{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:16:30Z","timestamp":1776096990686,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T00:00:00Z","timestamp":1709683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1OT2OD002751"],"award-info":[{"award-number":["1OT2OD002751"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study evaluates an AI assistant developed using OpenAI\u2019s GPT-4 for interpreting pharmacogenomic (PGx) testing results, aiming to improve decision-making and knowledge sharing in clinical genetics and to enhance patient care with equitable access.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>The AI assistant employs retrieval-augmented generation (RAG), which combines retrieval and generative techniques, by harnessing a knowledge base (KB) that comprises data from the Clinical Pharmacogenetics Implementation Consortium (CPIC). It uses context-aware GPT-4 to generate tailored responses to user queries from this KB, further refined through prompt engineering and guardrails.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Evaluated against a specialized PGx question catalog, the AI assistant showed high efficacy in addressing user queries. Compared with OpenAI\u2019s ChatGPT 3.5, it demonstrated better performance, especially in provider-specific queries requiring specialized data and citations. Key areas for improvement include enhancing accuracy, relevancy, and representative language in responses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The integration of context-aware GPT-4 with RAG significantly enhanced the AI assistant\u2019s utility. RAG\u2019s ability to incorporate domain-specific CPIC data, including recent literature, proved beneficial. Challenges persist, such as the need for specialized genetic\/PGx models to improve accuracy and relevancy and addressing ethical, regulatory, and safety concerns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study underscores generative AI\u2019s potential for transforming healthcare provider support and patient accessibility to complex pharmacogenomic information. While careful implementation of large language models like GPT-4 is necessary, it is clear that they can substantially improve understanding of pharmacogenomic data. With further development, these tools could augment healthcare expertise, provider productivity, and the delivery of equitable, patient-centered healthcare services.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocae039","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:48:06Z","timestamp":1708390086000},"page":"1356-1366","source":"Crossref","is-referenced-by-count":49,"title":["Empowering personalized pharmacogenomics with generative AI solutions"],"prefix":"10.1093","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-2613","authenticated-orcid":false,"given":"Mullai","family":"Murugan","sequence":"first","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine , Houston, TX, United States"}]},{"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine , Houston, TX, United States"},{"name":"Department of Molecular and Human Genetics, Baylor College of Medicine , Houston, TX, United States"}]},{"given":"Eric","family":"Venner","sequence":"additional","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine , Houston, TX, United States"},{"name":"Department of Molecular and Human Genetics, Baylor College of Medicine , Houston, TX, United States"}]},{"given":"Christie M","family":"Ballantyne","sequence":"additional","affiliation":[{"name":"Sections of Cardiology and Cardiovascular Research, Department of Medicine, Baylor College of Medicine , Houston, TX, United States"}]},{"given":"Katherine M","family":"Robinson","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of Pittsburgh , Pittsburgh, PA, United States"}]},{"given":"James C","family":"Coons","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of Pittsburgh , Pittsburgh, PA, United States"},{"name":"Department of Pharmacy, UPMC Presbyterian-Shadyside Hospital , Pittsburgh, PA, United States"}]},{"given":"Liwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine , Houston, TX, United States"}]},{"given":"Philip E","family":"Empey","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of Pittsburgh , Pittsburgh, PA, United States"},{"name":"Institute for Precision Medicine, UPMC\/University of Pittsburgh , Pittsburgh, PA, United States"}]},{"given":"Richard A","family":"Gibbs","sequence":"additional","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine , Houston, TX, United States"},{"name":"Department of Molecular and Human Genetics, Baylor College of Medicine , Houston, TX, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,3,6]]},"reference":[{"issue":"4","key":"2024052019470568400_ocae039-B1","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1038\/gim.2012.157","article-title":"Implementing genomic medicine in the clinic: the future is here","volume":"15","author":"Manolio","year":"2013","journal-title":"Genet Med"},{"issue":"12","key":"2024052019470568400_ocae039-B2","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1016\/j.ajhg.2022.11.003","article-title":"Genomic medicine year in review: 2022","volume":"109","author":"Manolio","year":"2022","journal-title":"Am J Hum Genet"},{"issue":"5","key":"2024052019470568400_ocae039-B3","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1111\/cge.13917","article-title":"Pitfalls and challenges in genetic test interpretation: an exploration of genetic professionals experience with interpretation of results","volume":"99","author":"Donohue","year":"2021","journal-title":"Clin Genet"},{"issue":"12","key":"2024052019470568400_ocae039-B4","doi-asserted-by":"crossref","first-page":"2289","DOI":"10.1038\/s41436-021-01267-x","article-title":"Challenges in genetic testing: clinician variant interpretation processes and the impact on clinical care","volume":"23","author":"Berrios","year":"2021","journal-title":"Genet Med"},{"issue":"6","key":"2024052019470568400_ocae039-B5","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1097\/PPO.0000000000000553","article-title":"Challenges and errors in genetic testing: the fifth case series","volume":"27","author":"Farmer","year":"2021","journal-title":"Cancer J"},{"key":"2024052019470568400_ocae039-B6","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1146\/annurev-genom-110320-121752","article-title":"Scaling genetic counseling in the genomics era","volume":"22","author":"Amendola","year":"2021","journal-title":"Annu Rev Genomics Hum Genet"},{"issue":"1","key":"2024052019470568400_ocae039-B7","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1002\/cpt.2161","article-title":"Opportunity for genotype-guided prescribing among adult patients in 11 US health systems","volume":"110","author":"Hicks","year":"2021","journal-title":"Clin Pharmacol Ther"},{"issue":"1","key":"2024052019470568400_ocae039-B8","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1186\/s12967-022-03745-5","article-title":"Evaluating the frequency and the impact of pharmacogenetic alleles in an ancestrally diverse Biobank population","volume":"20","author":"Verma","year":"2022","journal-title":"J Transl Med"},{"key":"2024052019470568400_ocae039-B9"},{"key":"2024052019470568400_ocae039-B10","author":"Zhao"},{"key":"2024052019470568400_ocae039-B11","author":"Aslam","year":"2023"},{"issue":"15","key":"2024052019470568400_ocae039-B12","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1002\/cncr.34827","article-title":"ChatGPT-A promising generative AI tool and its implications for cancer care","volume":"129","author":"Uprety","year":"2023","journal-title":"Cancer"},{"issue":"1","key":"2024052019470568400_ocae039-B13","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1001\/jama.2023.25054","article-title":"Will generative artificial intelligence deliver on its promise in health care?","volume":"331","author":"Wachter","year":"2024","journal-title":"JAMA"},{"issue":"1","key":"2024052019470568400_ocae039-B14","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"7969","key":"2024052019470568400_ocae039-B15","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-023-06160-y","article-title":"Health system-scale language models are all-purpose prediction engines","volume":"619","author":"Jiang","year":"2023","journal-title":"Nature"},{"issue":"2","key":"2024052019470568400_ocae039-B16","doi-asserted-by":"crossref","first-page":"e32875","DOI":"10.2196\/32875","article-title":"Operationalizing and implementing pretrained, large artificial intelligence linguistic models in the US health care system: outlook of generative pretrained transformer 3 (GPT-3) as a service model","volume":"10","author":"Sezgin","year":"2022","journal-title":"JMIR Med Inform"},{"issue":"13","key":"2024052019470568400_ocae039-B17","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N Engl J Med"},{"key":"2024052019470568400_ocae039-B18","author":"Lee"},{"issue":"2","key":"2024052019470568400_ocae039-B19","first-page":"605","article-title":"ChatGPT\u2014Reshaping medical education and clinical management","volume":"39","author":"Khan","year":"2023","journal-title":"Pak J Med Sci Q"},{"key":"2024052019470568400_ocae039-B20","doi-asserted-by":"crossref","first-page":"104512","DOI":"10.1016\/j.ebiom.2023.104512","article-title":"Attention is not all you need: the complicated case of ethically using large language models in healthcare and medicine","volume":"90","author":"Harrer","year":"2023","journal-title":"EBioMedicine"},{"key":"2024052019470568400_ocae039-B21","author":"Gao"},{"key":"2024052019470568400_ocae039-B22","year":"2023"},{"issue":"2","key":"2024052019470568400_ocae039-B23","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.therap.2016.09.017","article-title":"Pharmacogenetics in cardiovascular diseases: state of the art and implementation-recommendations of the French National Network of Pharmacogenetics (RNPGx)","volume":"72","author":"Lamoureux","year":"2017","journal-title":"Therapie"},{"key":"2024052019470568400_ocae039-B24","author":"PGx Statins KB","year":"2023"},{"key":"2024052019470568400_ocae039-B25","author":"Carbonell","year":"1999"},{"key":"2024052019470568400_ocae039-B26","author":"GitHub"},{"key":"2024052019470568400_ocae039-B27","author":"Neelakantan"},{"key":"2024052019470568400_ocae039-B28","author":"GitHub OpenAI Ada Embedding ground truth evaluation"},{"key":"2024052019470568400_ocae039-B29","author":"OpenAI platform","year":"2023"},{"issue":"3","key":"2024052019470568400_ocae039-B30","doi-asserted-by":"crossref","first-page":"279","DOI":"10.4300\/JGME-D-12-00156.1","article-title":"Using effect size-or why the P value is