DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 40 references that are in the map. First posted on arXiv 15 May 2026.
Builds on
16 of 40 references.
References · 16
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Qwen Technical Reportcited by 3,273
- 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
- 2025OpenAI GPT-5 System Cardcited by 910
- 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
- 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
- 2024Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmarkcited by 38
- 2024ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosiscited by 37
- 2025GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Imagescited by 35
- 2020Class-Weighted Classification: Trade-offs and Robust Approachescited by 30
- 2024Teach Multimodal LLMs to Comprehend Electrocardiographic Imagescited by 25
- 2021ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Networkcited by 14
4 more
- 2025Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Modelscited by 11
- 2025BenchECG and xECG: a benchmark and baseline for ECG foundation modelscited by 8
- 2026ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretationcited by 8
- 2026ECG-Agent: On-Device Tool-Calling Agent for ECG Multi-Turn Dialoguecited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals
- 2026TRACE: Expert-Aligned ECG Representation Learning with Rigorous Benchmarking and Real-World Validation in Acute Cardiac Care
- 2025ECG-RAMBA: Zero-Shot ECG Generalization by Morphology-Rhythm Disentanglement and Long-Range Modeling
- 2025Generating Realistic Multi-Beat ECG Signals
- 2025Benchmarking ECG FMs: A Reality Check Across Clinical Tasks
- 2026Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis
- 2026ECGQuest: Benchmarking and Fine-Tuning Language Models for Electrocardiography
- 2026ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms