{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:21:46Z","timestamp":1789100506694,"version":"build-2803163510"},"reference-count":41,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Laboratory testing is a cornerstone of diagnostic decision-making in emergency departments (EDs), yet its overuse contributes substantially to unnecessary health care costs and inefficiencies. Predictive approaches that leverage electronic health record data may help optimize and guide more appropriate test use.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and evaluate machine learning models that predict laboratory test use during ED visits by integrating structured clinical data and unstructured text from electronic health records.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We analyzed 13,115 adult ED visits from the 2021 National Hospital Ambulatory Medical Care Survey\u2013Emergency Department dataset. Structured predictors included demographics, vital signs, insurance status, and medical history, while unstructured data from chief complaints and injury descriptions were encoded using Bidirectional Encoder Representations from Transformers\u2013based embeddings. Four model configurations were developed: structured-only, unstructured-only, combined structured and unstructured data, and an ensemble (mean probability) approach. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The combined model achieved the highest predictive performance (AUC=0.83), outperforming both the structured-only model (AUC=0.78) and the unstructured-only model (AUC=0.74). The ensemble model also performed well but did not exceed the combined model. Key predictors of laboratory testing included older age, ambulance arrival, abnormal vital signs, and chronic comorbidities, whereas injury-related visits were associated with a lower likelihood of testing.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Integrating structured and unstructured electronic health record data improves the prediction of laboratory test use in ED settings. These findings support the development of data-driven clinical decision support tools aimed at enhancing diagnostic efficiency and reducing unnecessary testing.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/85255","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:20:06Z","timestamp":1779063606000},"page":"e85255-e85255","source":"Crossref","is-referenced-by-count":1,"title":["Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8108-1997","authenticated-orcid":false,"given":"Xingyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2278-1287","authenticated-orcid":false,"given":"Haipeng","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1422-7326","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3199-1113","authenticated-orcid":false,"given":"Anao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1016\/j.pcl.2018.07.003","article-title":"Diagnostic decision-making in the emergency department","volume":"65","author":"Medford-Davis","journal-title":"Pediatr Clin North Am"},{"issue":"2","key":"R2","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1080\/08998280.2023.2288788","article-title":"Lab testing overload: a comprehensive analysis of overutilization in hospital-based settings","volume":"37","author":"Shaik","journal-title":"Proc (Bayl Univ Med Cent)"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01384-8","article-title":"Laboratory test ordering in inpatient hospitals: a systematic review on the effects and features of clinical decision support systems","volume":"21","author":"Zare","journal-title":"BMC Med Inform Decis Mak"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1097\/01.poc.0000271401.14936.40","article-title":"Analysis of emergency department test ordering patterns in an urban academic medical center: can the point\u2011of\u2011care option in a satellite laboratory provide sufficient menu to permit full service testing","volume":"6","author":"Johnson","journal-title":"Point Care"},{"key":"R5","unstructured":"Institute of Medicine (US) Roundtable on Evidence-Based Medicine. Transparency of cost and performance. In: Yong PL Saunders RS Olsen L , editors. The Healthcare Imperative. National Academies Press; 2010:335-358. ISBN: 9780309186834"},{"issue":"11 Suppl","key":"R6","doi-asserted-by":"publisher","first-page":"S123","DOI":"10.7326\/M19-0876","article-title":"Using electronic health record portals to improve patient engagement: research priorities and best practices","volume":"172","author":"Lyles","journal-title":"Ann Intern Med"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baaa010","article-title":"Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine","volume":"2020","author":"Ahmed","journal-title":"Database (Oxford)"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108377","article-title":"Not