Synthetic Data Augmentation for Medical Audio Classification: A Preliminary Evaluation

TL;DR

Medical audio classification faces data scarcity and class imbalance, motivating synthetic data augmentation. The study evaluates three generative strategies—variational autoencoders, diffusion models, and GANs with WGAN-GP—on a COVID-19 cough dataset using a baseline CNN, augmenting the minority class by 50%. Results show no consistent improvement from individual augmentations; only an ensemble of augmented models yields modest gains in macro F1 and AUROC, suggesting benefits stem from diversification rather than single-model improvements. The findings highlight that synthetic augmentation's value is context-dependent and point to future directions such as pretraining, representation learning, domain-informed priors, and more rigorous evaluation frameworks for medical audio tasks.

Abstract

Medical audio classification remains challenging due to low signal-to-noise ratios, subtle discriminative features, and substantial intra-class variability, often compounded by class imbalance and limited training data. Synthetic data augmentation has been proposed as a potential strategy to mitigate these constraints; however, prior studies report inconsistent methodological approaches and mixed empirical results. In this preliminary study, we explore the impact of synthetic augmentation on respiratory sound classification using a baseline deep convolutional neural network trained on a moderately imbalanced dataset (73%:27%). Three generative augmentation strategies (variational autoencoders, generative adversarial networks, and diffusion models) were assessed under controlled experimental conditions. The baseline model without augmentation achieved an F1-score of 0.645. Across individual augmentation strategies, performance gains were not observed, with several configurations demonstrating neutral or degraded classification performance. Only an ensemble of augmented models yielded a modest improvement in F1-score (0.664). These findings suggest that, for medical audio classification, synthetic augmentation may not consistently enhance performance when applied to a standard CNN classifier. Future work should focus on delineating task-specific data characteristics, model-augmentation compatibility, and evaluation frameworks necessary for synthetic augmentation to be effective in medical audio applications.

Figures (1)

• Figure 1: Macro-averaged F1 score and AUROC for CNN classifiers across augmentation methods.