Background
Coronary artery calcium (CAC) scoring is recommended in adults with unclear cardiovascular (CV) risk to inform preventative strategies and has major limitations. We developed a deep learning (DL) algorithm to predict CAC from 12-lead electrocardiograms (ECG-AI).
Methods
Historical cohort of 43,210 consecutive patients that from 1997-2020 underwent clinically indicated CAC and ECG within 1 year. Age, sex and major modifiable CV risk factors were collected during medical visits. We excluded those on statins, paced rhythm, history of myocardial infarction or missing data. We trained a convolutional neural network based on ECG-AI output +/- CV risk factors to predict a high CAC score (≥ 300) on a random sample of 60% of the dataset, validated in 20%. We evaluated model performance with thresholds that yielded 90% sensitivity, in the remaining 20%.
Results
Mean ± SD age 55 ± 9.8, 31% women, 1,857 (20%) had CAC ≥ 300. Algorithm’s AUC of the ROC, specificity, and accuracy was 77%, 38%, 44%, for ECG-AI only; and 83%, 56%, 60% for ECG-AI + age and sex; and 83%, 57%, 61% for ECG-AI, age, sex + CV risk factors, see Figure. The ECG-AI + age and sex algorithm displayed equivalent performance when compared to the one including CV risk factors (p>0.05). Subgroup performance was constant, including those with no CV risk factors.
Conclusion
The DL-enabled ECG can help predict a high CAC score, even without information on CV risk. This algorithm could improve selection of subjects with higher likelihood of CAC.