{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T12:56:32Z","timestamp":1791982592403,"version":"4.4.0"},"reference-count":23,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Access Publication Fund of the University of Duisburg-Essen"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To address the challenges of data heterogeneity and manual feature engineering in clinical predictive modeling, we introduce FHIR-Former, an open-source framework integrating Fast Healthcare Interoperability Resources (FHIR) with large language models (LLMs) to automate and standardize clinical prediction tasks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>FHIR-Former dynamically processes structured (eg, lab results, medications) and unstructured (eg, clinical notes) data from FHIR resources. The pipeline supports multiple classification tasks, including 30-day readmission, imaging study prediction, and ICD code classification. Leveraging open-source LLMs (GeBERTa), we trained models on 1.1 million data points across ten FHIR resources using retrospective inpatient data (2018-2024). Hyperparameters were optimized via Bayesian methods, and outputs were mapped to FHIR RiskAssessment resources for interoperability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>FHIR-Former achieved an F1-score of 70.7% and accuracy of 72.9% for 30-day readmission, 51.8% F1-score (88.1% accuracy) for mortality prediction, and 61% macro F1-score for imaging study classification. The ICD code prediction model attained 94% accuracy. Performance demonstrated promising performance for readmission and showed scalability across tasks without manual feature engineering.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>FHIR-Former eliminates institution-specific preprocessing by adapting to diverse FHIR implementations, enabling seamless integration of multimodal data. Its configurable architecture outperformed prior frameworks reliant on static inputs or limited to unstructured text. Real-time risk scores embedded in FHIR servers enhance clinical workflows without disrupting existing practices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By harmonizing FHIR standardization with LLM flexibility, FHIR-Former advances scalable, interoperable predictive modeling in healthcare. The open-source framework facilitates automation, improves resource allocation, and supports personalized decision-making, bridging gaps between AI innovation and clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf165","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T11:47:24Z","timestamp":1758023244000},"page":"1793-1801","source":"Crossref","is-referenced-by-count":15,"title":["FHIR-Former: enhancing clinical predictions through Fast Healthcare Interoperability Resources and large language models"],"prefix":"10.1093","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8463-8786","authenticated-orcid":false,"given":"Merlin","family":"Engelke","sequence":"first","affiliation":[{"name":"Institute for Artificial Intelligence in Medicine, University Medicine Essen , Essen, 45131,","place":["Germany"]},{"name":"Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen , Essen, 45147,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5929-0271","authenticated-orcid":false,"given":"Giulia","family":"Baldini","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence in Medicine, University Medicine Essen , Essen, 45131,","place":["Germany"]},{"name":"Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen , Essen, 45147,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8686-0682","authenticated-orcid":false,"given":"Jens","family":"Kleesiek","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence in Medicine, University Medicine Essen , Essen, 45131,","place":["Germany"]},{"name":"Faculty of Computer Science and Medical Faculty, University of Duisburg-Essen , Essen, 45127,","place":["Germany"]},{"name":"Department of Physics, TU Dortmund University , Dortmund, 44227,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5811-7100","authenticated-orcid":false,"given":"Felix","family":"Nensa","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence in Medicine, University Medicine Essen , Essen, 45131,","place":["Germany"]},{"name":"Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen , Essen, 45147,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4016-7799","authenticated-orcid":false,"given":"Amin","family":"Dada","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence in Medicine, University Medicine Essen , Essen, 45131,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"2025112514470425100_ocaf165-B1","doi-asserted-by":"crossref","first-page":"21038","DOI":"10.1038\/s41598-020-78212-6","article-title":"Prediction of disease progression and outcomes in multiple sclerosis with machine learning","volume":"10","author":"Pinto","year":"2020","journal-title":"Sci Rep"},{"key":"2025112514470425100_ocaf165-B2","author":"Machine learning for comprehensive forecasting of Alzheimer\u2019s Disease progression | Scientific Reports"},{"key":"2025112514470425100_ocaf165-B3","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"},{"key":"2025112514470425100_ocaf165-B4","doi-asserted-by":"crossref","first-page":"2362","DOI":"10.1038\/s41598-019-39071-y","article-title":"Predictive modeling of the hospital readmission risk from patients\u2019 