Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Predicting Laboratory Test Utilization in Emergency Departments Using Machine Learning Models Integrating Structured and Unstructured Electronic Health Records
Xingyu Zhang;
Haipeng Ling;
Xin Zhang;
Anao Zhang
ABSTRACT
Laboratory testing is essential in emergency departments (EDs), but overuse contributes to unnecessary costs. This study explored machine learning models to predict lab test utilization during ED visits using both structured and unstructured electronic health record (EHR) data. We analyzed 15,115 adult visits from the 2021 National Hospital Ambulatory Medical Care Survey–ED. Structured variables included demographics, vital signs, insurance, and medical history; unstructured text from chief complaints and injury descriptions was processed using BERT embeddings. Four models were trained across structured-only, unstructured-only, combined, and ensemble configurations. The combined model achieved the highest AUC (0.83), outperforming structured-only (0.78) and unstructured-only (0.74) models. Key predictors of testing included older age, ambulance arrival, abnormal vitals, and chronic conditions, while injury-related visits predicted lower use. Integrating structured and unstructured EHR data improves lab test prediction and supports the development of decision support tools to promote more efficient diagnostic practices in EDs.
Citation
Please cite as:
Zhang X, Ling H, Zhang X, Zhang A
Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study
