To reduce the need for skilled clinicians in heart sound interpretation, recent studies on automating cardiac auscultation have explored deep learning approaches. However, despite the demands for large data for deep learning, the size of the heart sound datasets is limited, and no pre-trained model is available. On the contrary, many pre-trained models for general audio tasks are available as general-purpose audio representations. This study explores the potential of general-purpose audio representations pre-trained on large-scale datasets for transfer learning in heart murmur detection. Experiments on the CirCor DigiScope heart sound dataset show that the recent self-supervised learning Masked Modeling Duo (M2D) outperforms previous methods with the results of a weighted accuracy of 0.832 and an unweighted average recall of 0.713. Experiments further confirm improved performance by ensembling M2D with other models. These results demonstrate the effectiveness of general-purpose audio representation in processing heart sounds and open the way for further applications. Our code is available online which runs on a 24 GB consumer GPU at https://github.com/nttcslab/m2d/tree/master/app/circor
Murmurs are sounds caused by turbulent blood flow that are often the first sign of structural heart disease. These sounds are detected by auscultating the heart using a stethoscope, or more recently by a phonocardiogram (PCG). We aim to identify the presence, absence, or unclear cases of murmurs, as well as predict normal or abnormal clinical outcome from PCG recordings using machine learning. We trained and tested two 1-dimensional convolutional neural networks (CNN) on a PCG data set from a pediatric population of 1568 individuals. One model predicted murmurs, while the other model predicted clinical outcomes. Both models were trained to give recording-wise predictions, while the final predictions were given for every patient (patient-wise predictions). This paper describes our participation in the George B. Moody PhysioNet Challenge 2022 whose objective was to identify heart murmurs and clinical outcome from PCGs. Our team, Simulab, trained a clinical outcome classifier that achieved a challenge cost score of 12419 (ranked 14th out of 39 teams) and the murmur classifier achieved a weighted accuracy of 0.593 (ranked 30th out of 40 teams) on the test set.
Cardiac auscultation is one of the most cost-effective techniques used to detect and identify many heart conditions. Computer-assisted decision systems based on auscultation can support physicians in their decisions. Unfortunately, the application of such systems in clinical trials is still minimal since most of them only aim to detect the presence of extra or abnormal waves in the phonocardiogram signal, i.e., only a binary ground truth variable (normal vs abnormal) is provided. This is mainly due to the lack of large publicly available datasets, where a more detailed description of such abnormal waves (e.g., cardiac murmurs) exists. To pave the way to more effective research on healthcare recommendation systems based on auscultation, our team has prepared the currently largest pediatric heart sound dataset. A total of 5282 recordings have been collected from the four main auscultation locations of 1568 patients, in the process, 215780 heart sounds have been manually annotated. Furthermore, and for the first time, each cardiac murmur has been manually annotated by an expert annotator according to its timing, shape, pitch, grading, and quality. In addition, the auscultation locations where the murmur is present were identified as well as the auscultation location where the murmur is detected more intensively. Such detailed description for a relatively large number of heart sounds may pave the way for new machine learning algorithms with a real-world application for the detection and analysis of murmur waves for diagnostic purposes.