{"id":"https://openalex.org/W4390992069","doi":"https://doi.org/10.1109/bibm58861.2023.10386068","title":"A domain adaptive pre-training language model for sentence classification of Chinese electronic medical record","display_name":"A domain adaptive pre-training language model for sentence classification of Chinese electronic medical record","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390992069","doi":"https://doi.org/10.1109/bibm58861.2023.10386068"},"language":"en","primary_location":{"id":"doi:10.1109/bibm58861.2023.10386068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10386068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104230935","display_name":"Yilin Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Zou","raw_affiliation_strings":["University of Chinese Academy of Sciences,Key Laboratory of Systems Health Science of Zhejiang Province,School of Life Science Hangzhou Institute for Advanced Study,Hangzhou,China","School of Life Science Hangzhou Institute for Advanced Study, Key Laboratory of Systems Health Science of Zhejiang Province, University of Chinese Academy of Sciences, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Key Laboratory of Systems Health Science of Zhejiang Province,School of Life Science Hangzhou Institute for Advanced Study,Hangzhou,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Life Science Hangzhou Institute for Advanced Study, Key Laboratory of Systems Health Science of Zhejiang Province, University of Chinese Academy of Sciences, Hangzhou, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003677173","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-9211-6582"},"institutions":[{"id":"https://openalex.org/I4210096013","display_name":"Shanghai Institute of Nutrition and Health","ror":"https://ror.org/00rytkh49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210096013"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068195220","display_name":"Yunchao Ling","orcid":"https://orcid.org/0000-0002-5438-0753"},"institutions":[{"id":"https://openalex.org/I4210096013","display_name":"Shanghai Institute of Nutrition and Health","ror":"https://ror.org/00rytkh49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210096013"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Ling","raw_affiliation_strings":["Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112480254","display_name":"Daqing Lv","orcid":"https://orcid.org/0009-0003-5678-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daqing Lv","raw_affiliation_strings":["Shanghai Southgene Technology Co., Ltd,Shanghai,China","Shanghai Southgene Technology Co., Ltd, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Southgene Technology Co., Ltd,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Southgene Technology Co., Ltd, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651748","display_name":"Ziming Li","orcid":"https://orcid.org/0009-0004-7529-7176"},"institutions":[{"id":"https://openalex.org/I2802608112","display_name":"Shanghai Chest Hospital","ror":"https://ror.org/03fjc3817","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802608112"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Li","raw_affiliation_strings":["Shanghai Chest Hospital,Shanghai,China","Shanghai Chest Hospital, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Chest Hospital,Shanghai,China","institution_ids":["https://openalex.org/I2802608112"]},{"raw_affiliation_string":"Shanghai Chest Hospital, Shanghai, China","institution_ids":["https://openalex.org/I2802608112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582857","display_name":"Shun Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096013","display_name":"Shanghai Institute of Nutrition and Health","ror":"https://ror.org/00rytkh49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210096013"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Lu","raw_affiliation_strings":["Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences. Shanghai Sixth People’s Hospital,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences. Shanghai Sixth People’s Hospital,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419052","display_name":"Guoqing Zhang","orcid":"https://orcid.org/0000-0001-8827-7546"},"institutions":[{"id":"https://openalex.org/I4210096013","display_name":"Shanghai Institute of Nutrition and Health","ror":"https://ror.org/00rytkh49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210096013"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Zhang","raw_affiliation_strings":["Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences,CAS Key Laboratory of Computational Biology,Bio-Med Big Data