{"id":"https://openalex.org/W3103901889","doi":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","title":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining","display_name":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3103901889","doi":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","mag":"3103901889"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.clinicalnlp-1.3","doi":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","pdf_url":"https://www.aclweb.org/anthology/2020.clinicalnlp-1.3.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/2020.clinicalnlp-1.3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045955332","display_name":"Zachariah Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachariah Zhang","raw_affiliation_strings":["NYU Langone Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Langone Health","institution_ids":["https://openalex.org/I4210086933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043432558","display_name":"Jingshu Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingshu Liu","raw_affiliation_strings":["NYU Langone Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Langone Health","institution_ids":["https://openalex.org/I4210086933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079997593","display_name":"Narges Razavian","orcid":"https://orcid.org/0000-0002-9922-6370","observed_orcids":["https://orcid.org/0000-0002-9922-6370"]},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Narges Razavian","raw_affiliation_strings":["NYU Langone Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Langone Health","institution_ids":["https://openalex.org/I4210086933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079997593"],"corresponding_institution_ids":["https://openalex.org/I4210086933"],"apc_list":null,"apc_paid":null,"fwci":4.9612,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.96416009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9897000193595886,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9897000193595886,"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/T14400","display_name":"Medical Coding and Health Information","score":0.007600000128149986,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0008999999845400453,"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/icd-coding","display_name":"ICD coding","score":0.9110000133514404},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.8339999914169312},{"id":"https://openalex.org/keywords/unsupervised-pretraining","display_name":"unsupervised pre-training","score":0.8880000114440918},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.8730000257492065},{"id":"https://openalex.org/keywords/clinical-notes","display_name":"clinical notes","score":0.6179999709129333},{"id":"https://openalex.org/keywords/large-scale-text-classification","display_name":"large-scale text classification","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145692348480225},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7037397623062134},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6779994964599609},{"id":"https://openalex.org/C2781116378","wikidata":"https://www.wikidata.org/wiki/Q45127","display_name":"ICD-10","level":2,"score":0.5767063498497009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4831125736236572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47154501080513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41960710287094116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33627721667289734},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20018866658210754},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08312231302261353},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2020.clinicalnlp-1.3","doi":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","pdf_url":"https://www.aclweb.org/anthology/2020.clinicalnlp-1.3.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.03685","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.03685","pdf_url":"https://arxiv.org/pdf/2006.03685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2006.03685","doi":"https://doi.org/10.48550/arxiv.2006.03685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.03685","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.clinicalnlp-1.3","doi":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.clinicalnlp-1.3","pdf_url":"https://www.aclweb.org/anthology/2020.clinicalnlp-1.3.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.46810001134872437,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3103901889.pdf","grobid_xml":"https://content.openalex.org/works/W3103901889.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1995228216","https://openalex.org/W2072610178","https://openalex.org/W2122402213","https://openalex.org/W2133564696","https://openalex.org/W2146089916","https://openalex.org/W2146353025","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2396881363","https://openalex.org/W2517388783","https://openalex.org/W2577790096","https://openalex.org/W2626778328","https://openalex.org/W2757643185","https://openalex.org/W2768948924","https://openalex.org/W2769851464","https://openalex.org/W2778088240","https://openalex.org/W2787560479","https://openalex.org/W2798843374","https://openalex.org/W2886093373","https://openalex.org/W2896457183","https://openalex.org/W2899246880","https://openalex.org/W2899313146","https://openalex.org/W2911379778","https://openalex.org/W2911489562","https://openalex.org/W2919809473","https://openalex.org/W2925863688","https://openalex.org/W2937845937","https://openalex.org/W2947620613","https://openalex.org/W2948196927","https://openalex.org/W2952370363","https://openalex.org/W2955483668","https://openalex.org/W2962779279","https://openalex.org/W2962912956","https://openalex.org/W2963341956","https://openalex.org/W2963716420","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2964386916","https://openalex.org/W2964548917","https://openalex.org/W2965570621","https://openalex.org/W2987098737"],"related_works":["https://openalex.org/W4365791286","https://openalex.org/W3155761178","https://openalex.org/W4205600812","https://openalex.org/W7202361377","https://openalex.org/W7214121561","https://openalex.org/W3213934720","https://openalex.org/W4287854971","https://openalex.org/W4327862449","https://openalex.org/W4320151811","https://openalex.org/W4392798748"],"abstract_inverted_index":{"ICD":[0,53,105,120],"coding":[1,8,54,106],"is":[2,20],"the":[3,68,101,111,117],"task":[4,123],"of":[5,55,67,74,113,126,132],"classifying":[6],"and":[7,12,25,94],"all":[9],"diagnoses,":[10],"symptoms":[11],"procedures":[13],"associated":[14],"with":[15,87,107],"a":[16,44,72,78],"patient's":[17],"visit.The":[18],"process":[19],"often":[21],"manual,":[22],"extremely":[23],"time-consuming":[24],"expensive":[26],"for":[27,49,91,104],"hospitals":[28],"as":[29],"clinical":[30],"interactions":[31],"are":[32],"usually":[33],"recorded":[34],"in":[35],"free":[36],"text":[37],"medical":[38],"notes.In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"machine":[45],"learning":[46,86],"model,":[47],"BERT-XML,":[48],"large":[50,118],"scale":[51,119],"automated":[52],"EHR":[56,84,92,127],"notes,":[57,85],"utilizing":[58],"recently":[59],"developed":[60],"unsupervised":[61],"pretraining":[62],"that":[63],"have":[64],"achieved":[65],"state":[66],"art":[69],"performance":[70],"on":[71,83,116],"variety":[73],"NLP":[75],"tasks.We":[76],"train":[77],"BERT":[79,102],"model":[80],"from":[81],"scratch":[82],"vocabulary":[88],"better":[89],"suited":[90],"tasks":[93],"thus":[95],"outperform":[96],"off-the-shelf":[97],"models.We":[98],"further":[99],"adapt":[100],"architecture":[103],"multi-label":[108],"attention.We":[109],"demonstrate":[110],"effectiveness":[112],"BERT-based":[114],"models":[115],"code":[121],"classification":[122],"using":[124],"millions":[125],"notes":[128],"to":[129],"predict":[130],"thousands":[131],"unique":[133],"codes.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":12}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-11-23T00:00:00"}