{"id":"https://openalex.org/W4409546676","doi":"https://doi.org/10.3390/make7020036","title":"Machine-Learned Codes from EHR Data Predict Hard Outcomes Better than Human-Assigned ICD Codes","display_name":"Machine-Learned Codes from EHR Data Predict Hard Outcomes Better than Human-Assigned ICD Codes","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W4409546676","doi":"https://doi.org/10.3390/make7020036","pmid":"https://pubmed.ncbi.nlm.nih.gov/40406594"},"language":"en","primary_location":{"id":"doi:10.3390/make7020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7020036","pdf_url":"https://www.mdpi.com/2504-4990/7/2/36/pdf?version=1744885833","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/7/2/36/pdf?version=1744885833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100441319","display_name":"Ying Yin","orcid":"https://orcid.org/0000-0003-2156-4588"},"institutions":[{"id":"https://openalex.org/I1322918889","display_name":"United States Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98","country_code":"US","type":"government","lineage":["https://openalex.org/I1322918889"]},{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Yin","raw_affiliation_strings":["Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","Veterans Administration Hospital, Washington, DC 20422, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Veterans Administration Hospital, Washington, DC 20422, USA","institution_ids":["https://openalex.org/I1322918889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084025490","display_name":"Yijun Shao","orcid":"https://orcid.org/0000-0001-6419-7963"},"institutions":[{"id":"https://openalex.org/I1322918889","display_name":"United States Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98","country_code":"US","type":"government","lineage":["https://openalex.org/I1322918889"]},{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijun Shao","raw_affiliation_strings":["Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","Veterans Administration Hospital, Washington, DC 20422, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Veterans Administration Hospital, Washington, DC 20422, USA","institution_ids":["https://openalex.org/I1322918889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048344315","display_name":"Phillip Ma","orcid":"https://orcid.org/0000-0002-8302-5021"},"institutions":[{"id":"https://openalex.org/I1322918889","display_name":"United States Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98","country_code":"US","type":"government","lineage":["https://openalex.org/I1322918889"]},{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phillip Ma","raw_affiliation_strings":["Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","Veterans Administration Hospital, Washington, DC 20422, USA"],"raw_orcid":"https://orcid.org/0000-0002-8302-5021","affiliations":[{"raw_affiliation_string":"Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Veterans Administration Hospital, Washington, DC 20422, USA","institution_ids":["https://openalex.org/I1322918889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058747294","display_name":"Qing Zeng\u2010Treitler","orcid":"https://orcid.org/0000-0002-8353-7473"},"institutions":[{"id":"https://openalex.org/I1322918889","display_name":"United States Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98","country_code":"US","type":"government","lineage":["https://openalex.org/I1322918889"]},{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Zeng-Treitler","raw_affiliation_strings":["Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","Veterans Administration Hospital, Washington, DC 20422, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Veterans Administration Hospital, Washington, DC 20422, USA","institution_ids":["https://openalex.org/I1322918889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090492562","display_name":"Stuart J. Nelson","orcid":"https://orcid.org/0000-0002-8756-0179"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stuart J. Nelson","raw_affiliation_strings":["Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090492562"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.9057,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86832457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"7","issue":"2","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9973999857902527,"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/T12246","display_name":"Chronic Disease Management Strategies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.8918633460998535},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6713395118713379},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6294301152229309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270918846130371},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5926859378814697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5448848605155945},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.5398236513137817},{"id":"https://openalex.org/keywords/medical-classification","display_name":"Medical classification","score":0.5349223613739014},{"id":"https://openalex.org/keywords/icd-10","display_name":"ICD-10","score":0.5153098106384277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48103052377700806},{"id":"https://openalex.org/keywords/diagnosis-code","display_name":"Diagnosis code","score":0.44740018248558044},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.3878993093967438},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1763264536857605},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.1671401858329773},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11094442009925842},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.08513504266738892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0836564302444458}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8918633460998535},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6713395118713379},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6294301152229309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270918846130371},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5926859378814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5448848605155945},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.5398236513137817},{"id":"https://openalex.org/C154874363","wikidata":"https://www.wikidata.org/wiki/Q3518464","display_name":"Medical