Spiking Neural Networks for the Analysis of Physiological Signals

Abstract

Physiological signals, such as electroencephalograms (EEG), electrocardiograms (ECG), and electromyograms (EMG) play a critical role in modern clinical diagnosis, monitoring, and rehabilitation. While deep artificial neural networks (ANNs) have achieved strong performance in analyzing these signals, their high computational cost and energy demands limit deployment in real-time, wearable, and edge-based healthcare systems. Spiking Neural Networks (SNNs), inspired by biological neural computation, offer an event-driven alternative that naturally captures temporal dynamics and enables energy-efficient inference. This article provides a comprehensive review of SNN-based methods for physiological signal analysis across EEG, ECG, and EMG modalities. We survey neuron models, network architectures, encoding schemes, and training methodologies, and systematically review recent state-of-the-art applications in medical diagnosis and rehabilitation. Through analysis, we identify recurring architectural and methodological trends that indicate the dominance of convolution-based spiking architectures, the critical role of encoding strategies in determining energy efficiency, and the task-dependent nature of SNN training approaches. Despite demonstrating performance comparable to conventional deep learning models, often at significantly reduced computational cost, SNN research remains challenged by inconsistent evaluation protocols, limited benchmark standardization, and restricted clinical validation. We conclude by outlining key open challenges and future research directions, emphasizing the need for standardized benchmarks, encoding-aware training, and hybrid ANN–SNN systems. As neuromorphic hardware and event-driven learning methods continue to mature, SNNs are well-positioned to introduce scalable, low-power physiological signal processing for next-generation intelligent healthcare systems.