all datasets are born equal: on heterogeneous tabular data and adversarial examples","volume":"242","author":"Mathov","journal-title":"Knowl Based Syst"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.945006","article-title":"Structured data vs. unstructured data in machine learning prediction models for suicidal behaviors: a systematic review and meta-analysis","volume":"4","author":"Hopkins","journal-title":"Front Digit Health"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooab006","article-title":"Use of machine learning to predict clinical decision support compliance, reduce alert burden, and evaluate duplicate laboratory test ordering alerts","volume":"4","author":"Baron","journal-title":"JAMIA Open"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinbiochem.2023.01.002","article-title":"Targeting repetitive laboratory testing with electronic health records-embedded predictive decision support: a pre-implementation study","volume":"113","author":"Rabbani","journal-title":"Clin Biochem"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/j.neuron.2024.01.016","article-title":"Data science opportunities of large language models for neuroscience and biomedicine","volume":"112","author":"Bzdok","journal-title":"Neuron"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2022.102817","article-title":"Knowledge Discovery: methods from data mining and machine learning","volume":"110","author":"Shu","journal-title":"Soc Sci Res"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"100754","DOI":"10.1016\/j.hjdsi.2024.100754","article-title":"The National Ambulatory Medical Care Survey (NAMCS) at fifty: past and future","volume":"12","author":"Goodson","journal-title":"Healthc (Amst)"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1016\/j.jdiacomp.2014.02.005","article-title":"Assessing the burden of diabetes mellitus in emergency departments in the United States: the National Hospital Ambulatory Medical Care Survey (NHAMCS)","volume":"28","author":"Asao","journal-title":"J Diabetes Complications"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Kaur J Sohal RS . Noise estimation and removal in natural language processing. In: Handbook of Vibroacoustics, Noise and Harshness. Springer; 2025:693-717. [doi: 10.1007\/978-981-97-8100-3_38]","DOI":"10.1007\/978-981-97-8100-3_38"},{"key":"R17","unstructured":"Bird S Klein E Loper E . Natural Language Processing with Python. O\u2019Reilly Media; 2009. ISBN: 9780596555719"},{"issue":"7","key":"R18","first-page":"1708","volume":"12","author":"Deepa","journal-title":"Turk J Comput Math Educ"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2021.06.005","article-title":"Improving the performance of aspect based sentiment analysis using fine-tuned Bert Base Uncased model","volume":"2","author":"Geetha","journal-title":"Int J Intell Netw"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Kumar A Ware N Gupta S . Leveraging transfer learning: fine-tuning methodology for enhanced text classification using BERT. Presented at: 2024 IEEE Pune Section International Conference (PuneCon); Dec 13-15, 2024; Pune, India. [doi: 10.1109\/PuneCon63413.2024.10895448]","DOI":"10.1109\/PuneCon63413.2024.10895448"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Devlin J Chang MW Lee K Toutanova K . BERT: pre-training of deep bidirectional transformers for language understanding. Presented at: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019); Jun 2-7, 2019; Minneapolis, Minnesota. [doi: 10.18653\/v1\/N19-1423]","DOI":"10.18653\/v1\/N19-1423"},{"issue":"2","key":"R22","doi-asserted-by":"publisher","first-page":"325","DOI":"10.19139\/soic-2310-5070-1846","article-title":"Proposed two-steps procedure of classification high dimensional data with regularized logistic regression","volume":"12","author":"Alshebly","journal-title":"Stat Optim Inf Comput"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","first-page":"25","DOI":"10.4097\/kja.21209","article-title":"Receiver operating characteristic curve: overview and practical use for clinicians","volume":"75","author":"Nahm","journal-title":"Korean J Anesthesiol"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Naidu G Zuva T Sibanda EM . A review of evaluation metrics in machine learning algorithms. In: Artificial Intelligence Application in Networks and Systems. Springer; 2023:15-25. [doi: 10.1007\/978-3-031-35314-7_2]","DOI":"10.1007\/978-3-031-35314-7_2"},{"key":"R25","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917); Dec 4-9, 2017:4766-4775; Long Beach, California, USA. URL: https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295230 [Accessed 29-05-2026]"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Sharma P Mirzan SR Bhandari A et al. Evaluating tree explanation methods for