The ECG-MTDA framework achieved an AUC of 93.16 on the PTB-XL benchmark and an AUC of 0.97 ± 0.02 for short-term paroxysmal atrial fibrillation progression prediction.
Does the ECG-MTDA framework improve automated ECG interpretation and short-term pAF progression prediction compared to existing multimodal models?
The ECG-MTDA framework, which decouples waveform morphology from rhythm dynamics and aligns with LLM-generated text, significantly improves automated ECG diagnostic classification and short-term pAF progression prediction.
Effect estimate: AUC 0.97
Effective automated electrocardiogram (ECG) interpretation hinges on disentangling waveform morphology from rhythm dynamics, a challenge for existing multimodal models that often conflate these heterogeneous attributes and introduce semantic ambiguity. We introduce ECG-MTDA, a framework that explicitly decouples these components. It learns morphology-oriented representations via a PQRST-guided masked autoencoder, while separately modeling temporal dynamics using continuous wavelet transform. Crucially, we align the learned morphology with concise, label-conditioned textual descriptions generated by a large language model (LLM) using a contrastive objective, creating a semantically grounded embedding space. ECG-MTDA demonstrates superior performance on the PTB-XL and CPSC 2018 benchmarks (e. g. , AUC 93. 16 on PTB-XL Superclass), with statistically significant gains over a strong multimodal baseline. Furthermore, on a challenging in-house cohort (n=620) for short-term paroxysmal atrial fibrillation (pAF) progression prediction, the model achieves an AUC of 0. 97 0. 02 with high sensitivity (0. 80 0. 04) and specificity (0. 98 0. 01). Ablation studies and qualitative analyses confirm the benefits of our decoupled design and morphology-text alignment. Our results demonstrate that this clinically-inspired decoupling strategy yields more precise and robust multimodal representations for complex ECG analysis, enhancing both diagnostic classification and near-term risk stratification.
Zheng et al. (Thu,) conducted a other in Electrocardiogram (ECG) interpretation and paroxysmal atrial fibrillation (n=620). ECG-MTDA framework vs. Strong multimodal baseline was evaluated on Diagnostic classification (PTB-XL Superclass) and short-term paroxysmal atrial fibrillation progression prediction (AUC 0.97). The ECG-MTDA framework achieved an AUC of 93.16 on the PTB-XL benchmark and an AUC of 0.97 ± 0.02 for short-term paroxysmal atrial fibrillation progression prediction.