Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters

TL;DR

This paper explores lightweight unsupervised anomaly detection filters optimized via neural architecture search to improve ECG classification robustness on resource-limited wearable devices, effectively handling noise and unseen pathologies.

Contribution

It introduces a NAS-optimized Deep SVDD approach as a lightweight upstream filter for ECG anomaly detection, suitable for microcontrollers, enhancing classification accuracy.

Findings

Deep SVDD achieved the best Pareto efficiency in detection performance and size.

The lightweight filter improved diagnostic classifier accuracy by up to 21 percentage points.

The approach is feasible under strict hardware constraints (≤512k parameters).

Abstract

Continuous electrocardiogram (ECG) monitoring via wearable devices is vital for early cardiovascular disease detection. However, deploying deep learning models on resource-constrained microcontrollers faces reliability challenges, particularly from Out-of-Distribution (OOD) pathologies and noise. Standard classifiers often yield high-confidence errors on such data. Existing OOD detection methods either neglect computational constraints or address noise and unseen classes separately. This paper investigates Unsupervised Anomaly Detection (UAD) as a lightweight, upstream filtering mechanism. We perform a Neural Architecture Search (NAS) on six UAD approaches, including Deep Support Vector Data Description (Deep SVDD), input reconstruction with (Variational-)Autoencoders (AE/VAE), Masked Anomaly Detection (MAD), Normalizing Flows (NFs) and Denoising Diffusion Probabilistic Models (DDPM) under strict hardware constraints ($\leq$512k parameters), suitable for microcontrollers. Evaluating on the PTB-XL and BUT QDB datasets, we demonstrate that a NAS-optimized Deep SVDD offers the superior Pareto efficiency between detection performance and model size. In a simulated deployment, this lightweight filter improves the accuracy of a diagnostic classifier by up to 21.0 percentage points, demonstrating that optimized UAD filters can safeguard ECG analysis on wearables.