AI-Powered Resting 12-Lead Electrocardiogram Algorithm for Predicting Low Peak Oxygen Consumption: Development and Validation Study

Background Low peak oxygen consumption (V̇O 2 ) is associated with higher cardiovascular and all-cause mortality, while improvements in peak V̇O 2 reduce this risk. Although early detection allows timely intervention, practical screening tools remain lacking. As electrocardiograms (ECGs) reflect both cardiac and age-related changes, they may offer a viable screening approach. Objective This study aimed to detect low peak V̇O 2 using resting 12-lead ECGs analyzed by a trained neural network. Methods The low peak V̇O 2 estimation model was developed using data from 965 individuals (n=540, 56% with cardiac or pulmonary disorders) mainly at Chang Gung Memorial Hospital, Linkou, and validated in an independent cohort of 242 individuals (n=194, 80% with cardiac disorders) at the Keelung branch. Resting ECGs were recorded immediately before cardiopulmonary exercise testing. Low peak V̇O 2 was defined as a peak V̇O 2 of <14 mL/kg/min. Results The mean peak V̇O 2 was 17.5 (SD 6.1) and 15.4 (SD 3.9) mL/kg/min in the training and validation datasets, with 27% (261/965) and 38% (92/242) classified as low peak V̇O 2 , respectively. Wavelet analysis improved model accuracy, underscoring its value for feature extraction. Three input models were compared: (1) individual characteristics (IC; age, sex, BMI, resting heart rate, and heart rate variability), (2) ECG alone, and (3) ECG plus IC. ECG alone outperformed IC, and combining both yielded the highest accuracy. For low peak V̇O 2 prediction, ECG plus IC achieved mean area under the curve, precision, and recall values of 0.89, 0.72, and 0.72 in cross-validation, and 0.87, 0.67, and 0.61 in external validation. Conclusions An artificial intelligence–driven ECG-based algorithm showed strong potential for screening low peak V̇O 2 , enabling early identification of individuals with low peak V̇O 2 and facilitating timely clinical intervention.