862"
]
}
}
]
}

39
tests/ground_truth/annotations/002_simple_unknown_bacterio_476_23159413.json Normal file
View File

@@ -0,0 +1,39 @@
{
"pdf_path": "002_simple_unknown_bacterio_476_23159413.pdf",
"total_pages": 2,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ETABLISSEMENT": [
"Centre Hospitalier de la Côte Basque"
],
"TEL": [
"0559443674"
],
"NOM": [
"JAOUEN Anne-Christine",
"MENARD-DEROURE Fanny",
"LEYSSENE David Dr",
"CURUTCHET-BURTIN Marie-Laure Dr",
"SEGUES Rémi Dr",
"SABATIER Pierre Dr",
"Anne Christine JAOUEN"
],
"IPP": [
"BA164017"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"Anne Christine JAOUEN"
]
}
}
]
}

25
tests/ground_truth/annotations/003_simple_compte_rendu_CRO_23155084.json Normal file
View File

@@ -0,0 +1,25 @@
{
"pdf_path": "003_simple_compte_rendu_CRO_23155084.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"NOM": [
"GASTON GILLES"
],
"ADRESSE": [
"10 RUE DES HAUTRS VENTS"
],
"CODE_POSTAL": [
"14190 OUILLY LE TESSON"
],
"DATE_NAISSANCE": [
"Né le 02/04/2010"
]
}
}
]
}

7
tests/ground_truth/annotations/004_simple_anapath_anapath_53_23224186.redacted_raster.json Normal file
View File

@@ -0,0 +1,7 @@
{
"pdf_path": "004_simple_anapath_anapath_53_23224186.redacted_raster.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": []
}

118
tests/ground_truth/annotations/005_simple_compte_rendu_CRH_23155836.json Normal file
View File

@@ -0,0 +1,118 @@
{
"pdf_path": "005_simple_compte_rendu_CRH_23155836.pdf",
"total_pages": 2,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"102 RUE MARIE CURIE"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"40390 ST MARTIN DE SEIGNANX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.23",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"DEBES EDOUARD",
"Thomas Grellety",
"BOUBE",
"BRUGEL",
"GUILNGAR"
],
"DATE_NAISSANCE": [
"née le 27/04/1959"
],
"EMAIL": [
"faudemar@ch-cotebasque.fr",
"mboube@ch-cotebasque.fr",
"mbrugel@ch-cotebasque.fr",
"mcboudier@ch-cotebasque.fr",
"goutorbe@ch-cotebasque.fr",
"aguilngar@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"t@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"09018266"
],
"EPISODE": [
"N° Episode 23155836"
]
}
},
{
"page_number": 1,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.23",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"BOUBE",
"BRUGEL",
"CHAPPE Capucine",
"MEURAT Aurore",
"DEBES Edouard"
],
"EMAIL": [
"faudemar@ch-cotebasque.fr",
"mboube@ch-cotebasque.fr",
"mbrugel@ch-cotebasque.fr",
"mcboudier@ch-cotebasque.fr",
"aguilngar@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"fprevost@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"09018266"
],
"EPISODE": [
"N° Episode 23155836"
]
}
}
]
}

43
tests/ground_truth/annotations/008_simple_trackare_trackare-14004105-23202435_14004105_23202435.json Normal file
View File

@@ -0,0 +1,43 @@
{
"pdf_path": "008_simple_trackare_trackare-14004105-23202435_14004105_23202435.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"22 LOT MENDI ALDE Ville de résidence",
"4, AVENUE DE TRÉVILLE ",
"22 LOT MENDI ALDE\tVille de résidence"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"Code Postal: 64130",
"64130 MAULEON-LICHARRE"
],
"IPP": [
"14004105"
],
"DATE_NAISSANCE": [
"Date de naissance: 03/04/1946"
],
"VILLE": [
"CHERAUTE"
],
"NOM": [
"Romain DIDAILLER",
"François GARNIER"
],
"TEL": [
"05 59 28 07 85",
"0676085336",
"06.16.86.27.44"
]
}
}
]
}

32
tests/ground_truth/annotations/009_simple_compte_rendu_CRO_23051225.json Normal file
View File

@@ -0,0 +1,32 @@
{
"pdf_path": "009_simple_compte_rendu_CRO_23051225.pdf",
"total_pages": 2,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"DATE_NAISSANCE": [
"né le 22/01/1954"
],
"NOM": [
"Jean-Michel SOUBELET",
"Pierre BRUNETEAU",
"Leire SAGARDUY",
"Charlène HANEQUIN",
"Charlène HANEQUIN Gonarthrose"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"Jean-Michel SOUBELET",
"Pierre BRUNETEAU"
]
}
}
]
}

35
tests/ground_truth/annotations/010_simple_anapath_ANAPATH_23217289.json Normal file
View File

@@ -0,0 +1,35 @@
{
"pdf_path": "010_simple_anapath_ANAPATH_23217289.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"NOM": [
"Marie DEL CASTILLO",
"Etienne MOLL",
"Marie DESROUSSEAUX Dr",
"Lewis GRECOURT Dr",
"Elodie LAURENT Dr",
"DIDAILLER Romain",
"Lewis GRECOURT"
],
"ADRESSE": [
"13 Av. de l'Interne Jacques Loeb",
"14 allée de Bordenave ",
"14 allée de bordenave "
],
"CODE_POSTAL": [
"64100 BAYONNE",
"64240 MACAYE",
"64990 SAINT PIERRE"
],
"TEL": [
"05 24 33 03 91"
]
}
}
]
}

59
tests/ground_truth/annotations/011_moyen_compte_rendu_CRH_23080179.json Normal file
View File

@@ -0,0 +1,59 @@
{
"pdf_path": "011_moyen_compte_rendu_CRH_23080179.pdf",
"total_pages": 4,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"NOM": [
"Thomas BAUX",
"LABADIE Anne-Michèle"
],
"ADRESSE": [
"12, PLACE DU GENERAL LECLERC",
"12, PLACE DU GENERAL LECLERC\n"
],
"CODE_POSTAL": [
"64600 ANGLET",
"64600 ANGLET\nCher Confrère"
],
"DATE_NAISSANCE": [
"née le 24/05/1940"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"Anne-Michèle LABADIE"
]
}
},
{
"page_number": 2,
"pii": {
"DATE_NAISSANCE": [
"né le 28/04/23"
],
"NOM": [
"LABADIE",
"Anne-Michèle LABADIE"
]
}
},
{
"page_number": 3,
"pii": {
"DATE_NAISSANCE": [
"NE le 05/05/23"
],
"NOM": [
"Sophie BERNARD"
]
}
}
]
}

53
tests/ground_truth/annotations/012_moyen_compte_rendu_CRH_692_23200418.json Normal file
View File

@@ -0,0 +1,53 @@
{
"pdf_path": "012_moyen_compte_rendu_CRH_692_23200418.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13 avenue de l",
"4, ALLÉE BORDENAVE"
],
"CODE_POSTAL": [
"64109 BAYONNE Cedex",
"64990 ST PIERRE"
],
"ETABLISSEMENT": [
"Pôle de Chirurgie - Anesthésie - Bloc Opératoire",
"Unité Urologie"
],
"TEL": [
"05.59.44.38.44",
"05.59.4 4.35.23",
"05.59.44.35.05",
"05.59.44.35.03",
"05.59.44.44.94",
"05.59.44.43.42",
"05.59.44.35.02",
"05.59.44.35.09",
"05.59.44.32.01"
],
"NOM": [
"Romain DIDAILLER",
"Claude UTHURRISQ",
"Laura ETCHECHOURY",
"Renaud GONTIER",
"Félix GOUTORBE",
"Marie LACLAU-LACROUTS",
"Vincent COMAT",
"Marie-Irene LARTIGUE",
"Antoine DOUARD",
"Yann LA MMERTYN",
"Laurent MASCLE",
"Alessandro FALCHETTI",
"Florence MAZERES",
"Caroline RIVERA",
"Bruno CORDON"
]
}
}
]
}

57
tests/ground_truth/annotations/013_moyen_compte_rendu_363_23085243_CRO.json Normal file
View File

@@ -0,0 +1,57 @@
{
"pdf_path": "013_moyen_compte_rendu_363_23085243_CRO.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13 avenue de l",
"4 RUE DE BELFORT",
"6, CHEMIN DE LA MAROUETTE"
],
"CODE_POSTAL": [
"64109 BAYONNE Cedex",
"64100 BAYONNE"
],
"ETABLISSEMENT": [
"Pôle de Chirurgie - Anesthésie - Bloc Opératoire",
"Unité Urologie"
],
"TEL": [
"05.59.44.38.44",
"05.59.44.35.23",
"05.59.44.35.05",
"05.59.44.35.03",
"05.59.44.44.94",
"05.59.44.43.42",
"05.59.44.35.02",
"05.59.44.35.09",
"05.59.44.32.01"
],
"NOM": [
"Romain DIDAILLER",
"Laura ETCHECHOURY",
"Renaud GONTIER",
"Marie Christine CAZELLES",
"Marie LACLAU-LACROUTS CHCB",
"Juliette DEWAILLY",
"Vincent COMAT",
"Antoine DOUARD",
"Yann LAMMERTYN",
"DENIS LABAT",
"Laurent MASCLE",
"Alessandro FALCHETTI",
"Florence MAZERES",
"Caroline RIVERA",
"Bruno CORDON"
],
"DATE_NAISSANCE": [
"Né le 28/03/1942"
]
}
}
]
}

