{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T16:09:24Z","timestamp":1782144564114,"version":"3.54.5"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2239824"],"award-info":[{"award-number":["2239824"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of General Medical Sciences of the National Institutes of Health","award":["K23GM37182"],"award-info":[{"award-number":["K23GM37182"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM139967"],"award-info":[{"award-number":["R01GM139967"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21GM148931"],"award-info":[{"award-number":["R21GM148931"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop an electronic medical record (EMR) data processing tool that confers clinical context to machine learning (ML) algorithms for error handling, bias mitigation, and interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We present Trust-MAPS, an algorithm that translates clinical domain knowledge into high-dimensional, mixed-integer programming models that capture physiological and biological constraints on clinical measurements. EMR data are projected onto this constrained space, effectively bringing outliers to fall within a physiologically feasible range. We then compute the distance of each data point from the constrained space modeling healthy physiology to quantify deviation from the norm. These distances, termed \u201ctrust-scores,\u201d are integrated into the feature space for downstream ML applications. We demonstrate the utility of Trust-MAPS by training a binary classifier for early sepsis prediction on data from the 2019 PhysioNet Computing in Cardiology Challenge, using the XGBoost algorithm and applying SMOTE for overcoming class-imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The Trust-MAPS framework shows desirable behavior in handling potential errors and boosting predictive performance. We achieve an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.89-0.92) for predicting sepsis 6 hours before onset\u2014a marked 15% improvement over a baseline model trained without Trust-MAPS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussions<\/jats:title>\n                    <jats:p>Downstream classification performance improves after Trust-MAPS preprocessing, highlighting the bias reducing capabilities of the error-handling projections. Trust-scores emerge as clinically meaningful features that not only boost predictive performance for clinical decision support tasks but also lend interpretability to ML models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR and confers interpretability and superior predictive power to models trained for clinical decision support.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf058","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T07:24:21Z","timestamp":1744183461000},"page":"123-132","source":"Crossref","is-referenced-by-count":5,"title":["Improving clinical decision support through interpretable machine learning and error handling in electronic health records"],"prefix":"10.1093","volume":"33","author":[{"given":"Mehak","family":"Arora","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University , Durham, NC, 27708,","place":["United States"]},{"name":"Department of Surgery, Duke University School of Medicine , Durham, NC, 27708,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Mortagy","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Georgia Institute of Technology , Atlanta, GA, 30332,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Dwarshuis","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Georgia Institute of Technology , Atlanta, GA, 30332,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey","family":"Wang","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Emory University School of Medicine , Atlanta, GA, 30322,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5142-1137","authenticated-orcid":false,"given":"Philip","family":"Yang","sequence":"additional","affiliation":[{"name":"Division of Pulmonary, Allergy, Critical Care and Sleep Medicine, Emory University School of Medicine , Atlanta, GA, 30322,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andre L","family":"Holder","sequence":"additional","affiliation":[{"name":"Division of Pulmonary, Allergy, Critical Care and Sleep Medicine, Emory University School of Medicine , Atlanta, GA, 30322,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Swati","family":"Gupta","sequence":"additional","affiliation":[{"name":"Sloan School of Management, Massachusetts Institute of Technology , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rishikesan","family":"Kamaleswaran","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University , Durham, NC, 