An LLM-based staged extraction framework achieved comparable discrimination to a CNN-based model for localizing PVC origins from 12-lead ECGs (AUC 0.720 vs. 0.712).
Observational (n=157)
Does an LLM-based staged extraction framework accurately localize left-versus-right PVC origin from 12-lead ECG images compared to a CNN-based model in patients undergoing catheter ablation?
An LLM-based staged extraction framework can localize PVC origins from 12-lead ECGs with accuracy comparable to CNN models while providing a traceable diagnostic process.
ABSTRACT Background Accurate localization of premature ventricular contraction (PVC) origin from 12‐lead electrocardiography (ECG) is important for procedural planning in catheter ablation. Although convolutional neural network (CNN)‐based models have shown promising diagnostic performance, they require task‐specific training and remain limited in interpretability. We evaluated whether large language model (LLM)‐based ECG image interpretation could perform binary left‐versus‐right PVC origin localization from 12‐lead ECG images while providing a traceable diagnostic process. Methods We retrospectively studied 157 patients who underwent successful catheter ablation of PVCs or idiopathic ventricular tachycardia. ECG images were classified as RIGHT‐origin ( n = 103) or LEFT‐origin ( n = 54) according to the final successful ablation site. Three approaches were compared: a CNN‐based baseline model, an LLM‐based one‐shot approach, and an LLM‐based staged extraction framework with deterministic rule‐based integration. Performance was evaluated across five independent seeds using positive predictive value (PPV), negative predictive value (NPV), recall, and PPV + NPV. Results The CNN‐based baseline model achieved a PPV of 0.546 ± 0.058 and an NPV of 0.793 ± 0.047, with area under the curve values ranging from 0.595 to 0.730. The staged extraction framework generated a continuous rule‐based score with discrimination numerically comparable to the CNN‐based model (AUC 0.720 ± 0.045 vs. 0.712 ± 0.054). A stricter threshold, determined from training data, increased PPV at the expense of recall and warrants prospective external validation of this operating point. Conclusions LLM‐based staged extraction demonstrated the potential to achieve binary left‐versus‐right PVC origin localization from 12‐lead ECG images while providing a traceable stepwise diagnostic process. The continuous rule‐based score showed discrimination numerically comparable to the CNN‐based model, and the strict threshold—determined using training data—identified a potential high‐PPV operating point that requires prospective external validation.
Matsumoto et al. (Sat,) conducted a observational in Premature ventricular contraction (PVC) or idiopathic ventricular tachycardia (n=157). LLM-based staged extraction framework for ECG image interpretation vs. CNN-based baseline model was evaluated on Binary left-versus-right PVC origin localization (discrimination/AUC). An LLM-based staged extraction framework achieved comparable discrimination to a CNN-based model for localizing PVC origins from 12-lead ECGs (AUC 0.720 vs. 0.712).