DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
cs.LG, cs.AI
Submitted: 2026-05-15
Updated: 2026-09-27
Comments: Accepted at NeurIPS 2026. 40 pages
License: http://creativecommons.org/licenses/by/4.0/
The gist: Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local instances.
Terminology
Abstract
Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local instances. This is limiting because beat labels often depend on multi-beat rhythm context, including timing, compensatory pauses, and beat-to-beat morphological consistency. We present DeepArrhythmia, a tool-grounded multimodal framework for segment-contextualized beat-level ECG arrhythmia classification. Given a multi-beat ECG segment, DeepArrhythmia combines the raw ECG signal and a rendered waveform image, localizes R peaks to identify beat instances, and produces structured beat-level predictions. The framework decouples physiological measurement from evidence integration using specialized tools for beat localization, numerical rhythm--morphology extraction, and morphology-focused textual analysis. DeepArrhythmia uses segment-level confidence to route between minimal and rich evidence states, since richer physiological evidence is not uniformly useful. This agentic design integrates rhythm context, explicit physiological grounding, and selective evidence acquisition for decision making.
Sources
- Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models
- Qwen Technical Report
- ECG-Agent: On-Device Tool-Calling Agent for ECG Multi-Turn Dialogue
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
- Teach Multimodal LLMs to Comprehend Electrocardiographic Images
- BenchECG and xECG: a benchmark and baseline for ECG foundation models
- OpenAI GPT-5 System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Gemma: Open Models Based on Gemini Research and Technology
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks