Datasets
Dataset
indicphi
by Sidharth1743
IndicPHI Synthetic Indian clinical documents with PHI/PII span labels for 23 languages (22 scheduled Indian languages + English). All identifiers are synthetic surrogates, not real patients.
MITtoken-classification 20 010K < n < 100K rows
published 4 Sept 2026
Preview
First 5 rows of default / train, from the Hugging Face dataset viewer.
| document_id | text | tokenized_text | ner | spans | token_align_errors | document_language_code | doc_type_id | domain_id | uuid | stage | split |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 00475c261ac4462895b6d6d925a61083__0 | MRN-15FE5B1DAF HSP-AS-935C09 এ এছ এ এইচ এ টোকা — গাঁও Baksa Gaon, জিলা Baksa হিতাধিকাৰী Manisha Brahma, 37 / Female এ এছ এ এইচ এ: Lakhima Basumatary | ফোন 9593541505 ভ্ৰমণৰ তথ্য: হিতাধিকাৰীগৰাকীয়ে Baksa Primary Health Centre-ত অত্যধিক ভাগৰ, কাৰণ নোহোৱাকৈ ওজন কমা আৰু সোনকালে পেট ভৰি যোৱাৰ দৰে জৰুৰী… | ["MRN","-","15","FE","5","B","1","DAF","HSP","-","AS","-","935","C","09","এ","এছ","এ","এইচ","এ","ট","ো","ক","া","—","গ","া","ঁ","ও","Baksa","Gaon",",","জ","ি","ল","া","Baksa","হ","ি","ত","া","ধ","ি","ক","া","ৰ","ী","Manisha","Brahma",",","37","/","Female","এ","এছ","এ","এইচ","এ",":","Lakhima","Basum… | [[0,7,"MRN"],[8,14,"HOSPITAL_ID"],[29,30,"VILLAGE"],[36,36,"DISTRICT"],[47,48,"PATIENT_NAME"],[50,50,"AGE"],[52,52,"GENDER"],[59,60,"ASHA_WORKER_NAME"],[65,65,"PHONE_NUMBER"],[90,93,"HOSPITAL_NAME"],[443,444,"RELATIVE_NAME"],[445,451,"BPL_RATION_CARD"],[452,453,"VOTER_ID"],[454,454,"RELIGION"]] | [{"start":0,"end":14,"label":"MRN","text":"MRN-15FE5B1DAF"},{"start":15,"end":28,"label":"HOSPITAL_ID","text":"HSP-AS-935C09"},{"start":54,"end":64,"label":"VILLAGE","text":"Baksa Gaon"},{"start":71,"end":76,"label":"DISTRICT","text":"Baksa"},{"start":88,"end":102,"label":"PATIENT_NAME","text":"Man… | [] | as | asha_worker_note | oncology_chronic | 00475c261ac4462895b6d6d925a61083 | s10_split | train |
| 00b1897dc68c424b80d2b7bbcccfd5b8__0 | MRN-98E7212340 HSP-AS-91CD6B PHC ৰেজিষ্টাৰ — Kamrup Metropolitan Community Health Centre গাঁও Kamrup Metropolitan Tola জিলা Kamrup Metropolitan Pramod Brahma 22 Male ফোন 9033793835 আশা Binita Boro BPL-AS-210001-0018 ASV1234567 68-6322-1461-0285 ৰোগীজন পালমোনাৰী টিবিৰ (pulmonary TB) নিবিড় পৰ্যায়ৰ … | ["MRN","-","98","E","7212340","HSP","-","AS","-","91","CD","6","B","PHC","ৰ","ে","জ","ি","ষ","্","ট","া","ৰ","—","Kamrup","Metropolitan","Community","Health","Centre","গ","া","ঁ","ও","Kamrup","Metropolitan","Tola","জ","ি","ল","া","Kamrup","Metropolitan","Pramod","Brahma","22","Male","ফ","ো","ন","90… | [[0,4,"MRN"],[5,12,"HOSPITAL_ID"],[24,28,"HOSPITAL_NAME"],[33,35,"VILLAGE"],[40,41,"DISTRICT"],[42,43,"PATIENT_NAME"],[44,44,"AGE"],[45,45,"GENDER"],[49,49,"PHONE_NUMBER"],[52,53,"ASHA_WORKER_NAME"],[54,60,"BPL_RATION_CARD"],[61,62,"VOTER_ID"],[63,69,"ABHA_ID"]] | [{"start":0,"end":14,"label":"MRN","text":"MRN-98E7212340"},{"start":15,"end":28,"label":"HOSPITAL_ID","text":"HSP-AS-91CD6B"},{"start":45,"end":88,"label":"HOSPITAL_NAME","text":"Kamrup Metropolitan Community Health Centre"},{"start":94,"end":118,"label":"VILLAGE","text":"Kamrup Metropolitan Tola"… | [] | as | phc_register | tb_ncd | 00b1897dc68c424b80d2b7bbcccfd5b8 | s10_split | train |
| 00b464ab336f4892bfe5816f4911ffc0__0 | Pallavi Kalita 30 Female Rumi Das Barpeta Tola Barpeta 9564604439 Bikash Kalita BPL VOTER_ID Hindu MRN-861D9BD5E1 HSP-AS-9F2B7B Barpeta Primary Health Centre Dr. Ananya Sharma আশা কৰ্মীৰ টোকা — গাঁও: বৰপেটা টোলা, জিলা: বৰপেটা হিতাধিকাৰী: Pallavi Kalita, ৩০ / মহিলা আশা কৰ্মী: Rumi Das | ফোন: 9564604… | ["Pallavi","Kalita","30","Female","Rumi","Das","Barpeta","Tola","Barpeta","9564604439","Bikash","Kalita","BPL","VOTER","_","ID","Hindu","MRN","-","861","D","9","BD","5","E","1","HSP","-","AS","-","9","F","2","B","7","B","Barpeta","Primary","Health","Centre","Dr",".","Ananya","Sharma","আশ","া","কৰ",… | [[0,1,"PATIENT_NAME"],[2,2,"AGE"],[3,3,"GENDER"],[4,5,"ASHA_WORKER_NAME"],[6,7,"VILLAGE"],[8,8,"DISTRICT"],[9,9,"PHONE_NUMBER"],[10,11,"RELATIVE_NAME"],[12,12,"BPL_RATION_CARD"],[13,15,"VOTER_ID"],[16,16,"RELIGION"],[17,25,"MRN"],[26,35,"HOSPITAL_ID"],[36,39,"HOSPITAL_NAME"],[40,43,"DOCTOR_NAME"],[… | [{"start":0,"end":14,"label":"PATIENT_NAME","text":"Pallavi Kalita"},{"start":15,"end":17,"label":"AGE","text":"30"},{"start":18,"end":24,"label":"GENDER","text":"Female"},{"start":25,"end":33,"label":"ASHA_WORKER_NAME","text":"Rumi Das"},{"start":34,"end":46,"label":"VILLAGE","text":"Barpeta Tola"… | ["token_boundary_snap:RELATIVE_NAME:814-827->tok[468:469]chars[814:828]"] | as | asha_worker_note | psychiatry_behavioral | 00b464ab336f4892bfe5816f4911ffc0 | s10_split | train |
| 010ee165e8474452bbb8a41b8aecabdd__0 | HSP-AS-4A352E Ranjit Brahma MRN-CEA12A3B8B 36-7344-3050-0158 Lakhimpur Community Health Centre Lakhimpur Gaon Lakhimpur Male 18 8015331397 Bimala Devi BPL-AS-884712 VOTER-AS-77483921 Cane Cutter ইএছআই (ESI) ৰোগী, ডায়েবেটিক ফুট এবচেছ (diabetic foot abscess) ইনচিচন আৰু ড্ৰেইনেজৰ বাবে জৰুৰী