Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection
This work addresses heart murmur detection for medical diagnosis, but it is incremental as it builds on existing deep learning and Bayesian methods for a specific challenge.
The study tackled heart murmur detection by implementing a Dual Bayesian ResNet model, achieving a weighted accuracy of 0.771 on a hidden test set and placing fourth in a challenge, with integration of demographic data improving accuracy from 0.762 to 0.820 on a held-out subset.
This study presents our team PathToMyHeart's contribution to the George B. Moody PhysioNet Challenge 2022. Two models are implemented. The first model is a Dual Bayesian ResNet (DBRes), where each patient's recording is segmented into overlapping log mel spectrograms. These undergo two binary classifications: present versus unknown or absent, and unknown versus present or absent. The classifications are aggregated to give a patient's final classification. The second model is the output of DBRes integrated with demographic data and signal features using XGBoost.DBRes achieved our best weighted accuracy of $0.771$ on the hidden test set for murmur classification, which placed us fourth for the murmur task. (On the clinical outcome task, which we neglected, we scored 17th with costs of $12637$.) On our held-out subset of the training set, integrating the demographic data and signal features improved DBRes's accuracy from $0.762$ to $0.820$. However, this decreased DBRes's weighted accuracy from $0.780$ to $0.749$. Our results demonstrate that log mel spectrograms are an effective representation of heart sound recordings, Bayesian networks provide strong supervised classification performance, and treating the ternary classification as two binary classifications increases performance on the weighted accuracy.