claims data using machine learning: a case study on COPD","volume":"9","author":"Min","year":"2019","journal-title":"Sci Rep"},{"key":"2025112514470425100_ocaf165-B5","doi-asserted-by":"crossref","first-page":"13505","DOI":"10.1038\/s41598-021-92799-4","article-title":"Long-term cancer survival prediction using multimodal deep learning","volume":"11","author":"Vale-Silva","year":"2021","journal-title":"Sci Rep"},{"key":"2025112514470425100_ocaf165-B6","doi-asserted-by":"crossref","first-page":"6994","DOI":"10.1038\/s41598-019-43372-7","article-title":"Deep learning-based survival prediction of oral cancer patients","volume":"9","author":"Kim","year":"2019","journal-title":"Sci Rep"},{"key":"2025112514470425100_ocaf165-B7","doi-asserted-by":"crossref","first-page":"e3447","DOI":"10.2196\/medinform.3447","article-title":"Making big data useful for health care: a summary of the inaugural MIT critical data conference","volume":"2","author":"Badawi","year":"2014","journal-title":"JMIR Med Inform"},{"key":"2025112514470425100_ocaf165-B8","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/JPROC.2015.2501978","article-title":"Machine learning and decision support in critical care","volume":"104","author":"Johnson","year":"2016","journal-title":"Proc IEEE Inst Electr Electron Eng"},{"key":"2025112514470425100_ocaf165-B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/BHI50953.2021.9508558","author":"Zhang","year":"2021"},{"key":"2025112514470425100_ocaf165-B10","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit Med"},{"key":"2025112514470425100_ocaf165-B11","doi-asserted-by":"crossref","first-page":"103310","DOI":"10.1016\/j.jbi.2019.103310","article-title":"Developing a FHIR-based EHR phenotyping framework: a case study for identification of patients with obesity and multiple comorbidities from discharge summaries","volume":"99","author":"Hong","year":"2019","journal-title":"J Biomed Inform"},{"key":"2025112514470425100_ocaf165-B12","doi-asserted-by":"crossref","first-page":"e0201016","DOI":"10.1371\/journal.pone.0201016","article-title":"Predicting hospital admission at emergency department triage using machine learning","volume":"13","author":"Hong","year":"2018","journal-title":"PLoS One"},{"key":"2025112514470425100_ocaf165-B13","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13326-017-0148-7","article-title":"Towards achieving semantic interoperability of clinical study data with FHIR","volume":"8","author":"Leroux","year":"2017","journal-title":"J Biomed Semantics"},{"key":"2025112514470425100_ocaf165-B14","doi-asserted-by":"crossref","first-page":"e35724","DOI":"10.2196\/35724","article-title":"Fast healthcare interoperability resources (FHIR) for interoperability in health research: systematic review","volume":"10","author":"Vorisek","year":"2022","journal-title":"JMIR Med Inform"},{"key":"2025112514470425100_ocaf165-B15","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1038\/s41746-022-00580-2","article-title":"Developing a shared sepsis data infrastructure: a systematic review and concept map to FHIR","volume":"5","author":"Brant","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2025112514470425100_ocaf165-B16","doi-asserted-by":"crossref","first-page":"e45209","DOI":"10.2196\/45209","article-title":"Electronic health record and semantic issues using fast healthcare interoperability resources: systematic mapping review","volume":"26","author":"Amar","year":"2024","journal-title":"J Med Internet Res"},{"key":"2025112514470425100_ocaf165-B17","doi-asserted-by":"publisher","first-page":"72","DOI":"10.18653\/v1\/W19-1909","volume-title":"Proceedings of the 2nd Clinical Natural Language Processing Workshop","author":"Alsentzer","year":"2019"},{"key":"2025112514470425100_ocaf165-B18","doi-asserted-by":"publisher","author":"Alnegheimish","year":"2020","DOI":"10.1109\/DSAA49011.2020.00068"},{"key":"2025112514470425100_ocaf165-B19","doi-asserted-by":"publisher","author":"Chakraborty","year":"2019","DOI":"10.1145\/3292500.3330718"},{"key":"2025112514470425100_ocaf165-B20","first-page":"13801","author":"Dada","year":"2023"},{"key":"2025112514470425100_ocaf165-B21","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1001\/jama.2011.1515","article-title":"Risk prediction models for hospital readmission: a systematic review","volume":"306","author":"Kansagara","year":"2011","journal-title":"JAMA"},{"key":"2025112514470425100_ocaf165-B22","doi-asserted-by":"crossref","first-page":"7180","DOI":"10.1038\/s41598-022-11226-4","article-title":"Mortality prediction of patients in intensive care units using machine learning algorithms based on electronic health records","volume":"12","author":"Choi","year":"2022","journal-title":"Sci Rep"},{"key":"2025112514470425100_ocaf165-B23","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/12\/1793\/64660809\/ocaf165.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/12\/1793\/64660809\/ocaf165.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T19:47:11Z","timestamp":1764100031000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/12\/1793\/8285046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":23,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,10,13]]},"published-print":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf165","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,12]]},"published":{"date-parts":[[2025,10,13]]}}}