Abstract
Aim
To develop an artificial intelligence-based approach with multi-labeling capability to identify both ST-elevation myocardial infarction (STEMI) and 12 heart rhythms based on 12-lead ECGs.
Methods
We trained, validated, and tested a long short-term memory (LSTM) model for the multi-label diagnosis of 13 ECG patterns (STEMI+12 rhythm classes) using 60,537 clinical ECGs from 35,981 patients recorded between Jan 15, 2009 and Dec 31, 2018. In addition to the internal test above, we conducted a real-world external test, comparing the LSTM model with board-certified physicians of different specialties using a separate dataset of 308 ECGs covering all 13 ECG diagnoses.
Results
In the internal test, the area under curves (AUCs) of the LSTM model in classifying the 13 ECG patterns ranged between 0.939 and 0.999. For the external test, the LSTM model for multi-labeling of the 13 ECG patterns evaluated by AUC was 0.987±0.021, which was superior to those of cardiologists (0.898±0.113, P < 0.001), emergency physicians (0.820±0.134, P < 0.001), internists (0.765±0.155, P < 0.001), and a commercial algorithm (0.845±0.121, P < 0.001). Of note, the LSTM model achieved an accuracy of 0.987, AUC of 0.997, and precision, recall, and F 1 score of 0.952, 0.870, and 0.909, respectively, in detecting STEMI.
Conclusions
We demonstrated the usefulness of an LSTM model in the multi-labeling detection of both rhythm classes and STEMI in competitive testing against board-certified physicians. This AI tool exceeding the cardiologist-level performance in detecting STEMI and rhythm classes on 12-lead ECG may be useful in prioritizing chest pain triage and expediting clinical decision making in healthcare.