Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Previous studies have successfully predicted overweight status by applying deep learning to 12-lead electrocardiogram (ECG); however, models for predicting underweight status remain unexplored. Here, we assessed the feasibility of deep learning in predicting extremely low body weight using 12-lead ECGs, thereby investigating the prediction rationale for highlighting the parts of ECGs that are associated with extremely low body weight. Using records of inpatients predominantly with anorexia nervosa, we trained a convolutional neural network (CNN) that inputs a 12-lead ECG and outputs a binary prediction of whether body mass index is ≤ 12.6 kg/m². This threshold was identified in a previous study as the optimal cutoff point for predicting the onset of refeeding syndrome. The CNN model achieved an area under the receiver operating characteristic curve of 0.807 (95% confidence interval, 0.745-0.869) on the test dataset. The gradient-weighted class activation map showed that the model focused on QRS waves. A negative correlation with the prediction scores was observed for QRS voltage. These results suggest that deep learning is feasible for predicting extremely low body weight using 12-lead ECGs, and several ECG features, such as lower QRS voltage, may be associated with extremely low body weight in patients with anorexia nervosa.