Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters
Not on the map. Why?
Abstract (arXiv)
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 (≤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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 50 references that are in the map. First posted on arXiv 30 Oct 2025.
Builds on
15 of 50 references.
References · 15
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2016Concrete Problems in AI Safetycited by 1,582
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
- 2018Do Deep Generative Models Know What They Don't Know?cited by 443
- 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
- 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
- 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
- 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
- 2022MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Seriescited by 12
- 2025Autoencoders for Anomaly Detection are Unreliablecited by 9
- 2023In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detectioncited by 7
3 more
- 2022A Domain Generalization Approach for Out-Of-Distribution 12-lead ECG Classification with Convolutional Neural Networkscited by 5
- 2024Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG Diagnosiscited by 3
- 2025ECG Identity Authentication in Open-set with Multi-model Pretraining and Self-constraint Center & Irrelevant Sample Repulsion Learningcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers
- 2024Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning
- 2023Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata
- 2025Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals
- 2025ECG-RAMBA: Zero-Shot ECG Generalization by Morphology-Rhythm Disentanglement and Long-Range Modeling
- 2026Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection
- 2025Interpretable Multimodal Zero-Shot ECG Diagnosis via Structured Clinical Knowledge Alignment
- 2025Lightweight Multi-task CNN for ECG Diagnosis with GRU-Diffusion ↗