AI summaryⓘ
The authors created a computer model that generates synthetic heart sound recordings to help with training and testing heart-sound analysis tools. They used a special method to make realistic sound features and checked how believable the sounds are using math tests, machine learning, and expert listeners. The synthetic sounds kept important timing features but had some differences in rhythm and sudden bursts compared to real sounds. Their tests showed the model can produce realistic signals that still help classify normal versus abnormal heart sounds, though detecting abnormalities in short clips remains challenging. Overall, their work offers a useful starting point for making artificial heart sounds, while pointing out ongoing difficulties in perfecting abnormal sound features.
phonocardiogram (PCG)diffusion modellog-mel representationconditional U-Netsignal plausibilityResNet-50 classifierheart sound classificationsynthetic data generationenvelope-autocorrelationabnormality detection
Authors
Xinqi Bao, Jia Bi, Xin Chen, Ernest Nlandu Kamavuako, Saikat Chatterjee
Abstract
Publicly available phonocardiogram (PCG) datasets remain limited in size and pathological diversity, constraining both auscultation training and the generalisation of automated heart-sound classifiers. A class-conditional diffusion model for PCG generation is developed in the log-mel domain and synthetic fidelity is assessed using complementary (i) physiology-inspired plausibility metrics, (ii) downstream label-consistency evaluation, and (iii) expert listening. Experiments use the Phy-sioNet/Computing in Cardiology Challenge 2016 dataset (3240 recordings) with recording-level splits. After preprocessing and quality control, 16,749 non-overlapping 4 s clips are mapped to a normalised 1 x 128 x 128 log-mel representation to train a conditional 2D U-Net denoiser with classifier-free guidance. Signal-level plausibility is quantified on reconstructed waveforms using three lightweight metrics: an envelope-autocorrelation rhythm score, an amplitude-based explosion score, and the dominant cycle lag. Synthetic clips preserve similar dominant cycle durations but exhibit reduced envelope periodicity and increased transient burstiness relative to real clips. For downstream evaluation, a ResNet-50 classifier achieves 92.24% accuracy on the held-out real test set and 82.8% accuracy on class-balanced synthetic batches, indicating that generated signals retain discriminative structure relevant to normal/abnormal classification. In a pilot expert listening study (60 clips, two clinicians), most synthetic clips are judged as heart-sound-like, while abnormality sensitivity is low for both real and synthetic 4 s excerpts. Overall, the results provide a practical baseline for diffusion-based PCG generation while highlighting remaining challenges in retaining abnormal acoustic cues and reducing reconstruction-induced artefacts.