7
tests/ground_truth/annotations/014_moyen_compte_rendu_CRO_23167029.redacted_raster.json Normal file
View File

@@ -0,0 +1,7 @@
{
"pdf_path": "014_moyen_compte_rendu_CRO_23167029.redacted_raster.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": []
}

38
tests/ground_truth/annotations/015_moyen_unknown_CONSULTATION_ANESTHESISTE_23139653.json Normal file
View File

@@ -0,0 +1,38 @@
{
"pdf_path": "015_moyen_unknown_CONSULTATION_ANESTHESISTE_23139653.pdf",
"total_pages": 3,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ETABLISSEMENT": [
"Centre Hospitalier de la Côte Basque"
],
"NOM": [
"LEGRAS Claire",
"PONCABARE Jean"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"LEGRAS Claire",
"PONCABARE Jean",
"HANNEQUIN Charlène"
]
}
},
{
"page_number": 2,
"pii": {
"NOM": [
"LEGRAS Claire"
]
}
}
]
}

194
tests/ground_truth/annotations/016_moyen_compte_rendu_CRH_23149905.json Normal file
View File

@@ -0,0 +1,194 @@
{
"pdf_path": "016_moyen_compte_rendu_CRH_23149905.pdf",
"total_pages": 3,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"2 AVENUE PIERRE LARRAMENDY"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.35.69",
"05.59.44.35.30",
"05.59.44.35.06",
"05.59.44.39.24",
"05.59.44.37.07",
"05.59.44.37.33",
"05.59.44.31.39",
"05.59.44.37.35",
"05.59.44.37.46",
"05.59.44.37.32",
"05.59.44.37.39"
],
"ETABLISSEMENT": [
"Pôle de Médecine Interne",
"Service de Maladies Infectieuses",
"Service DR ARRUABARENA SANDRINE",
"Clinique AOMI",
"CHU de Bordeaux Insuffisance Rénale",
"CHU de Bordeaux"
],
"NOM": [
"Laure ALLEMAN",
"Philippe",
"ARRUABARRENA",
"Sophie FARBOS Dr",
"BERNADY Toki Eder",
"ANGOSTO",
"Heidi WILLE IRC",
"Claire CASTEL"
],
"RPPS": [
"10101718855",
"10101489531",
"10002806528",
"10100333581",
"10100401941"
],
"DATE_NAISSANCE": [
"né le 12/12/1946"
],
"EMAIL": [
"c.castel@ch-cotebasque.fr",
"secr.malinf@ch-cotebasque.fr"
],
"IPP": [
"11027270"
],
"EPISODE": [
"N° Episode 23149905"
]
}
},
{
"page_number": 1,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.35.69",
"05.59.44.35.30",
"05.59.44.35.06",
"05.59.44.39.24",
"05.59.44.37.07",
"05.59.44.37.33",
"05.59.44.31.39",
"05.59.44.37.35",
"05.59.44.37.46",
"05.59.44.37.32",
"05.59.44.37.39"
],
"ETABLISSEMENT": [
"Pôle de Médecine Interne",
"Service de Maladies Infectieuses",
"CHU de Bordeaux"
],
"NOM": [
"Laure ALLEMAN Transfert",
"SOULIER",
"Philippe",
"Marc Olivier VAREIL",
"Claire CASTEL",
"Araujo",
"MILADI"
],
"RPPS": [
"10101718855",
"10101489531",
"10002806528",
"10100333581",
"10100401941"
],
"EMAIL": [
"c.castel@ch-cotebasque.fr",
"secr.malinf@ch-cotebasque.fr"
],
"IPP": [
"11027270"
],
"EPISODE": [
"N° Episode 23149905"
]
}
},
{
"page_number": 2,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.35.69",
"05.59.44.35.30",
"05.59.44.35.06",
"05.59.44.39.24",
"05.59.44.37.07",
"05.59.44.37.33",
"05.59.44.31.39",
"05.59.44.37.35",
"05.59.44.37.46",
"05.59.44.37.32",
"05.59.44.37.39"
],
"ETABLISSEMENT": [
"Pôle de Médecine Interne",
"Service de Maladies Infectieuses",
"CHU de Bordeaux"
],
"NOM": [
"Laure ALLEMAN",
"Miladi",
"Philippe",
"Sophie FARBOS",
"Acquier Mathieu",
"Marc Olivier VAREIL",
"Heidi WILLE",
"WILLE Heidi",
"Claire CASTEL",
"ACQUIER Mathieu",
"ARRUABARENA SANDRINE"
],
"RPPS": [
"10101718855",
"10101489531",
"10002806528",
"10100333581",
"10100401941"
],
"EMAIL": [
"c.castel@ch-cotebasque.fr",
"secr.malinf@ch-cotebasque.fr"
],
"IPP": [
"11027270"
],
"EPISODE": [
"N° Episode 23149905"
]
}
}
]
}

7
tests/ground_truth/annotations/017_moyen_compte_rendu_CRO_23222062.redacted_raster.json Normal file
View File

@@ -0,0 +1,7 @@
{
"pdf_path": "017_moyen_compte_rendu_CRO_23222062.redacted_raster.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": []
}

227
tests/ground_truth/annotations/018_moyen_compte_rendu_CRH_23042753.json Normal file
View File

@@ -0,0 +1,227 @@
{
"pdf_path": "018_moyen_compte_rendu_CRH_23042753.pdf",
"total_pages": 4,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"3297 QUARTIER AUZO TTIPI"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"64430 ST ETIENNE DE BAIGORRY"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.23",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"NARBAIS AUDREY",
"Thomas Grellety",
"BOUBE",
"BRUGEL",
"NIVET",
"PUJOS"
],
"DATE_NAISSANCE": [
"née le 23/02/1980"
],
"EMAIL": [
"audemar@ch-cotebasque.fr",
"mbrugel@ch-cotebasque.fr",
"cboudier@ch-cotebasque.fr",
"fgoutorbe@ch-cotebasque.fr",
"aguilngar@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"t@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"01306172"
],
"EPISODE": [
"N° Episode 23042753"
]
}
},
{
"page_number": 1,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"PUJOS",
"BOUBE",
"BRUGEL Num",
"AUDEMAR Franck",
"DUTREY Sarah",
"NARBAIS AUDREY",
"MELLIN Marie"
],
"EMAIL": [
"faudemar@ch-cotebasque.fr",
"mboube@ch-cotebasque.fr",
"mcboudier@ch-cotebasque.fr",
"fgoutorbe@ch-cotebasque.fr",
"guilngar@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"fprevost@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"01306172"
],
"EPISODE": [
"N° Episode 23042753"
]
}
},
{
"page_number": 2,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"64430 ST ETIENNE DE BAIGORRY"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.23",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"MELLIN MARIE",
"Thomas Grellety",
"BRUGEL",
"NIVET",
"PUJOS"
],
"DATE_NAISSANCE": [
"née le 23/02/1980"
],
"EMAIL": [
"faudemar@ch-cotebasque.fr",
"mbrugel@ch-cotebasque.fr",
"cboudier@ch-cotebasque.fr",
"fgoutorbe@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"t@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"01306172"
],
"EPISODE": [
"N° Episode 23042753"
]
}
},
{
"page_number": 3,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.23",
"05.59.44.37.25",
"05.59.44.37.22",
"05.59.44.37.29"
],
"ETABLISSEMENT": [
"Pôle Spécialités Médicales",
"Service de Gastro-Entérologie - Oncologie Digestive"
],
"NOM": [
"Christelle Béraut",
"PUJOS",
"BRUGEL",
"AUDEMAR Franck",
"DUTREY Sarah",
"NARBAIS AUDREY",
"MELLIN Marie"
],
"EMAIL": [
"faudemar@ch-cotebasque.fr",
"mboube@ch-cotebasque.fr",
"mcboudier@ch-cotebasque.fr",
"fgoutorbe@ch-cotebasque.fr",
"aguilngar@ch-cotebasque.fr",
"tkhuong-huu@ch-cotebasque.fr",
"dnivet@ch-cotebasque.fr",
"boui@ch-cotebasque.fr",
"fprevost@ch-cotebasque.fr"
],
"RPPS": [
"10100532760"
],
"IPP": [
"01306172"
],
"EPISODE": [
"N° Episode 23042753"
]
}
}
]
}

95
tests/ground_truth/annotations/019_moyen_compte_rendu_CRO_332_23049003.json Normal file
View File

