The DL-based automated recommendation system for laboratory tests achieved a significantly higher area under the receiver operating characteristic curve (AUROCmacro and AUROCmicro of 0.76 and 0.87, respectively). A total of 129,938 prescriptions were used in our model. Results: We used the area under the receiver operating characteristic curve, precision, recall, and hamming loss as comparative measures. In the internal validation, 25% of data were randomly selected from the training set to evaluate the performance of this model. The data set was split into training and testing sets (80:20) to develop the DL model. We reviewed the record of all patients who visited the cardiology department at least once and were prescribed laboratory tests. Methods: A retrospective analysis of the National Health Insurance database between January 1, 2013, and December 31, 2013, was performed. Objective: The objective of this study was to develop an artificial intelligence–based automated model that can provide laboratory tests recommendation based on simple variables available in EHRs. Therefore, developing an automated laboratory test recommendation tool using available data from electronic health records (EHRs) could support current clinical practice. Nowadays, artificial intelligence methods such as machine learning and deep learning (DL) have been extensively used as powerful tools for pattern recognition in large data sets. However, recognizing the value of correct laboratory test ordering remains underestimated by policymakers and clinicians. Diagnosis of patients could be wrong, missed, or delayed if laboratory tests are performed erroneously. Graduate Institute of Biomedical Informatics, College of Medical Science and TechnologyĮmail: Laboratory tests are considered an essential part of patient safety as patients’ screening, diagnosis, and follow-up are solely based on laboratory tests. JMIR Perioperative Medicine 50 articles.JMIR Biomedical Engineering 52 articles.Journal of Participatory Medicine 62 articles.JMIR Rehabilitation and Assistive Technologies 143 articles.JMIR Pediatrics and Parenting 166 articles.Interactive Journal of Medical Research 218 articles.JMIR Public Health and Surveillance 819 articles.Journal of Medical Internet Research 6261 articles.