Development and validation of an ECG-based nomogram for early diagnosis of dilated cardiomyopathy.

Abstract

Objective: To develop a nomogram based on electrocardiogram (ECG) parameters to predict the early diagnosis of dilated cardiomyopathy (DCM), enhancing diagnostic accuracy and enabling earlier clinical intervention.

Methods: A retrospective analysis was conducted on ECG data from 168 DCM patients and 130 healthy controls (N-DCM), diagnosed between October 2022 and August 2024. Lasso regression identified 11 significant ECG features (e.g., QTc interval, PR interval, QRS duration), and a nomogram model was constructed. Model performance was evaluated using ROC curves, calibration curves, decision curves, and clinical utility curves.

Results: Significant differences in ECG parameters were observed between DCM and N-DCM groups, with DCM patients showing elevated values across multiple parameters. The nomogram demonstrated high predictive accuracy, achieving an AUC of 0.928 in the training group and 0.862 in the validation group. Calibration and decision curve analyses confirmed good calibration and clinical utility.

Conclusion: The ECG-based nomogram provides an effective tool for early DCM diagnosis, with strong predictive accuracy and clinical benefits. It shows promising applicability for large-scale screenings, contributing to earlier detection and improved patient outcomes.