@@ -0,0 +1,95 @@
{
"pdf_path": "019_moyen_compte_rendu_CRO_332_23049003.pdf",
"total_pages": 2,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"NOM": [
"MARC WEBER",
"Romain BILLON-GRAND",
"Philippe CAILLAUD",
"Joe FADDOUL",
"Daniel LAGUERRE",
"Pascale LARROUY",
"Maritxu GRENADE",
"PIERRE URBISTONDO",
"BILLON-GRAND",
"Fanny LAFOURCADE",
"CAILLAUD",
"Véronique ARTIGUEBIEILLE",
"FADDOUL",
"Cindy AUBERT",
"LAGUERRE",
"Christelle"
],
"CODE_POSTAL": [
"64310 ASCAIN"
],
"ETABLISSEMENT": [
"Service Mr PIERRE URBISTONDO"
],
"ADRESSE": [
"1286 CHEMIN DE GAINEKO BORDA"
],
"TEL": [
"05.59.44.33.20",
"05.59.44.35.43",
"05.59.44.35.47",
"05.59.44.43.58",
"05.59.44.35.49",
"05.59.44.43.44",
"05.59.44.35.42",
"05.59.44.35.45"
],
"DATE_NAISSANCE": [
"né le 26/08/1947"
],
"EMAIL": [
"secr.neurochir@ch-cotebasque.fr"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"PIERRE URBISTONDO",
"Romain BILLON-GRAND",
"Philippe CAILLAUD COMPTE",
"Daniel LAGUERRE",
"Pascale LARROUY",
"Maritxu GRENADE",
"Eric DUFOUR",
"BILLON-GRAND",
"MARC WEBER",
"Fanny LAFOURCADE",
"CAILLAUD Préparation",
"Véronique ARTIGUEBIEILLE",
"FADDOUL",
"Cindy AUBERT",
"LAGUERRE",
"Christelle"
],
"AGE": [
"Patient de 75 ans"
],
"TEL": [
"05.59.44.33.20",
"05.59.44.35.43",
"05.59.44.35.47",
"05.59.44.43.58",
"05.59.44.35.49",
"05.59.44.43.44",
"05.59.44.35.42",
"05.59.44.35.45"
],
"EMAIL": [
"secr.neurochir@ch-cotebasque.fr"
]
}
}
]
}

7
tests/ground_truth/annotations/020_moyen_compte_rendu_CRO_23084754.redacted_raster.json Normal file
View File

@@ -0,0 +1,7 @@
{
"pdf_path": "020_moyen_compte_rendu_CRO_23084754.redacted_raster.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": []
}

7
tests/ground_truth/annotations/021_moyen_compte_rendu_CRO_23201117.redacted_raster.json Normal file
View File

@@ -0,0 +1,7 @@
{
"pdf_path": "021_moyen_compte_rendu_CRO_23201117.redacted_raster.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": []
}

23
tests/ground_truth/annotations/022_moyen_compte_rendu_cro2_516_23187028.json Normal file
View File

@@ -0,0 +1,23 @@
{
"pdf_path": "022_moyen_compte_rendu_cro2_516_23187028.pdf",
"total_pages": 1,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ETABLISSEMENT": [
"Centre Hospitalier de la Côte Basque",
"Service Demandeur"
],
"TEL": [
"05.59.44.35.35"
],
"NOM": [
"Samuel KASPARIAN"
]
}
}
]
}

570
tests/ground_truth/annotations/023_complexe_compte_rendu_CRH_23102610.json Normal file
View File

