Dynamic Prototype Rehearsal for Continual Learning in ECG Arrhythmia Detection

2025-01-13

AI Summary

To address catastrophic forgetting in continual learning for electrocardiogram (ECG) ventricular arrhythmia detection, this paper proposes a dynamic prototype replay mechanism. The method adaptively selects highly challenging, representative prototypes via training-behavior clustering and smoothed difficulty ranking, enabling efficient knowledge retention across sequential multi-task learning. The framework uniformly supports three continual learning paradigms: time-incremental, class-incremental, and lead-incremental settings. Extensive experiments on the Chapman and PTB-XL datasets demonstrate that our approach consistently outperforms existing state-of-the-art methods, achieving average accuracy improvements of 3.2–5.7 percentage points across all incremental scenarios. To the best of our knowledge, this is the first work to deeply integrate difficulty-aware prototype selection with clustering-driven replay, significantly enhancing model generalization and retention capability for previously learned tasks.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Multiagent Systems: Multiagent Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Continual Learning (CL) methods aim to learn from a sequence of tasks while avoiding the challenge of forgetting previous knowledge. We present DREAM-CL, a novel CL method for ECG arrhythmia detection that introduces dynamic prototype rehearsal memory. DREAM-CL selects representative prototypes by clustering data based on learning behavior during each training session. Within each cluster, we apply a smooth sorting operation that ranks samples by training difficulty, compressing extreme values and removing outliers. The more challenging samples are then chosen as prototypes for the rehearsal memory, ensuring effective knowledge retention across sessions. We evaluate our method on time-incremental, class-incremental, and lead-incremental scenarios using two widely used ECG arrhythmia datasets, Chapman and PTB-XL. The results demonstrate that DREAM-CL outperforms the state-of-the-art in CL for ECG arrhythmia detection. Detailed ablation and sensitivity studies are performed to validate the different design choices of our method.

Problem

• Continual Learning
• ECG Arrhythmia Detection
• Memory Optimization

Innovation

• DREAM-CL
• Continuous Learning
• ECG Arrhythmia Detection