Center,Shanghai,China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210096013","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67470869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4776","last_page":"4783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8133005499839783},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6471094489097595},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6138647198677063},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5561825633049011},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.5242907404899597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236751437187195},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5090908408164978},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4970898926258087},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.4894663095474243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4755384922027588},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.44787153601646423},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4230080246925354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39549940824508667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133005499839783},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6471094489097595},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6138647198677063},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5561825633049011},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.5242907404899597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236751437187195},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5090908408164978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4970898926258087},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.4894663095474243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4755384922027588},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.44787153601646423},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4230080246925354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39549940824508667},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm58861.2023.10386068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10386068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2114361266","https://openalex.org/W2801547136","https://openalex.org/W2889764698","https://openalex.org/W2896457183","https://openalex.org/W2950784811","https://openalex.org/W2952370363","https://openalex.org/W2965373594","https://openalex.org/W2976476443","https://openalex.org/W3012073743","https://openalex.org/W3021636956","https://openalex.org/W3023618320","https://openalex.org/W3034238904","https://openalex.org/W3102725307","https://openalex.org/W3128338931","https://openalex.org/W3155510817","https://openalex.org/W3169341408","https://openalex.org/W3173606101","https://openalex.org/W3183580055","https://openalex.org/W3199484478","https://openalex.org/W3201908633","https://openalex.org/W3212459720","https://openalex.org/W3213921583","https://openalex.org/W4205410133","https://openalex.org/W4206217845","https://openalex.org/W4231122779","https://openalex.org/W4281946158","https://openalex.org/W4293574676","https://openalex.org/W4327566711","https://openalex.org/W4386942538","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6838876490"],"related_works":["https://openalex.org/W2793132289","https://openalex.org/W4387517132","https://openalex.org/W3094868181","https://openalex.org/W3116252395","https://openalex.org/W4281560212","https://openalex.org/W3180764077","https://openalex.org/W2769084352","https://openalex.org/W4386322467","https://openalex.org/W2997394673","https://openalex.org/W4385574021"],"abstract_inverted_index":{"Accurately":[0],"extracting":[1],"and":[2,21,82,130,147,187],"classifying":[3],"Chinese":[4,102,106],"electronic":[5],"medical":[6,15,22,55,77,107,172],"record":[7],"(EMR),":[8],"which":[9,134],"contain":[10],"huge":[11],"amounts":[12],"of":[13,28,40,61,101,113,176],"valuable":[14],"information,":[16],"have":[17],"promising":[18],"practical":[19],"application":[20],"value":[23],"in":[24],"the":[25,31,38,49,67,111,120,138,144,159,165,177,182],"health":[26],"care":[27],"China.":[29],"While":[30],"pivotal":[32],"issue":[33],"has":[34],"gathered":[35],"escalating":[36],"attention,":[37],"bulk":[39],"current":[41],"research":[42],"is":[43,124,156],"directed":[44],"towards":[45],"operations":[46],"conducted":[47],"at":[48,66,193],"document":[50],"or":[51],"entity":[52],"level":[53],"within":[54,171,181],"records.":[56],"Only":[57],"a":[58,70,90,131],"restricted":[59],"body":[60],"work":[62],"addresses":[63],"these":[64],"concerns":[65],"sentence":[68,99],"level,":[69],"critical":[71],"aspect":[72],"for":[73,98,118],"downstream":[74],"tasks":[75],"like":[76],"information":[78],"retrieval,":[79],"diagnosis":[80],"normalization,":[81],"question":[83],"answering.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"present":[89],"domain":[91,108],"adaptive":[92],"pre-training":[93,119],"language":[94,121],"model":[95],"named":[96],"CEMR-LM":[97,104,155,163],"classification":[100],"EMRs.":[103],"acquires":[105],"knowledge":[109],"through":[110],"utilization":[112],"copious":[114],"unlabeled":[115],"clinical":[116],"corpus":[117],"model.":[122,183],"This":[123],"fortified":[125],"by":[126,174],"combining":[127],"fine-tuning":[128],"strategy":[129],"dual-channel":[132],"mechanism,":[133],"collectively":[135],"contribute":[136],"to":[137,158,167],"model\u2019s":[139],"heightened":[140],"performance.":[141],"Experiments":[142],"on":[143],"benchmark":[145],"dataset":[146,151],"real":[148],"world":[149],"hospital":[150],"both":[152],"demonstrate":[153],"that":[154],"superior":[157],"state-of-the-art":[160],"methods.":[161],"Furthermore,":[162],"possesses":[164],"capability":[166],"elucidate":[168],"indicative":[169],"elements":[170],"records":[173],"visualizing":[175],"attention":[178],"weights":[179],"embedded":[180],"The":[184],"implemented":[185],"code":[186],"experimental":[188],"datasets":[189],"are":[190],"available":[191],"online":[192],"https://github.com/BioMedBigDataCenter/CEMR-LM.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}