In cardiology, it is standard for patients suffering from ventricular arrhythmias (the leading cause of sudden cardiac death) belonging to high risk populations to be treated using Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs). S-ICDs carry a risk of so-called T Wave Over Sensing (TWOS), which can lead to inappropriate shocks with an inherent health risk. For this reason, according to current practice patients' Electrocardiograms (ECGs) are screened over 10 seconds to measure the T:R ratio (the ratio between the amplitudes of the T and R waves), which is a used as a marker for the likelihood of TWOS. Unfortunately, the temporal variability of a patient' T:R ratio can render this short screening procedure unreliable. In this paper, we propose and investigate a tool based on deep learning for the automatic prediction of the T:R ratios of 10-second ECG segments. In particular, we evaluate different deep learning model architectures, assess a range of stochastic gradient descent based optimization methods for model training, perform hyperparameter tuning, and create ensembles of the best performing models. Our automated T:R ratio detection tool can enable clinicians to provide a more reliable assessment of whether a patient is eligible for S-ICD implantation by allowing for a significantly longer screening window which captures the behavior of the patient's T:R ratio better than the current practice.
Anthony J. Dunn, Stefano Coniglio, Mohamed ElRefai, Paul R. Roberts, Benedict W. Wiles, and Alain B. Zemkoho, Deep learning and hyperparameter optimization for assessing one’s eligibility for a subcutaneous implantable cardioverter-defibrillator, https://optimization-online.org/?p=21066, 2022
View Deep learning and hyperparameter optimization for assessing one’s eligibility for a subcutaneous implantable cardioverter-defibrillator