anomaly reasoning: a case study of SHAP treeexplainer and treeinterpreter. In: Advances in Conceptual Modeling. Springer; 2020:35-45. [doi: 10.1007\/978-3-030-65847-2_4]","DOI":"10.1007\/978-3-030-65847-2_4"},{"issue":"11","key":"R27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0165521","article-title":"Comparing machine learning classifiers and linear\/logistic regression to explore the relationship between hand dimensions and demographic characteristics","volume":"11","author":"Miguel-Hurtado","journal-title":"PLoS One"},{"issue":"11","key":"R28","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101260","article-title":"Combining clinical notes with structured electronic health records enhances the prediction of mental health crises","volume":"4","author":"Garriga","journal-title":"Cell Rep Med"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01297-6","article-title":"Combining structured and unstructured data for predictive models: a deep learning approach","volume":"20","author":"Zhang","journal-title":"BMC Med Inform Decis Mak"},{"issue":"15","key":"R30","doi-asserted-by":"publisher","first-page":"3783","DOI":"10.1007\/s11606-022-07453-0","article-title":"Characterizing the relationship between payer mix and diagnostic intensity at the hospital level","volume":"37","author":"Ellenbogen","journal-title":"J Gen Intern Med"},{"issue":"12","key":"R31","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1136\/emermed-2020-210628","article-title":"The association between vital signs and clinical outcomes in emergency department patients of different age categories","volume":"39","author":"Candel","journal-title":"Emerg Med J"},{"issue":"15","key":"R32","doi-asserted-by":"publisher","first-page":"8528","DOI":"10.3390\/app15158528","article-title":"A study of NEWS vital signs in the emergency department for predicting short- and medium-term mortality using decision tree analysis","volume":"15","author":"Sibilio","journal-title":"Appl Sci"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1093\/jalm\/jfad094","article-title":"Explainable machine learning models for rapid risk stratification in the emergency department: a multicenter study","volume":"9","author":"van Doorn","journal-title":"J Appl Lab Med"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","DOI":"10.1007\/s00068-025-02840-8","article-title":"Imaging strategies for patients with multiple and\/or severe injuries in the resuscitation room: a systematic review and clinical practice guideline update","volume":"51","author":"Huber-Wagner","journal-title":"Eur J Trauma Emerg Surg"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","first-page":"954","DOI":"10.14744\/tjtes.2021.14826","article-title":"The use of routine laboratory testing in acute trauma care: a retrospective analysis","volume":"28","author":"Popal","journal-title":"Ulus Travma Acil Cerrahi Derg"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Patlas MN Katz DS Odedra D . Emergency and trauma imaging. In: Atlas of Emergency Imaging from Head-to-Toe. Springer; 2025:1-7. [doi: 10.1007\/978-3-030-44092-3_1-3]","DOI":"10.1007\/978-3-030-44092-3_1-3"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2022.104176","article-title":"Diagnostic stewardship for blood cultures in the emergency department: a multicenter validation and prospective evaluation of a machine learning prediction tool","volume":"82","author":"Schinkel","journal-title":"EBioMedicine"},{"key":"R38","unstructured":"Mohan S Li D . MedMentions: a large biomedical corpus annotated with UMLS concepts. arXiv. Preprint posted online on Feb 25, 2019. [doi: 10.48550\/arXiv.1902.09476]"},{"issue":"10","key":"R39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgph.0003555","article-title":"Racial differences in laboratory testing as a potential mechanism for bias in AI: a matched cohort analysis in emergency department visits","volume":"4","author":"Chang","journal-title":"PLOS Glob Public Health"},{"key":"R40","unstructured":"Abdollahpouri H Adomavicius G Burke R et al. Beyond personalization: research directions in multistakeholder recommendation. arXiv. Preprint posted online on May 1, 2019. [doi: 10.48550\/arXiv.1905.01986]"},{"issue":"3","key":"R41","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1561\/2200000106","article-title":"Causal fairness analysis: a causal toolkit for fair machine learning","volume":"17","author":"Ple\u010dko","journal-title":"Found Trends Mach Learn"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e85255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:50Z","timestamp":1785536750000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e85255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.2196\/85255","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"article-number":"v14i6e85255"}}