27708,","place":["United States"]},{"name":"Department of Surgery, Duke University School of Medicine , Durham, NC, 27708,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"2026010211513372200_ocaf058-B1","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/j.medj.2021.04.006","article-title":"Machine learning in clinical decision making","volume":"2","author":"Adlung","year":"2021","journal-title":"Med"},{"key":"2026010211513372200_ocaf058-B2","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.jcrc.2018.07.021","article-title":"Secondary EMR data for quality improvement and research: a comparison of manual and electronic data collection from an integrated critical care electronic medical record system","volume":"47","author":"Brundin-Mather","year":"2018","journal-title":"J Crit Care"},{"key":"2026010211513372200_ocaf058-B3","first-page":"587","author":"Phillips","year":"2009"},{"key":"2026010211513372200_ocaf058-B4","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/s40747-021-00349-2","article-title":"Diabetes classification application with efficient missing and outliers data handling algorithms","volume":"8","author":"Torkey","year":"2022","journal-title":"Complex Intell Syst"},{"key":"2026010211513372200_ocaf058-B5","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.3390\/pr10061199","article-title":"A healthcare quality assessment model based on outlier detection algorithm","volume":"10","author":"Alharbe","year":"2022","journal-title":"Processes"},{"key":"2026010211513372200_ocaf058-B6","first-page":"131","author":"Sharma","year":"2023"},{"key":"2026010211513372200_ocaf058-B7","author":"Raghunathan","year":"2001"},{"key":"2026010211513372200_ocaf058-B8","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1097\/CCM.0000000000004145","article-title":"Early prediction of sepsis from clinical data","volume":"48","author":"Reyna","year":"2020","journal-title":"Crit Care Med."},{"key":"2026010211513372200_ocaf058-B9","doi-asserted-by":"crossref","first-page":"e1091","DOI":"10.1097\/CCM.0000000000004550","article-title":"An explainable artificial intelligence predictor for early detection of sepsis","volume":"48","author":"Yang","year":"2020","journal-title":"Crit Care Med"},{"key":"2026010211513372200_ocaf058-B10","first-page":"1","author":"Morrill","year":"2019"},{"key":"2026010211513372200_ocaf058-B11","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1038\/s41598-023-30091-3","article-title":"Exploring a global interpretation mechanism for deep learning networks when predicting sepsis","volume":"13","author":"Strickler","year":"2023","journal-title":"Sci Rep"},{"key":"2026010211513372200_ocaf058-B12","doi-asserted-by":"crossref","first-page":"e0251248","DOI":"10.1371\/journal.pone.0251248","article-title":"MGP-AttTCN: an interpretable machine learning model for the prediction of sepsis","volume":"16","author":"Rosnati","year":"2021","journal-title":"PloS One"},{"key":"2026010211513372200_ocaf058-B13","doi-asserted-by":"crossref","first-page":"e0000569","DOI":"10.1371\/journal.pdig.0000569","article-title":"Improving sepsis prediction in intensive care with SepsisAI: a clinical decision support system with a focus on minimizing false alarms","volume":"3","author":"Gupta","year":"2024","journal-title":"PLOS Digit Health"},{"key":"2026010211513372200_ocaf058-B14","first-page":"1","article-title":"Early prediction of sepsis using double fusion of deep features and handcrafted features","volume":"53","author":"Duan","year":"2023","journal-title":"Appl Intell (Dordr)"},{"key":"2026010211513372200_ocaf058-B15","author":"Clifford","year":"2020"},{"key":"2026010211513372200_ocaf058-B16","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s13755-023-00210-5","article-title":"Knowledge and data-driven prediction of organ failure in critical care patients","volume":"11","author":"Ma","year":"2023","journal-title":"Health Inform Sci Syst"},{"key":"2026010211513372200_ocaf058-B17","doi-asserted-by":"crossref","first-page":"106638","DOI":"10.1016\/j.cmpb.2022.106638","article-title":"Knowledge-driven feature engineering to detect multiple symptoms using ambulatory blood pressure monitoring data","volume":"217","author":"Janjua","year":"2022","journal-title":"Comput Meth Program Biomed"},{"key":"2026010211513372200_ocaf058-B18","first-page":"6158","author":"Yin","year":"2024"},{"key":"2026010211513372200_ocaf058-B19","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","article-title":"An interpretable machine learning model for accurate prediction of sepsis in the ICU","volume":"46","author":"Nemati","year":"2018","journal-title":"Crit Care