The diagnostic efficiency of artificial intelligence based 2 hours Holter monitoring in premature ventricular and supraventricular contractions detection
Qiong Huang, Yuansheng Fan, Jialin Wang, Zhiyang Xu, Linfeng Yang, Junhong Wang, Yiyang Zhan, Xiangqing Kong, Ningtian Zhou
Abstract
BACKGROUND: Electrocardiography (ECG) and 24 hours Holter monitoring (24 h-Holter) provided valuable information for premature ventricular and supraventricular contractions (PVC and PSVC). Currently, artificial intelligence (AI) based 2 hours single-lead Holter (2 h-Holter) monitoring may provide an improved strategy for PSVC/PVC diagnosis. HYPOTHESIS: AI combined with single-lead Holter monitoring improves PSVC/PVC detection. METHODS: In total, 170 patients were enrolled between August 2022 and 2023. All patients wore both devices simultaneously; then, we compared diagnostic efficiency, including the sensitivity/specificity/positive predictive-value (PPV) and negative predictive-value (NPV) in detecting PSVC/PVC by 24 h-Holter and 2 h-Holter. RESULTS: The PPV and NPV in patients underwent 2 h-Holter were 76.00%/87.50% and 96.35%/98.55, respectively, and the sensitivity and specificity were 79.17%/91.30%, and 95.65%/97.84% in PSVC/PVC detection compared with 24 h-Holter. The areas under the ROC curves (AUCs) for PSVC and PVC were 0.885 and 0.741, respectively (p < .0001). CONCLUSIONS: The potential advantages of the 2 h-Holter were shortened wearing period, improved convenience, and excellent consistency of diagnosis.