{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T22:45:56Z","timestamp":1787870756113,"version":"build-2784847793"},"reference-count":29,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:00:00Z","timestamp":1729641600000},"content-version":"vor","delay-in-days":296,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This manuscript presents PheNormGPT, a framework for extraction and normalization of key findings in clinical text. PheNormGPT relies on an innovative approach, leveraging large language models to extract key findings and phenotypic data in unstructured clinical text and map them to Human Phenotype Ontology concepts. It utilizes OpenAI\u2019s GPT-3.5 Turbo and GPT-4 models with fine-tuning and few-shot learning strategies, including a novel few-shot learning strategy for custom-tailored few-shot example selection per request. PheNormGPT was evaluated in the BioCreative VIII Track 3: Genetic Phenotype Extraction from Dysmorphology Physical Examination Entries shared task. PheNormGPT achieved an F1 score of 0.82 for standard matching and 0.72 for exact matching, securing first place for this shared task.<\/jats:p>","DOI":"10.1093\/database\/baae103","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T16:09:16Z","timestamp":1729699756000},"source":"Crossref","is-referenced-by-count":3,"title":["PheNormGPT: a framework for extraction and normalization of key medical findings"],"prefix":"10.1093","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4534-0055","authenticated-orcid":false,"given":"Ekin","family":"Soysal","sequence":"first","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston , 7000 Fannin St #600, Houston, TX 77030,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6525-5213","authenticated-orcid":false,"given":"Kirk","family":"Roberts","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston , 7000 Fannin St #600, Houston, TX 77030,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"key":"2025030713434954600_R1","doi-asserted-by":"publisher","first-page":"e206","DOI":"10.1136\/amiajnl-2013-002428","article-title":"Electronic health records-driven phenotyping: challenges, recent advances, and perspectives","volume":"20","author":"Pathak","year":"2013","journal-title":"J Am Med Inf Assoc"},{"key":"2025030713434954600_R2","doi-asserted-by":"publisher","first-page":"e147","DOI":"10.1136\/amiajnl-2012-000896","article-title":"Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network","volume":"20","author":"Newton","year":"2013","journal-title":"J Am Med Inf Assoc"},{"key":"2025030713434954600_R3","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s12911-019-0786-z","article-title":"Developing a portable natural language processing based phenotyping system","volume":"19","author":"Sharma","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025030713434954600_R4","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TCBB.2018.2849968","article-title":"Natural language processing for EHR-based computational phenotyping","volume":"16","author":"Zeng","year":"2018","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025030713434954600_R5","doi-asserted-by":"publisher","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":"2025030713434954600_R6","doi-asserted-by":"publisher","first-page":"D1207","DOI":"10.1093\/nar\/gkaa1043","article-title":"The human phenotype ontology in 2021","volume":"49","author":"K\u00f6hler","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2025030713434954600_R7","article-title":"A normalized lexical lookup approach to identifying UMLS concepts in free text","volume":"129","author":"Bashyam","year":"2007","journal-title":"Stud Health Technol Inform"},{"key":"2025030713434954600_R8","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.3172","article-title":"Next generation phenotyping using the unified medical language system","volume":"2","author":"Adamusiak","year":"2014","journal-title":"JMIR Med Inform"},{"key":"2025030713434954600_R9","first-page":"41","article-title":"Coverage of phenotypes in standard terminologies","volume-title":"Joint Bio-Ontologies and BioLINK ISMB","author":"Winnenburg","year":"2014"},{"key":"2025030713434954600_R10","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1093\/jamia\/ocx132","article-title":"CLAMP\u2013a toolkit for efficiently building customized clinical natural language processing pipelines","volume":"25","author":"Soysal","year":"2018","journal-title":"J Am Med Inf Assoc"},{"key":"2025030713434954600_R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103132","article-title":"MCN: a comprehensive corpus for medical concept normalization","volume":"92","author":"Luo","year":"2019","journal-title":"J Biomed Informat"},{"key":"2025030713434954600_R12","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1055\/s-0040-1718940","article-title":"Leveraging the UMLS as a data standard for rare disease data normalization and harmonization","volume":"59","author":"Zhu","year":"2020","journal-title":"Methods Inf Med"},{"key":"2025030713434954600_R13","first-page":"1","article-title":"A clinical trials corpus annotated with UMLS entities to enhance the access to evidence-based medicine","volume":"21","author":"Campillos-Llanos","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025030713434954600_R14","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1093\/jamia\/ocad161","article-title":"The suitability of UMLS and SNOMED-CT for encoding outcome concepts","volume":"30","author":"Newbury","year":"2023","journal-title":"J Am Med Inf Assoc"},{"key":"2025030713434954600_R15","article-title":"Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program","author":"Aronson","year":"2001"},{"key":"2025030713434954600_R16","doi-asserted-by":"publisher","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":"2025030713434954600_R17","doi-asserted-by":"publisher","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":"2025030713434954600_R18","doi-asserted-by":"publisher","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":"2025030713434954600_R19","doi-asserted-by":"publisher","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":"2025030713434954600_R20","doi-asserted-by":"publisher","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":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025030713434954600_R21","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"2025030713434954600_R22","article-title":"Llama 2: open foundation and fine-tuned chat models","volume-title":"arXiv preprint","author":"Touvron","year":"2023"},{"key":"2025030713434954600_R23","article-title":"The falcon series of language models: towards open frontier models","volume-title":"Hugging Face Repository","author":"Almazrouei","year":"2023"},{"key":"2025030713434954600_R24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLoS Digital Health"},{"key":"2025030713434954600_R25","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint","author":"Achiam","year":"2023"},{"key":"2025030713434954600_R26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011319","article-title":"Ten quick tips for harnessing the power of ChatGPT in computational biology","volume":"19","author":"Lubiana","year":"2023","journal-title":"PLoS Comput Biol"},{"key":"2025030713434954600_R27","article-title":"Gpt-ner: named entity recognition via large language models","volume-title":"arXiv preprint","author":"Wang","year":"2023"},{"key":"2025030713434954600_R28","first-page":"688","article-title":"spaCy 2: natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017"},{"key":"2025030713434954600_R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2023.104770","article-title":"Benchmarking large language models\u2019 performances for myopia care: a comparative analysis of ChatGPT-3.5, ChatGPT-4.0, and Google Bard","volume":"95","author":"Lim","year":"2023","journal-title":"EBioMedicine"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baae103\/60093736\/baae103.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baae103\/60093736\/baae103.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T13:44:06Z","timestamp":1741355046000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/baae103\/7833209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1093\/database\/baae103","relation":{},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]},"article-number":"baae103"}}