@@ -0,0 +1,570 @@
{
"pdf_path": "023_complexe_compte_rendu_CRH_23102610.pdf",
"total_pages": 9,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"24 AVENUE DE LA BAIE DE TXIGUNDI"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"64700 HENDAYE"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Dyslipidémie",
"Service Pas d'activité physique",
"Service Poids maximal en",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI Rééquilibrage",
"Marc Olivier VAREIL",
"Araujo",
"Sophie FARBOS",
"Heidi WILLE Tabac",
"Laure ALLEMAN",
"Margaux BOUET Hernie",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Julien MARY",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Irène MACHELART",
"Loiseau",
"Moldovane"
],
"DATE_NAISSANCE": [
"né le 30/07/1950"
],
"AGE": [
"âge de 55 ans"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 1,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service MV",
"Service Transaminases normales",
"Service FENOFIBRATE",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX Bruits",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY LDL",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"Sophie FARBOS",
"Heidi WILLE",
"Laure ALLEMAN",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN Ajout",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE Rendez-vous",
"Hilaire CHARLANNE"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 2,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Docteur MAURY Elisa",
"Service Monsieur BRONSWICK GILDAS",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ Rédigé",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"ARISTEGUY Jacques",
"Laure ALLEMAN PR",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Hilaire CHARLANNE",
"Laurence RITZ-QUILLACQ",
"Irène MACHELART"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 3,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"57 BOULEVARD GENERAL LECLERC"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"64700 HENDAYE"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Dyslipidémie",
"Service Pas d'activité physique",
"Service Poids maximal en",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"ARISTEGUY JACQUES",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI Rééquilibrage",
"Marc Olivier VAREIL",
"Araujo",
"Sophie FARBOS",
"Heidi WILLE Tabac",
"Laure ALLEMAN",
"Margaux BOUET Hernie",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Julien MARY",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Irène MACHELART",
"Loiseau",
"Moldovane"
],
"DATE_NAISSANCE": [
"né le 30/07/1950"
],
"AGE": [
"âge de 55 ans"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 4,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service MV",
"Service Transaminases normales",
"Service FENOFIBRATE",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX Bruits",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY LDL",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"Sophie FARBOS",
"Heidi WILLE",
"Laure ALLEMAN",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN Ajout",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE Rendez-vous",
"Hilaire CHARLANNE"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 5,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Docteur MAURY Elisa",
"Service Monsieur BRONSWICK GILDAS",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ Rédigé",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"ARISTEGUY Jacques",
"Laure ALLEMAN PR",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Hilaire CHARLANNE",
"Laurence RITZ-QUILLACQ",
"Irène MACHELART"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 6,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"1 PLACE AMELIE RABA LEON"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"33076 BORDEAUX CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Dyslipidémie",
"Service Pas d'activité physique",
"Service Poids maximal en",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI Rééquilibrage",
"Marc Olivier VAREIL",
"Araujo",
"Sophie FARBOS",
"Heidi WILLE Tabac",
"Laure ALLEMAN",
"Margaux BOUET Hernie",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Julien MARY",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Irène MACHELART",
"Loiseau",
"Moldovane"
],
"DATE_NAISSANCE": [
"né le 30/07/1950"
],
"AGE": [
"âge de 55 ans"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 7,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service MV",
"Service Transaminases normales",
"Service FENOFIBRATE",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX Bruits",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY LDL",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"Sophie FARBOS",
"Heidi WILLE",
"Laure ALLEMAN",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN Ajout",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE Rendez-vous",
"Hilaire CHARLANNE"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
},
{
"page_number": 8,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX"
],
"TEL": [
"05 59 44 35 35",
"05 59 63 35 88",
"05.59.44.37.33",
"05.59.44.37.42",
"05.59.44.37.32",
"05.59.44.38.62",
"05.59.44.37.74",
"05.33.78.81.89"
],
"ETABLISSEMENT": [
"Pôle Médecine Interne",
"Service Docteur MAURY Elisa",
"Service Monsieur BRONSWICK GILDAS",
"Pôle Méd"
],
"NOM": [
"Stéphanie BORDES COUECOU",
"Suzanne DEVAUX",
"Irène NICOLETIS",
"Anne BARTEAU",
"Delphine DEMARSY",
"Elisa MAURY",
"Laurence RITZ-QUILLACQ Rédigé",
"Marion GSCHWIND",
"Mathieu AUZI",
"Marc Olivier VAREIL",
"ARISTEGUY Jacques",
"Laure ALLEMAN PR",
"Margaux BOUET",
"Adeline LACRAZ",
"Pauline D'HALLUIN",
"Séverine POULAIN",
"Julien MARY",
"Thibault MOLES",
"Agnès MONNIER DUTHEIL",
"Stéphane MARCE",
"Alexia HOURDILLE",
"Hilaire CHARLANNE",
"Laurence RITZ-QUILLACQ",
"Irène MACHELART"
],
"IPP": [
"01290152"
],
"EPISODE": [
"N° Episode 23102610"
]
}
}
]
}

219
tests/ground_truth/annotations/024_complexe_trackare_trackare-17001141-23066188_17001141_23066188.json Normal file
View File

@@ -0,0 +1,219 @@
{
"pdf_path": "024_complexe_trackare_trackare-17001141-23066188_17001141_23066188.pdf",
"total_pages": 19,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"33 RUE JEAN FOURCADE Ville de résidence",
"39 rue Bernard de Coral ",
"33 RUE JEAN FOURCADE\tVille de résidence"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"Code Postal: 64122",
"64122 URRUGNE"
],
"IPP": [
"17001141"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
],
"VILLE": [
"BAYONNE CEDEX"
],
"NOM": [
"Céline BELLEAU",
"Gaelle COQUEL"
],
"TEL": [
"05 59 54 31 97"
],
"ETABLISSEMENT": [
"unité de Médecine hors SC"
]
}
},
{
"page_number": 1,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 2,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 3,
"pii": {
"NOM": [
"Aurélie",
"Céline",
"Aurélie VALADE",
"Céline BELLEAU"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 4,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 5,
"pii": {
"NOM": [
"Charlotte",
"Céline",
"Charlotte PETRIAT",
"Céline BELLEAU"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 6,
"pii": {
"NOM": [
"Marie-Elise",
"Céline",
"Marie-Elise PICAMILH",
"Céline BELLEAU"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 7,
"pii": {
"NOM": [
"Céline",
"Marie",
"Céline BELLEAU",
"Marie- Elise PICAMILH"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 8,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 9,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 10,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 11,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 12,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 13,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 14,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 15,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 16,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 17,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
},
{
"page_number": 18,
"pii": {
"NOM": [
"Anne Christine Dr",
"Pierre SABATIER",
"Céline BELLEAU",
"Pierre SABATIER Dr",
"Anne Christine JAOUEN"
],
"DATE_NAISSANCE": [
"Date de naissance: 15/01/2017"
]
}
}
]
}

