Key result
A deep learning model combining LSTM and CNN estimated dynamic ventilatory threshold from ECGs with a mean difference of -0.28 ml/min/kg (95% CI -1.91 to 1.34) compared to labels on the Bruce protocol.
Why the study?
Assessing ventilatory threshold requires gas analyzers or heart rate variability from electrocardiograms, which requires at least 5 minutes of recording and depends on preprocessing algorithms.
Does a deep learning-based model using lead II ECGs accurately estimate ventilatory threshold?
Does a deep learning-based model using lead II ECGs accurately estimate ventilatory threshold?
A novel deep learning model using lead II ECGs and physical characteristics can accurately estimate dynamic ventilatory threshold, potentially aiding in cardiorespiratory fitness management and cardiovascular rehabilitation.
DL model may enable noninvasive dynamic VT estimation from HRV; leaves open prospective validation before clinical use.
BACKGROUND AND OBJECTIVE: The ventilatory threshold (VT) marks the transition from aerobic to anaerobic metabolism and is used to assess cardiorespiratory endurance. A conventional way to assess VT is cardiopulmonary exercise testing, which requires a gas analyzer. Another method for measuring VT involves calculating the heart rate variability (HRV) from an electrocardiogram (ECG) by computing the variability of heartbeats. However, the HRV method has some limitations. ECGs should be recorded for at least 5 minutes to calculate the HRV, and the result may depend on the utilized ECG preprocessing algorithms. METHODS: To overcome these problems, we developed a deep learning-based model consisting of long short-term memory (LSTM) and convolutional neural network (CNN) for a lead II ECG. Variables reflecting subjects' physical characteristics, as well as ECG signals, were input into the model to estimate VT. We applied joint optimization to the CNN layers to generate an informative latent space, which was fed to the LSTM layers. The model was trained and evaluated on two datasets, one from the Bruce protocol and the other from a protocol including multiple tasks (MT). RESULTS: Acceptable performances (mean and 95% CI) were obtained on the datasets from the Bruce protocol (-0.28[-1.91,1.34] ml/min/kg) and the MT protocol (0.07[-3.14,3.28] ml/min/kg) regarding the differences between the predictions and labels. The coefficient of determination, Pearson correlation coefficient, and root mean square error were 0.84, 0.93, and 0.868 for the Bruce protocol and 0.73, 0.97, and 3.373 for the MT protocol, respectively. CONCLUSIONS: The results indicated that it is possible for the proposed model to simultaneously assess VT with the inputs of successive ECGs. In addition, from ablation studies concerning the physical variables and the joint optimization process, it was demonstrated that their use could boost the VT assessment performance of the model. The proposed model enables dynamic VT estimation with ECGs, which could help with managing cardiorespiratory fitness in daily life and cardiovascular rehabilitation in patients.
No takes yet. Share an insight, caveat, or question.
Cho et al. (2023) studied Cardiorespiratory fitness. Deep learning-based model (LSTM and CNN) for ECG vs. Cardiopulmonary exercise testing (labels) was evaluated on Difference between predicted and labeled ventilatory threshold (MD -0.28, 95% CI -1.91 to 1.34). A deep learning model combining LSTM and CNN estimated dynamic ventilatory threshold from ECGs with a mean difference of -0.28 ml/min/kg (95% CI -1.91 to 1.34) compared to labels on the Bruce protocol.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: