Automated Identification and Extraction of Exercise Treadmill Test Results.

ABSTRACT

Background Noninvasive cardiac tests, including exercise treadmill tests (ETTs), are commonly utilized in the evaluation of patients in the emergency department with suspected acute coronary syndrome. However, there are ongoing debates on their clinical utility and cost-effectiveness. It is important to be able to use ETT results for research, but manual review is prohibitively time-consuming for large studies. We developed and validated an automated method to interpret ETT results from electronic health records. To demonstrate the algorithm's utility, we tested the associations between ETT results with 30-day patient outcomes in a large population. Methods and Results A retrospective analysis of adult emergency department encounters resulting in an ETT within 30 days was performed. A set of randomly selected reports were double-blind reviewed by 2 physicians to validate a natural language processing algorithm designed to categorize ETT results into normal, ischemic, nondiagnostic, and equivocal categories. Natural language processing then searched and categorized results of 5214 ETT reports. The natural language processing algorithm achieved 96.4% sensitivity and 94.8% specificity in identifying normal versus all other categories. The rates of 30-day death or acute myocardial infarction varied (P<0.001) by categories for normal (0.08%), ischemic (1.9%), nondiagnostic (0.77%), and equivocal (0.58%) groups achieving good discrimination (C-statistic, 0.81; 95% CI, 0.7-0.92). Conclusions Natural language processing is an accurate and efficient strategy to facilitate large-scale outcome studies of noninvasive cardiac tests. We found that most patients are at low risk and have normal ETT results, while those with abnormal, nondiagnostic, or equivocal results have slightly higher risks and warrant future investigation.