classification","level":2,"score":0.5349223613739014},{"id":"https://openalex.org/C2781116378","wikidata":"https://www.wikidata.org/wiki/Q45127","display_name":"ICD-10","level":2,"score":0.5153098106384277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48103052377700806},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.44740018248558044},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3878993093967438},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1763264536857605},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.1671401858329773},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11094442009925842},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.08513504266738892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0836564302444458},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/make7020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7020036","pdf_url":"https://www.mdpi.com/2504-4990/7/2/36/pdf?version=1744885833","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmid:40406594","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40406594","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine learning and knowledge extraction","raw_type":null},{"id":"pmh:oai:doaj.org/article:bfd2ce221be24564934906d739ead722","is_oa":true,"landing_page_url":"https://doaj.org/article/bfd2ce221be24564934906d739ead722","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 2, p 36 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12093355","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12093355","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mach Learn Knowl Extr","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make7020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7020036","pdf_url":"https://www.mdpi.com/2504-4990/7/2/36/pdf?version=1744885833","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2170086849","display_name":null,"funder_award_id":"R01 HS28450-01A1","funder_id":"https://openalex.org/F4320332177","funder_display_name":"Agency for Healthcare Research and Quality"},{"id":"https://openalex.org/G402897623","display_name":null,"funder_award_id":"1I21HX003278-01A1","funder_id":"https://openalex.org/F4320332177","funder_display_name":"Agency for Healthcare Research and Quality"}],"funders":[{"id":"https://openalex.org/F4320332177","display_name":"Agency for Healthcare Research and Quality","ror":"https://ror.org/03jmfdf59"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409546676.pdf","grobid_xml":"https://content.openalex.org/works/W4409546676.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2102735598","https://openalex.org/W2140302476","https://openalex.org/W2332766554","https://openalex.org/W2517388783","https://openalex.org/W2554528864","https://openalex.org/W2902513010","https://openalex.org/W2902537416","https://openalex.org/W2939246364","https://openalex.org/W2959410487","https://openalex.org/W3004598824","https://openalex.org/W3118857047","https://openalex.org/W4309650827","https://openalex.org/W4397022293","https://openalex.org/W4403851051","https://openalex.org/W6766021862","https://openalex.org/W6810747344"],"related_works":["https://openalex.org/W4377564205","https://openalex.org/W1546356981","https://openalex.org/W4292539280","https://openalex.org/W57843728","https://openalex.org/W2208652537","https://openalex.org/W2967362169","https://openalex.org/W4367669108","https://openalex.org/W2804342371","https://openalex.org/W2802989430","https://openalex.org/W3096672025"],"abstract_inverted_index":{"We":[0,68],"used":[1],"machine":[2,137],"learning":[3,138],"(ML)":[4],"to":[5],"characterize":[6],"894,154":[7],"medical":[8],"records":[9,70],"of":[10,25,27,31,71,95,97,125,152,175],"outpatient":[11],"visits":[12],"from":[13],"the":[14,23,43,47,61,66,79,121,148,176],"Veterans":[15],"Administration":[16],"Central":[17],"Data":[18],"Warehouse":[19],"(VA":[20],"CDW)":[21],"by":[22,179],"likelihood":[24],"assignment":[26,145],"200":[28],"International":[29],"Classification":[30],"Diseases":[32],"(ICD)":[33],"code":[34,48,63,114,123,144,180],"blocks.":[35,181],"Using":[36],"four":[37],"different":[38],"predictive":[39],"models,":[40],"we":[41],"found":[42],"ML-derived":[44,122],"predictions":[45],"for":[46],"blocks":[49,124],"were":[50,83],"consistently":[51,84],"more":[52,171],"effective":[53],"in":[54,65,103],"predicting":[55,147],"death":[56,153],"or":[57,154],"90-day":[58],"rehospitalization":[59],"than":[60,86,142,173],"assigned":[62,112],"block":[64,115],"record.":[67],"reviewed":[69],"ICD":[72,113],"chapter":[73,81],"assignments.":[74],"The":[75],"review":[76],"revealed":[77],"that":[78,100,169,174],"ML-predicted":[80],"assignments":[82],"better":[85,141],"those":[87],"humanly":[88],"assigned.":[89],"Impact":[90],"factor":[91],"analysis,":[92],"a":[93,117],"method":[94],"explanation":[96],"AI":[98],"findings":[99],"was":[101,139],"developed":[102],"our":[104],"group,":[105],"demonstrated":[106],"little":[107],"effect":[108],"on":[109,120],"any":[110],"one":[111],"but":[116],"marked":[118],"impact":[119],"kidney":[126],"disease":[127],"as":[128,130,164,166],"well":[129,165],"several":[131],"other":[132,162],"morbidities.":[133],"In":[134],"this":[135],"study,":[136],"much":[140],"human":[143],"at":[146],"relatively":[149],"rare":[150],"outcomes":[151],"rehospitalization.":[155],"Future":[156],"work":[157],"will":[158],"address":[159],"generalizability":[160],"using":[161],"datasets,":[163],"addressing":[167],"coding":[168],"is":[170],"nuanced":[172],"categorization":[177],"provided":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}