{"id":"https://openalex.org/W4406354464","doi":"https://doi.org/10.1109/jbhi.2025.3529598","title":"PhenoAlign: A Hybrid Data-Knowledge-Driven Approach for Precisely Aligning Phenotype Information in Medical Texts","display_name":"PhenoAlign: A Hybrid Data-Knowledge-Driven Approach for Precisely Aligning Phenotype Information in Medical Texts","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406354464","doi":"https://doi.org/10.1109/jbhi.2025.3529598","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031079"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3529598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3529598","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5049101532","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0002-7521-4295"},"institutions":[{"id":"https://openalex.org/I92039509","display_name":"Guangzhou Medical University","ror":"https://ror.org/00zat6v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I92039509"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Guangzhou Medical University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7521-4295","affiliations":[{"raw_affiliation_string":"Guangzhou Medical University, Guangzhou, China","institution_ids":["https://openalex.org/I92039509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041469756","display_name":"Luming Chen","orcid":"https://orcid.org/0000-0003-2468-8631"},"institutions":[{"id":"https://openalex.org/I92039509","display_name":"Guangzhou Medical University","ror":"https://ror.org/00zat6v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I92039509"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luming Chen","raw_affiliation_strings":["Guangzhou Medical University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2468-8631","affiliations":[{"raw_affiliation_string":"Guangzhou Medical University, Guangzhou, China","institution_ids":["https://openalex.org/I92039509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080371739","display_name":"Lizong Deng","orcid":"https://orcid.org/0000-0001-9314-262X"},"institutions":[{"id":"https://openalex.org/I200296433","display_name":"Chinese Academy of Medical Sciences & Peking Union Medical College","ror":"https://ror.org/02drdmm93","country_code":"CN","type":"education","lineage":["https://openalex.org/I200296433"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizong Deng","raw_affiliation_strings":["Institute of Systems Medicine, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9314-262X","affiliations":[{"raw_affiliation_string":"Institute of Systems Medicine, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China","institution_ids":["https://openalex.org/I200296433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062116814","display_name":"Taijiao Jiang","orcid":"https://orcid.org/0000-0002-6280-6347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taijiao Jiang","raw_affiliation_strings":["Guangzhou National Laboratory, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory, Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00480845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"12","first_page":"9147","last_page":"9157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9853000044822693,"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/T10028","display_name":"Topic Modeling","score":0.9812999963760376,"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":0.7245808839797974},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3993430733680725},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3926151692867279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34493738412857056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245808839797974},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3993430733680725},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3926151692867279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34493738412857056}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2025.3529598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3529598","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:40031079","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031079","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":"IEEE journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G5226932133","display_name":null,"funder_award_id":"2021YFC2302001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2100133323","https://openalex.org/W2122402213","https://openalex.org/W2128084896","https://openalex.org/W2137724373","https://openalex.org/W2164572080","https://openalex.org/W2179498003","https://openalex.org/W2263904841","https://openalex.org/W2272393342","https://openalex.org/W2762181533","https://openalex.org/W2768488789","https://openalex.org/W2774466664","https://openalex.org/W2896457183","https://openalex.org/W2898031839","https://openalex.org/W2909934462","https://openalex.org/W2913694856","https://openalex.org/W2918098129","https://openalex.org/W2924820166","https://openalex.org/W2946102094","https://openalex.org/W2951146425","https://openalex.org/W2976298486","https://openalex.org/W2998447272","https://openalex.org/W3004612364","https://openalex.org/W3049575036","https://openalex.org/W3087028093","https://openalex.org/W3161053278","https://openalex.org/W3162922479","https://openalex.org/W3172260675","https://openalex.org/W4282923852","https://openalex.org/W4310786130","https://openalex.org/W4322766882","https://openalex.org/W4383711355","https://openalex.org/W4384071683","https://openalex.org/W4384561707","https://openalex.org/W4385948838","https://openalex.org/W4386275705","https://openalex.org/W4387665659","https://openalex.org/W4389894040","https://openalex.org/W4390692489","https://openalex.org/W4403511268"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Precisely":[0],"aligning":[1,129],"phenotypic":[2,59,130,146],"information":[3,39,60,131,211],"within":[4],"medical":[5,12,62,120,135,144,208,220,226],"texts":[6],"is":[7,31],"paramount":[8],"in":[9,185,198],"advancing":[10],"intelligent":[11,219],"applications,":[13,221],"such":[14],"as":[15],"similar":[16],"patient":[17,223],"case":[18],"retrieval.":[19],"However,":[20],"despite":[21],"its":[22],"criticality,":[23],"an":[24,49,157],"algorithm":[25],"specifically":[26],"designed":[27],"for":[28,99,166,207],"this":[29,65,199],"task":[30],"lacking.":[32],"We":[33,201],"previously":[34],"introduced":[35],"a":[36,85,96,118,203],"fine-grained":[37],"semantic":[38,42],"model,":[40],"the":[41,77,108,149,180],"structured":[43],"unit":[44],"of":[45,161,183],"phenotypes":[46],"(PhenoSSU),":[47],"and":[48,57,95,111,169,173,189,225],"automatic":[50],"extraction":[51,112,168],"algorithm.":[52],"This":[53,125,213],"model":[54,89],"accurately":[55],"characterizes":[56],"extracts":[58],"from":[61],"texts.":[63],"In":[64],"study,":[66],"we":[67,114],"explore":[68],"different":[69],"PhenoSSU":[70,109],"alignment":[71,110,123,139,147,170,187],"strategies.":[72],"The":[73,163],"results":[74],"show":[75],"that":[76],"data-knowledge-driven":[78],"approach":[79],"best":[80],"aligns":[81],"PhenoSSUs.":[82],"Specifically,":[83],"employing":[84],"BERT-based":[86],"pre-trained":[87],"language":[88,196],"(PLMs)":[90],"to":[91,179,218],"align":[92],"phrase-type":[93],"PhenoSSUs":[94,101],"knowledge-based":[97],"method":[98],"logic-type":[100],"demonstrates":[102],"efficacy.":[103],"Moreover,":[104],"by":[105,132,194],"successfully":[106],"integrating":[107],"algorithms,":[113],"have":[115],"developed":[116,202],"PhenoAlign,":[117],"novel":[119],"text":[121,145,209],"phenotype":[122,186,210],"tool.":[124],"tool":[126,206,214],"facilitates":[127],"precisely":[128],"processing":[133],"two":[134],"texts,":[136],"generating":[137],"accurate":[138],"outcomes.":[140],"PhenoAlign":[141],"exhibited":[142],"satisfactory":[143],"using":[148],"expert":[150],"annotated":[151],"gold":[152],"standard":[153],"test":[154],"set,":[155],"with":[156],"end-to-end":[158],"F1":[159,164],"score":[160],"0.820.":[162],"scores":[165],"phenoSSU":[167],"were":[171],"0.885":[172],"0.927,":[174],"respectively.":[175],"Our":[176],"analysis":[177],"extends":[178],"potential":[181],"application":[182],"ChatGPT":[184],"tasks,":[188],"find":[190],"significant":[191],"challenges":[192],"encountered":[193],"large":[195],"models":[197],"domain.":[200],"simple,":[204],"effective":[205],"alignment.":[212],"will":[215],"be":[216],"valuable":[217],"facilitating":[222],"care":[224],"research":[227],"advancements.":[228]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}