not enough","volume":"4","author":"Sullivan","year":"2012","journal-title":"J Grad Med Educ"},{"key":"2024052019470568400_ocae039-B31","author":"PGx AI and ChatGPT 3.5 Survey Results Analysis and Visualization","year":"2024"},{"key":"2024052019470568400_ocae039-B32","author":"PGx AI assistant reading level results"},{"key":"2024052019470568400_ocae039-B33","author":"AMA Health Literacy"},{"key":"2024052019470568400_ocae039-B34","author":"Jin"},{"issue":"18","key":"2024052019470568400_ocae039-B35","doi-asserted-by":"crossref","first-page":"4369","DOI":"10.1093\/bioinformatics\/btac508","article-title":"BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task","volume":"38","author":"Mahbub","year":"2022","journal-title":"Bioinformatics"},{"key":"2024052019470568400_ocae039-B36","doi-asserted-by":"crossref","first-page":"104392","DOI":"10.1016\/j.jbi.2023.104392","article-title":"KEBLM: Knowledge-Enhanced Biomedical Language Models","volume":"143","author":"Lai","year":"2023","journal-title":"J Biomed Inform"},{"issue":"4","key":"2024052019470568400_ocae039-B37","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1109\/TCBB.2021.3079339","article-title":"Named entity aware transfer learning for biomedical factoid question answering","volume":"19","author":"Peng","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"2024052019470568400_ocae039-B38","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1111\/cts.12884","article-title":"Precision medicine, AI, and the future of personalized health care","volume":"14","author":"Johnson","year":"2021","journal-title":"Clin Transl Sci"},{"key":"2024052019470568400_ocae039-B39","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.semcancer.2023.02.005","article-title":"Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy","volume":"90","author":"Zhang","year":"2023","journal-title":"Semin Cancer Biol"},{"issue":"12","key":"2024052019470568400_ocae039-B40","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1038\/s41416-023-02215-z","article-title":"Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer","volume":"128","author":"Guo","year":"2023","journal-title":"Br J Cancer"},{"issue":"1","key":"2024052019470568400_ocae039-B41","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1186\/s12910-021-00687-3","article-title":"Privacy and artificial intelligence: challenges for protecting health information in a new era","volume":"22","author":"Murdoch","year":"2021","journal-title":"BMC Med Ethics"},{"issue":"16","key":"2024052019470568400_ocae039-B42","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1001\/jama.2023.5321","article-title":"AI-generated medical advice-GPT and beyond","volume":"329","author":"Haupt","year":"2023","journal-title":"JAMA"},{"issue":"6","key":"2024052019470568400_ocae039-B43","doi-asserted-by":"crossref","first-page":"364","DOI":"10.2471\/BLT.23.290215","article-title":"Artificial intelligence for global health: cautious optimism with safeguards","volume":"101","author":"Pujari","year":"2023","journal-title":"Bull World Health Organ"},{"key":"2024052019470568400_ocae039-B44","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/B978-0-12-818438-7.00012-5","volume-title":"Artificial Intelligence in Healthcare","author":"Gerke","year":"2020"},{"key":"2024052019470568400_ocae039-B45","author":"Redrup Hill"},{"issue":"3","key":"2024052019470568400_ocae039-B46","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1136\/bmjqs-2018-008370","article-title":"Artificial intelligence, bias and clinical safety","volume":"28","author":"Challen","year":"2019","journal-title":"BMJ Qual Saf"},{"issue":"3","key":"2024052019470568400_ocae039-B47","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1002\/alr.23129","article-title":"Avoiding bias in artificial intelligence","volume":"13","author":"Gudis","year":"2023","journal-title":"Int Forum Allergy Rhinol"},{"issue":"1","key":"2024052019470568400_ocae039-B48","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1080\/15265161.2022.2135875","article-title":"An AI bill of rights: implications for health care AI and machine learning-A bioethics lens","volume":"23","author":"Blumenthal-Barby","year":"2023","journal-title":"Am J Bioeth"},{"issue":"4","key":"2024052019470568400_ocae039-B49","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1177\/1062860619878515","article-title":"Application of artificial intelligence in the health care safety context: opportunities and challenges","volume":"35","author":"Ellahham","year":"2020","journal-title":"Am J Med Qual"},{"key":"2024052019470568400_ocae039-B50","author":"Wornow"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1356\/57769063\/ocae039.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1356\/57769063\/ocae039.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T15:48:21Z","timestamp":1716220101000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/6\/1356\/7623454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,6]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3,6]]},"published-print":{"date-parts":[[2024,5,20]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae039","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.02.21.24302946","asserted-by":"object"}]},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6,1]]},"published":{"date-parts":[[2024,3,6]]}}}