Med"},{"key":"2026010211513372200_ocaf058-B20","doi-asserted-by":"crossref","first-page":"5088","DOI":"10.3390\/app11115088","article-title":"Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review","volume":"11","author":"Antoniadi","year":"2021","journal-title":"Appl Sci"},{"key":"2026010211513372200_ocaf058-B21","doi-asserted-by":"crossref","first-page":"9919269","DOI":"10.1155\/2023\/9919269","article-title":"Interpretability of clinical decision support systems based on artificial intelligence from technological and medical perspective: a systematic review","volume":"2023","author":"Xu","year":"2023","journal-title":"J Healthcare Eng"},{"key":"2026010211513372200_ocaf058-B22","doi-asserted-by":"publisher","first-page":"14790","DOI":"10.1073\/pnas.0807471105","author":"Donoho","year":"2008"},{"key":"2026010211513372200_ocaf058-B23","doi-asserted-by":"crossref","first-page":"e0223161","DOI":"10.1371\/journal.pone.0223161","article-title":"The univariate flagging algorithm (UFA): an interpretable approach for predictive modeling","volume":"14","author":"Sheth","year":"2019","journal-title":"PloS One"},{"key":"2026010211513372200_ocaf058-B24","doi-asserted-by":"publisher","first-page":"1675","DOI":"10.1145\/2939672.2939874","author":"Lakkaraju","year":"2016"},{"key":"2026010211513372200_ocaf058-B25","doi-asserted-by":"crossref","first-page":"617486","DOI":"10.3389\/fmed.2021.617486","article-title":"Early detection of sepsis with machine learning techniques: a brief clinical perspective","volume":"8","author":"Struelens","year":"2021","journal-title":"Front Med"},{"key":"2026010211513372200_ocaf058-B26","first-page":"272","author":"Duchi","year":"2008"},{"key":"2026010211513372200_ocaf058-B27","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1378\/chest.101.6.1644","article-title":"Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis","volume":"101","author":"Bone","year":"1992","journal-title":"Chest"},{"key":"2026010211513372200_ocaf058-B28","first-page":"707","author":"Vincent","year":"1996"},{"key":"2026010211513372200_ocaf058-B29","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1001\/jama.2016.0288","article-title":"Assessment of clinical criteria for sepsis: for the third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Seymour","year":"2016","journal-title":"JAMA"},{"key":"2026010211513372200_ocaf058-B30","article-title":"The utility of clustering in prediction tasks","author":"Trivedi","year":"2015","journal-title":"arXiv, preprint"},{"key":"2026010211513372200_ocaf058-B31","first-page":"785","author":"Chen","year":"2016"},{"key":"2026010211513372200_ocaf058-B32","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1111\/j.1365-2656.2008.01390.x","article-title":"A working guide to boosted regression trees","volume":"77","author":"Elith","year":"2008","journal-title":"J Anim Ecol"},{"key":"2026010211513372200_ocaf058-B33","doi-asserted-by":"crossref","first-page":"5658","DOI":"10.3390\/jcm12175658","article-title":"Machine learning-based early prediction of sepsis using electronic health records: a systematic review","volume":"12","author":"Islam","year":"2023","journal-title":"J Clin Med"},{"key":"2026010211513372200_ocaf058-B34","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/s41467-021-20910-4","article-title":"Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare","volume":"12","author":"Goh","year":"2021","journal-title":"Nature Commun"},{"key":"2026010211513372200_ocaf058-B35","doi-asserted-by":"crossref","first-page":"1305756","DOI":"10.3389\/fmed.2023.1305756","article-title":"Defining medical liability when artificial intelligence is applied on diagnostic algorithms: a systematic review","volume":"10","author":"Cestonaro","year":"2023","journal-title":"Front Med"},{"key":"2026010211513372200_ocaf058-B36","doi-asserted-by":"crossref","first-page":"6522633","DOI":"10.1155\/2021\/6522633","article-title":"Early prediction of sepsis based on machine learning algorithm","volume":"2021","author":"Zhao","year":"2021","journal-title":"Comput Intell Neurosci."},{"key":"2026010211513372200_ocaf058-B37","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1186\/s12938-018-0569-2","article-title":"Machine learning in critical care: state-of-the-art and a sepsis case study","volume":"17","author":"Vellido","year":"2018","journal-title":"Biomed Eng Online"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/1\/123\/62987217\/ocaf058.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/1\/123\/62987217\/ocaf058.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T16:51:46Z","timestamp":1767372706000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/1\/123\/8117850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,4,22]]},"published-print":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf058","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,4,22]]}}}