# CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation

arXiv: https://arxiv.org/abs/2604.10420 · HTML: https://mlsanity.com/paper/2604.10420/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Automatic diagnosis of the 12-lead ECG using a deep neural network](https://mlsanity.com/paper/1904.01949/) (2019)
- [ECG-FM: An Open Electrocardiogram Foundation Model](https://mlsanity.com/paper/2408.05178/) (2024)
- [CausalVAE: Structured Causal Disentanglement in Variational Autoencoder](https://mlsanity.com/paper/2004.08697/) (2020)
- [HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations](https://mlsanity.com/paper/2409.19487/) (2024)
- [Teach Multimodal LLMs to Comprehend Electrocardiographic Images](https://mlsanity.com/paper/2410.19008/) (2024)
- [MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering](https://mlsanity.com/paper/2406.06573/) (2024)
- [LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts](https://mlsanity.com/paper/2412.12001/) (2024)
- [Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach](https://mlsanity.com/paper/2407.08215/) (2024)
- [ECG Unveiled: Analysis of Client Re-identification Risks in Real-World ECG Datasets](https://mlsanity.com/paper/2408.10228/) (2024)
- [ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis](https://mlsanity.com/paper/2502.17475/) (2025)
- [CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.12560/) (2025)
- [MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering](https://mlsanity.com/paper/2508.15849/) (2025)
- [Linkage Attacks Expose Identity Risks in Public ECG Data Sharing](https://mlsanity.com/paper/2508.15850/) (2025)
- [Causal Modeling](https://mlsanity.com/paper/1303.1471/) (2013)
- [TransECG: Leveraging Transformers for Explainable ECG Re-identification Risk Analysis](https://mlsanity.com/paper/2503.13495/) (2025)

## Built on by (most cited first, 2 of 2)

- [PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning](https://mlsanity.com/paper/2605.07267/) (2026)
- [ATRIA: Adaptive Traceable ECG Reporting with Iterative Agents](https://mlsanity.com/paper/2606.24392/) (2026)

## Abstract (arXiv)

Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and retrieval without explicit physiological or causal structure. This limits grounding, temporal reasoning, and counterfactual "what-if" analysis central to clinical decision-making. We propose CARE-ECG, a causally structured ECG-language reasoning framework that unifies representation learning, diagnosis, and explanation in a single pipeline. CARE-ECG encodes multi-lead ECGs into temporally organized latent biomarkers, performs causal graph inference for probabilistic diagnosis, and supports counterfactual assessment via structural causal models. To improve faithfulness, CARE-ECG grounds language outputs through causal retrieval-augmented generation and a modular agentic pipeline that integrates history, diagnosis, and response with verification. Across multiple ECG benchmarks and expert QA settings, CARE-ECG improves diagnostic accuracy and explanation faithfulness while reducing hallucinations (e.g., 0.84 accuracy on Expert-ECG-QA and 0.76 on SCP-mapped PTB-XL under GPT-4). Overall, CARE-ECG provides traceable reasoning by exposing key latent drivers, causal evidence paths, and how alternative physiological states would change outcomes.