Convolutional neural networks improved HRV analysis accuracy by single-lead Holter

Objective: New artificial intelligence (AI) algorithms are being applied to HRV but there is still needed for more comparison with classical HRV metrics. Convolutional Neural Network (CNN) was used to analyze HRV in four different groups distinguished by body mass index (BMI) and age. Methods: The cohort study enrolled total 265 patients wore an AI single-lead Holter and traditional multi-lead Holter for less than 22 h from March 1, 2023, to December 1, 2024. Indeed, RR-interval sequence as input for the CNN, then linear fitting and Bland–Altman analysis were used to illustrate the statistical results of AI Holter and traditional Holter in four groups: BMI <24 kg/m ² and age <65 years, BMI <24 kg/m ² and age ≥65 years, BMI ≥24 kg/m ² and age <65 years, and BMI ≥24 kg/m ² and age ≥65 years. Results: All groups had acceptable biases and r-values for different HRV parameters. SDANN was the most accurate HRV parameter in all groups, and SDNN, PNN50 also showed better test efficiency in specific groups. Conclusions: The AI single-lead Holter was reliable for HRV detection, and SDANN showed a satisfactory accuracy in all groups, but SDNN and PNN50 showed better test efficiency in specific groups.