Coronary interventions

A deep learning algorithm for detecting acute myocardial infarction

EuroIntervention 2021;17:765-773. DOI: 10.4244/EIJ-D-20-01155

Wen-Cheng Liu
Wen-Cheng Liu1, MD; Chin-Sheng Lin1, MD, PhD; Chien-Sung Tsai2, MD; Tien-Ping Tsao3, MD; Cheng-Chung Cheng1, MD; Jun-Ting Liou1, MD; Wei-Shiang Lin1, MD; Shu-Meng Cheng1, MD, PhD; Yu-Sheng Lou4, MS; Chia-Cheng Lee5,6, MD; Chin Lin4,7,8, PhD
1. Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.; 2. Division of Cardiovascular Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.; 3. Division of Cardiology, Heart Centre, Cheng Hsin Hospital, Taipei, Taiwan, R.O.C.; 4. Graduate Institute of Life Sciences, National Defense Medical Center, Taipei, Taiwan, R.O.C.; 5. Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C; 6. Division of Colorectal Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.; 7. School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C.; 8. School of Public Health, National Defense Medical Center, Taipei, Taiwan, R.O.C.

Background: Delayed diagnosis or misdiagnosis of acute myocardial infarction (AMI) is not unusual in daily practice. Since a 12-lead electrocardiogram (ECG) is crucial for the detection of AMI, a systematic algorithm to strengthen ECG interpretation may have important implications for improving diagnosis.

Aims: We aimed to develop a deep learning model (DLM) as a diagnostic support tool based on a 12-lead electrocardiogram.

Methods: This retrospective cohort study included 1,051/697 ECGs from 737/287 coronary angiogram (CAG)-validated STEMI/NSTEMI patients and 140,336 ECGs from 76,775 non-AMI patients at the emergency department. The DLM was trained and validated in 80% and 20% of these ECGs. A human-machine competition was conducted. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the performance of the DLM.

Results: The AUC of the DLM for STEMI detection was 0.976 in the human-machine competition, which was significantly better than that of the best physicians. Furthermore, the DLM independently demonstrated sufficient diagnostic capacity for STEMI detection (AUC=0.997; sensitivity, 98.4%; specificity, 96.9%). Regarding NSTEMI detection, the AUC of the combined DLM and conventional cardiac troponin I (cTnI) increased to 0.978, which was better than that of either the DLM (0.877) or cTnI (0.950).

Conclusions: The DLM may serve as a timely, objective and precise diagnostic decision support tool to assist emergency medical system-based networks and frontline physicians in detecting AMI and subsequently initiating reperfusion therapy.

Sign in to read and download the full article

Forgot your password?

No account yet?
Sign up for free!

Create my pcr account

Join us for free and access thousands of articles from EuroIntervention, as well as presentations, videos, cases from PCRonline.com

acute myocardial infarctionartificial intelligencedeep learning modelelectrocardiogram
Read next article
Incidence and clinical impact of major bleeding following left atrial appendage occlusion: insights from the Amplatzer Amulet Observational Post-Market Study

Latest news