368
tests/ground_truth/annotations/025_complexe_trackare_trackare-02016820-23095226_02016820_23095226.json Normal file
View File

@@ -0,0 +1,368 @@
{
"pdf_path": "025_complexe_trackare_trackare-02016820-23095226_02016820_23095226.pdf",
"total_pages": 31,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"7 RUE DES PADOUANS Ville de résidence",
"12 rue de l'industrie ",
"7 RUE DES PADOUANS\tVille de résidence"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"Code Postal: 64100",
"64600 ANGLET"
],
"IPP": [
"02016820"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
],
"VILLE": [
"OLORON STE MARIE"
],
"NOM": [
"Laurence MASSE",
"Gilles DELMAS"
],
"TEL": [
"0682304910",
"06 82 30 49\n10"
]
}
},
{
"page_number": 1,
"pii": {
"NOM": [
"Laurence",
"Alexandre",
"Laurence MASSE",
"Alexandre LEROY"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 2,
"pii": {
"NOM": [
"Laurence",
"BRILLAXIS",
"Sophie",
"Aguer",
"Laurence MASSE",
"Sophie SCHNEIDER"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 3,
"pii": {
"NOM": [
"Maxime",
"Diakité",
"Sophie",
"Bruneteau",
"Maxime CAZAYUS",
"Sophie SCHNEIDER"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 4,
"pii": {
"NOM": [
"CAZAYUS",
"GENEBES"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 5,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 6,
"pii": {
"NOM": [
"Leroy"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 7,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
],
"NOM": [
"Diakité"
]
}
},
{
"page_number": 8,
"pii": {
"NOM": [
"DIAKYTE"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 9,
"pii": {
"NOM": [
"Marjolaine",
"Nina",
"Nina CUGNIN"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 10,
"pii": {
"NOM": [
"Sophie",
"Laurence",
"François",
"Sophie SCHNEIDER",
"Laurence MASSE",
"François BANNIER"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 11,
"pii": {
"NOM": [
"Laurence",
"Sophie",
"Laurence MASSE",
"Sophie SCHNEIDER"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 12,
"pii": {
"NOM": [
"Sophie SCHNEIDER",
"Laurence MASSE",
"François",
"Sophie",
"François BANNIER"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 13,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
],
"NOM": [
"Laurence MASSE"
]
}
},
{
"page_number": 14,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 15,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 16,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 17,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 18,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 19,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 20,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 21,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 22,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 23,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 24,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 25,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 26,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 27,
"pii": {
"NIR": [
"159026442205016"
],
"NOM": [
"PELLERIN-GUIGNARD Aude",
"KERKENI Anis",
"NOCENT-EJNAINI Cecilia"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959",
"Date de naissance : 24/02/1959",
"Date de naissance : 24-02-1959"
]
}
},
{
"page_number": 28,
"pii": {
"NIR": [
"159026442205016"
],
"NOM": [
"CAZAYUS Maxime",
"Bonnebas"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 29,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
},
{
"page_number": 30,
"pii": {
"NOM": [
"Marie-Laure",
"Rémi SEGUES Dr",
"Marie-Laure CURUTCHET BURTIN"
],
"DATE_NAISSANCE": [
"Date de naissance: 24/02/1959"
]
}
}
]
}

303
tests/ground_truth/annotations/026_complexe_trackare_trackare-15000536-23074384_15000536_23074384.json Normal file
View File

@@ -0,0 +1,303 @@
{
"pdf_path": "026_complexe_trackare_trackare-15000536-23074384_15000536_23074384.pdf",
"total_pages": 25,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"1 RUE JOSEPH ST ANDRÉ Ville de résidence",
"4 RUE PONTRIQUE ",
"1 RUE JOSEPH ST ANDRÉ\tVille de résidence"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"Code Postal: 64340",
"64100 BAYONNE"
],
"IPP": [
"15000536"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
],
"VILLE": [
"BAYONNE CEDEX"
],
"NOM": [
"Marie DUBREL",
"Stéphanie DELMAS"
],
"ETABLISSEMENT": [
"unité de Médecine hors SC"
]
}
},
{
"page_number": 1,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 2,
"pii": {
"ETABLISSEMENT": [
"CMPP",
"CHU"
],
"NOM": [
"Marie-Elise",
"Michel",
"Services"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 3,
"pii": {
"NOM": [
"PICAMILH",
"Puget",
"Charlotte",
"Marie-Elise PICAMILH",
"Charlotte PETRIAT"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 4,
"pii": {
"ETABLISSEMENT": [
"CHU"
],
"NOM": [
"Michel",
"Services"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 5,
"pii": {
"NOM": [
"Charlotte",
"Céline",
"Catherine",
"DUBREL",
"Charlotte PETRIAT",
"Céline BELLEAU",
"Catherine DIDAILLER"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 6,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 7,
"pii": {
"NOM": [
"Picamilh"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 8,
"pii": {
"NOM": [
"Céline",
"Céline BELLEAU"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 9,
"pii": {
"NOM": [
"Charlotte",
"Marie-Elise",
"Charlotte PETRIAT",
"Céline BELLEAU",
"Marie-Elise PICAMILH"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 10,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 11,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 12,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 13,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 14,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 15,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 16,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 17,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 18,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 19,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 20,
"pii": {
"NOM": [
"MONSINJON Julien"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 21,
"pii": {
"NOM": [
"MONSINJON Julien",
"PETRIAT Charlotte",
"PUGET Catheri"
],
"DATE_NAISSANCE": [
"ne le 18/04/2023",
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 22,
"pii": {
"NOM": [
"PUGET Catherine",
"PETRIAT Charlotte"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 23,
"pii": {
"NOM": [
"Julien",
"Julien GUILLEMAUD"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
},
{
"page_number": 24,
"pii": {
"NOM": [
"Julien Dr",
"Julien",
"Rémi SEGUES Dr",
"Julien GUILLEMAUD Dr",
"Rémi SEGUES"
],
"DATE_NAISSANCE": [
"Date de naissance: 08/01/2015"
]
}
}
]
}

235
tests/ground_truth/annotations/027_complexe_trackare_trackare-10027557-23183041_10027557_23183041.json Normal file
View File

@@ -0,0 +1,235 @@
{
"pdf_path": "027_complexe_trackare_trackare-10027557-23183041_10027557_23183041.pdf",
"total_pages": 20,
"annotated_by": "auto-annotation-v1",
"annotation_date": "2026-03-02",
"pages": [
{
"page_number": 0,
"pii": {
"ADRESSE": [
"13, Avenue de l'Interne J",
"LOEB BP 8",
"4 RUE DU PETIT NANOT Ville de résidence",
"1, PLACE PEREIRE ",
"4 RUE DU PETIT NANOT\tVille de résidence"
],
"CODE_POSTAL": [
"64109 BAYONNE CEDEX",
"Code Postal: 64340",
"64100 BAYONNE"
],
"IPP": [
"10027557"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
],
"VILLE": [
"PARIS"
],
"NOM": [
"Marie LACLAU-LACROUTS",
"Georges PEPIN"
],
"TEL": [
"0634226193",
"0617381939",
"06.45.55.95.38"
],
"ETABLISSEMENT": [
"unité de Chirurgie hors SC"
]
}
},
{
"page_number": 1,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 2,
"pii": {
"NOM": [
"Renaud",
"Renaud GONTIER"
],
"AGE": [
"Patiente 52 ans"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 3,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 4,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 5,
"pii": {
"DOSSIER": [
"ndansetron"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 6,
"pii": {
"DOSSIER": [
"NDANSETRON"
],
"NOM": [
"Samuel",
"Marine",
"Samuel KASPARIAN",
"Marine JOBERT"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 7,
"pii": {
"NOM": [
"Samuel",
"Samuel KASPARIAN"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 8,
"pii": {
"DOSSIER": [
"NDANSETRON"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 9,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 10,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 11,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 12,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 13,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 14,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 15,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 16,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 17,
"pii": {
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 18,
"pii": {
"NOM": [
"Pierre SABATIER Dr",
"Rémi SEGUES"
],
"DATE_NAISSANCE": [
"Date de naissance: 12/06/1971"
]
}
},
{
"page_number": 19,
"pii": {
"DATE_NAISSANCE": [
"née le 12/06/1971",
"Date de naissance: 12/06/1971"
],
"ETABLISSEMENT": [
"Service Madame BEDOUET MARIE-LINE"
],
"NOM": [
"Marie LACLAU-LACROUTS"
]
}
}
]
}

23
tests/ground_truth/annotations/dataset_statistics.json Normal file
View File

@@ -0,0 +1,23 @@
{
"total_documents": 25,
"total_pages": 133,
"total_pii": 1167,
"by_type": {
"ETABLISSEMENT": 83,
"TEL": 193,
"NOM": 507,
"IPP": 25,
"ADRESSE": 79,
"CODE_POSTAL": 50,
"DATE_NAISSANCE": 114,
"EMAIL": 62,
"RPPS": 21,
"EPISODE": 18,
"VILLE": 5,
"AGE": 5,
"NIR": 2,
"DOSSIER": 3
},
"avg_pii_per_doc": 46.7,
"avg_pages_per_doc": 5.3
}