TY - JOUR
T1 - Automated Identification and Extraction of Exercise Treadmill Test Results
AU - Zheng, Chengyi
AU - Sun, Benjamin C.
AU - Wu, Yi Lin
AU - Lee, Ming Sum
AU - Shen, Ernest
AU - Redberg, Rita F.
AU - Ferencik, Maros
AU - Natsui, Shaw
AU - Kawatkar, Aniket A.
AU - Musigdilok, Visanee V.
AU - Sharp, Adam L.
PY - 2020/3/3
Y1 - 2020/3/3
N2 - 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.
AB - 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.
KW - cardiac event
KW - chest pain
KW - emergency department
KW - natural language processing
KW - noninvasive test
KW - treadmill test
UR - http://www.scopus.com/inward/record.url?scp=85079765283&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079765283&partnerID=8YFLogxK
U2 - 10.1161/JAHA.119.014940
DO - 10.1161/JAHA.119.014940
M3 - Article
C2 - 32079480
SN - 2047-9980
VL - 9
SP - e014940
JO - Journal of the American Heart Association
JF - Journal of the American Heart Association
IS - 5
ER -