A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms

Abstract

AbstractDetection of heart disease using a stethoscope requires significant skill and time, making it expensive and impractical for widespread screening in low-resource environments. Machine learning analysis of heart sound recordings can improve upon the accessibility and accuracy of diagnoses, but existing approaches require further validation on larger and more representative clinical datasets. For many previous algorithms, segmenting the signal into its individual sound components is a key first step. However, segmentation algorithms often struggle to find S1 or S2 sounds in the presence of strong murmurs or noise that significantly alter or mask the expected sound. Segmentation errors then propagate to the subsequent disease classifier steps. We propose a novel recurrent neural network and hidden semi-Markov model (HSMM) algorithm that can both segment the signal and detect a heart murmur, removing the need for a two-stage algorithm. This algorithm formed the ‘CUED Acoustics’ entry to the 2022 George B. Moody PhysioNet challenge, where it won the first prize in both the challenge tasks. The algorithm’s performance exceeded that of many end-to-end deep learning approaches that struggled to generalise to new test data. As our approach both segments the heart sound and detects a murmur, it can provide interpretable predictions for a clinician. The model also estimates the signal quality of the recording, which may be useful for a screening environment where non-experts are using a stethoscope. These properties make the algorithm a promising tool for screening of abnormal heart murmurs.Author summaryThe use of machine learning algorithms to detect heart disease from sound recordings has great potential to enable widespread and low-skill screening, improving early detection and treatment. The area has seen increasing interest in recent years, with many novel algorithms inspired by deep learning advancements in other fields. However, the size of heart sound datasets remains small, making deep learning models particularly susceptible to overfitting. In addition, the performance of these algorithms has rarely been directly compared on unseen data. We describe a novel lightweight algorithm to detect and classify murmurs in heart sound recordings. This algorithm was the winning entry into the George B. Moody PhysioNet 2022 challenge, beating many complex deep-learning approaches. Our approach both detects and localises the murmur, providing an interpretable result for a clinician.