ফ'ল'আপ। … | ["HSP","-","AS","-","4","A","352","E","Ranjit","Brahma","MRN","-","CEA","12","A","3","B","8","B","36","-","7344","-","3050","-","0158","Lakhimpur","Community","Health","Centre","Lakhimpur","Gaon","Lakhimpur","Male","18","8015331397","Bimala","Devi","BPL","-","AS","-","884712","VOTER","-","AS","-","… | [[0,7,"HOSPITAL_ID"],[8,9,"PATIENT_NAME"],[10,18,"MRN"],[19,25,"ABHA_ID"],[26,29,"HOSPITAL_NAME"],[30,31,"VILLAGE"],[32,32,"DISTRICT"],[33,33,"GENDER"],[34,34,"AGE"],[35,35,"PHONE_NUMBER"],[36,37,"ASHA_WORKER_NAME"],[38,42,"BPL_RATION_CARD"],[43,47,"VOTER_ID"],[48,49,"OCCUPATION"]] | [{"start":0,"end":13,"label":"HOSPITAL_ID","text":"HSP-AS-4A352E"},{"start":14,"end":27,"label":"PATIENT_NAME","text":"Ranjit Brahma"},{"start":28,"end":42,"label":"MRN","text":"MRN-CEA12A3B8B"},{"start":43,"end":60,"label":"ABHA_ID","text":"36-7344-3050-0158"},{"start":61,"end":94,"label":"HOSPITA… | [] | as | phc_register | surgical | 010ee165e8474452bbb8a41b8aecabdd | s10_split | train |
| 0124c44b385543a78312475b2fd524d9__0 | HSP-AS-881697 Sharad Brahma: Dhubri District Hospital-ত Dr. Anjali Sharma-ৰ সৈতে আইৰণ-ডেফিচিয়েন্সি এনিমিয়া ৱৰ্কআপৰ বাবে APT-240521-01 এপইণ্টমেণ্ট। নিশ্চিত কৰিবলৈ 9831273124-ত কল কৰক। MRN MRN-3680B62325। | ["HSP","-","AS","-","881697","Sharad","Brahma",":","Dhubri","District","Hospital","-","ত","Dr",".","Anjali","Sharma","-","ৰ","স","ৈ","ত","ে","আইৰণ","-","ড","ে","ফ","ি","চ","ি","য","়","ে","ন","্","স","ি","এন","ি","ম","ি","য","়","া","ৱৰ","্","কআপৰ","ব","া","ব","ে","APT","-","240521","-","01","এপইণ"… | [[0,4,"HOSPITAL_ID"],[5,6,"PATIENT_NAME"],[8,10,"HOSPITAL_NAME"],[13,16,"DOCTOR_NAME"],[52,56,"APPOINTMENT_ID"],[76,76,"PHONE_NUMBER"],[83,87,"MRN"]] | [{"start":0,"end":13,"label":"HOSPITAL_ID","text":"HSP-AS-881697"},{"start":14,"end":27,"label":"PATIENT_NAME","text":"Sharad Brahma"},{"start":29,"end":53,"label":"HOSPITAL_NAME","text":"Dhubri District Hospital"},{"start":56,"end":73,"label":"DOCTOR_NAME","text":"Dr. Anjali Sharma"},{"start":122,… | [] | as | automated_sms | general_medicine | 0124c44b385543a78312475b2fd524d9 | s10_split | train |
Cite this
MITtextCite
Tags
task_categories:token-classificationlanguage:aslanguage:bnlanguage:brxlanguage:doilanguage:enlanguage:gulanguage:hilanguage:knlanguage:koklanguage:kslanguage:mailanguage:mllanguage:mnilanguage:mrlanguage:nelanguage:orlanguage:palanguage:salanguage:satlanguage:sdlanguage:talanguage:telanguage:urlicense:mitsize_categories:10K<n<100Kformat:jsonmodality:textlibrary:datasetslibrary:pandaslibrary:polarslibrary:mlcroissantregion:usnamed-entity-recognitionglinersyntheticmedicalphipiiindia