{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T08:32:59Z","timestamp":1793781179428,"version":"4.6.1"},"reference-count":32,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010096","name":"Southern Medical University","doi-asserted-by":"publisher","award":["2023B002"],"award-info":[{"award-number":["2023B002"]}],"id":[{"id":"10.13039\/501100010096","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"Chinese Academy of Medical Sciences Initiative for Innovative Medicine","doi-asserted-by":"publisher","award":["2025-I2M-XHJC-002"],"award-info":[{"award-number":["2025-I2M-XHJC-002"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"Chinese Academy of Medical Sciences Initiative for Innovative Medicine","doi-asserted-by":"publisher","award":["2025-I2M-XHXX-020"],"award-info":[{"award-number":["2025-I2M-XHXX-020"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"Chinese Academy of Medical Sciences Initiative for Innovative Medicine","doi-asserted-by":"publisher","award":["2024-I2M-TS-002"],"award-info":[{"award-number":["2024-I2M-TS-002"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"Chinese Academy of Medical Sciences Initiative for Innovative Medicine","doi-asserted-by":"publisher","award":["T-A-003"],"award-info":[{"award-number":["T-A-003"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"Chinese Academy of Medical Sciences Initiative for Innovative Medicine","doi-asserted-by":"publisher","award":["2023-I2M-C&T-A-003"],"award-info":[{"award-number":["2023-I2M-C&T-A-003"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515110749"],"award-info":[{"award-number":["2023A1515110749"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003345","name":"CAMS","doi-asserted-by":"publisher","award":["2019PT320025"],"award-info":[{"award-number":["2019PT320025"]}],"id":[{"id":"10.13039\/501100003345","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010112","name":"Southern Medical University Nanfang Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010112","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005150","name":"Chinese Academy of Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005150","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82402760"],"award-info":[{"award-number":["82402760"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82572698"],"award-info":[{"award-number":["82572698"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82402889"],"award-info":[{"award-number":["82402889"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC2507700"],"award-info":[{"award-number":["2023YFC2507700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Genetics and Genomics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jgg.2026.02.009","type":"journal-article","created":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T23:37:02Z","timestamp":1771112222000},"page":"1292-1304","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"title":["Bridging clinical narratives and structured phenotypes with large language models and sentence transformers"],"prefix":"10.1016","volume":"53","author":[{"given":"Jihao","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guozhuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Hospedales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianle","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terry Jianguo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zefu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9429-2889","authenticated-orcid":false,"given":"Nan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jgg.2026.02.009_bib1","doi-asserted-by":"crossref","DOI":"10.2196\/12596","article-title":"Identifying clinical terms in medical text using ontology-guided machine learning","volume":"7","author":"Arbabi","year":"2019","journal-title":"JMIR Med. Inform."},{"key":"10.1016\/j.jgg.2026.02.009_bib2","series-title":"Qwen Technical Report,. arXiv,","author":"Bai","year":"2023"},{"key":"10.1016\/j.jgg.2026.02.009_bib3","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.jgg.2026.02.009_bib4","doi-asserted-by":"crossref","first-page":"3280","DOI":"10.1038\/s41467-025-56989-2","article-title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","volume":"16","author":"Chen","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.jgg.2026.02.009_bib5","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.ajhg.2021.12.008","article-title":"PhenoApt leverages clinical expertise to prioritize candidate genes via machine learning","volume":"109","author":"Chen","year":"2022","journal-title":"Am. J. Hum. Genet."},{"key":"10.1016\/j.jgg.2026.02.009_bib6","article-title":"DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning","author":"DeepSeek-AI","year":"2025","journal-title":"arXiv, arXiv:2501.12948"},{"key":"10.1016\/j.jgg.2026.02.009_bib7","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1038\/s41436-018-0381-1","article-title":"ClinPhen extracts and prioritizes patient phenotypes directly from medical records to expedite genetic disease diagnosis","volume":"21","author":"Deisseroth","year":"2019","journal-title":"Genet. Med."},{"key":"10.1016\/j.jgg.2026.02.009_bib8","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/jamia\/ocw177","article-title":"MetaMap Lite: an evaluation of a new java implementation of MetaMap","volume":"24","author":"Demner-Fushman","year":"2017","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jgg.2026.02.009_bib9","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv, arXiv: 1810.04805"},{"key":"10.1016\/j.jgg.2026.02.009_bib10","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1109\/TCBB.2022.3170301","article-title":"PhenoBERT: a combined deep learning method for automated recognition of human phenotype ontology","volume":"20","author":"Feng","year":"2023","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"10.1016\/j.jgg.2026.02.009_bib11","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.ajhg.2018.08.003","article-title":"PubCaseFinder: a case-report-based, phenotype-driven differential-diagnosis system for rare diseases","volume":"103","author":"Fujiwara","year":"2018","journal-title":"Am. J. Hum. Genet."},{"key":"10.1016\/j.jgg.2026.02.009_bib12","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13073-025-01521-w","article-title":"Improving automated deep phenotyping through large language models using retrieval-augmented generation","volume":"17","author":"Garcia","year":"2025","journal-title":"Genome Med."},{"key":"10.1016\/j.jgg.2026.02.009_bib13","doi-asserted-by":"crossref","first-page":"D1333","DOI":"10.1093\/nar\/gkad1005","article-title":"The Human Phenotype Ontology in 2024: phenotypes around the world","volume":"52","author":"Gargano","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"10.1016\/j.jgg.2026.02.009_bib14","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv,"},{"key":"10.1016\/j.jgg.2026.02.009_bib15","doi-asserted-by":"crossref","first-page":"btae406","DOI":"10.1093\/bioinformatics\/btae406","article-title":"FastHPOCR: pragmatic, fast, and accurate concept recognition using the human phenotype ontology","volume":"40","author":"Groza","year":"2024","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jgg.2026.02.009_bib16","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1186\/s12911-022-01927-1","article-title":"PheNominal: an EHR-integrated web application for structured deep phenotyping at the point of care","volume":"22","author":"Havrilla","year":"2022","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.jgg.2026.02.009_bib17","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1038\/s41436-018-0072-y","article-title":"Phrank measures phenotype sets similarity to greatly improve Mendelian diagnostic disease prioritization","volume":"21","author":"Jagadeesh","year":"2019","journal-title":"Genet. Med."},{"key":"10.1016\/j.jgg.2026.02.009_bib18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4258\/hir.2019.25.1.1","article-title":"Managing unstructured big data in healthcare system","volume":"25","author":"Kong","year":"2019","journal-title":"Healthc. Inform. Res."},{"key":"10.1016\/j.jgg.2026.02.009_bib19","doi-asserted-by":"crossref","first-page":"W566","DOI":"10.1093\/nar\/gkz386","article-title":"Doc2Hpo: a web application for efficient and accurate HPO concept curation","volume":"47","author":"Liu","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.jgg.2026.02.009_bib20","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1093\/bioinformatics\/btab019","article-title":"PhenoTagger: a hybrid method for phenotype concept recognition using human phenotype ontology","volume":"37","author":"Luo","year":"2021","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jgg.2026.02.009_bib21","article-title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","author":"McInnes","year":"2018","journal-title":"arXiv,"},{"key":"10.1016\/j.jgg.2026.02.009_bib22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1056\/NEJMoa1516767","article-title":"Resolution of disease phenotypes resulting from multilocus genomic variation","volume":"376","author":"Posey","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"10.1016\/j.jgg.2026.02.009_bib23","article-title":"Sentence-BERT: sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019","journal-title":"arXiv,"},{"key":"10.1016\/j.jgg.2026.02.009_bib24","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1038\/gim.2015.30","article-title":"Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology","volume":"17","author":"Richards","year":"2015","journal-title":"Genet. Med."},{"key":"10.1016\/j.jgg.2026.02.009_bib25","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jgg.2026.02.009_bib26","doi-asserted-by":"crossref","first-page":"S14","DOI":"10.1186\/1471-2105-10-S9-S14","article-title":"Comparison of concept recognizers for building the Open Biomedical Annotator","volume":"10","author":"Shah","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"10.1016\/j.jgg.2026.02.009_bib27","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.ajhg.2018.05.010","article-title":"Deep phenotyping on electronic health records facilitates genetic diagnosis by clinical exomes","volume":"103","author":"Son","year":"2018","journal-title":"Am. J. Hum. Genet."},{"key":"10.1016\/j.jgg.2026.02.009_bib28","doi-asserted-by":"crossref","first-page":"bau045","DOI":"10.1093\/database\/bau045","article-title":"Automated semantic annotation of rare disease cases: a case study","volume":"2014","author":"Taboada","year":"2014","journal-title":"Database (Oxford)"},{"key":"10.1016\/j.jgg.2026.02.009_bib29","article-title":"Gemma 3 Technical Report","author":"Team","year":"2025","journal-title":"arXiv,"},{"key":"10.1016\/j.jgg.2026.02.009_bib30","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1038\/nmeth.3484","article-title":"Phenolyzer: phenotype-based prioritization of candidate genes for human diseases","volume":"12","author":"Yang","year":"2015","journal-title":"Nat. Methods."},{"key":"10.1016\/j.jgg.2026.02.009_bib31","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2023.100887","article-title":"Enhancing phenotype recognition in clinical notes using large language models: PhenoBCBERT and PhenoGPT","volume":"5","author":"Yang","year":"2024","journal-title":"Patterns"},{"key":"10.1016\/j.jgg.2026.02.009_bib32","article-title":"Judging LLM-as-a-judge with MT-bench and Chatbot Arena","author":"Zheng","year":"2023","journal-title":"arXiv,"}],"container-title":["Journal of Genetics and Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1673852726000536?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1673852726000536?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T22:12:06Z","timestamp":1785967926000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1673852726000536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":32,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["S1673852726000536"],"URL":"https:\/\/doi.org\/10.1016\/j.jgg.2026.02.009","relation":{},"ISSN":["1673-8527"],"issn-type":[{"value":"1673-8527","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bridging clinical narratives and structured phenotypes with large language models and sentence transformers","name":"articletitle","label":"Article Title"},{"value":"Journal of Genetics and Genomics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jgg.2026.02.009","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Institute of Genetics and Developmental Biology, Chinese Academy of Sciences, and Genetics Society of China. Published by Elsevier Limited and Science Press.","name":"copyright","label":"Copyright"}]}}