JMIR Publications

ABSTRACT

Background:

Predictive medicine relies on algorithms to determine clinical treatments tailored to each patient’s individual characteristics. Predictive models based on AI have shown promise in identifying Atrial Fibrillation (AF) episodes; however, they rarely focus on short-term dynamic prediction.

Objective:

This study aims to evaluate the use of an AI model and remote monitoring data extracted from pacemaker devices to predict the onset or worsening of arrhythmias in the short term.

Methods:

This was an observational, prospective, multicenter study in which data from 314 patients were analyzed. A total of 65,243 data sequences were collected, of which 55,532 were used to train the algorithm. This model used 31-day records to predict whether the number of arrhythmic episodes increased, decreased, or remained the same in the following 14 days.

Results:

The sensitivity and specificity of the generated predictions were calculated from 9,711 prediction/observation pairs. The global sensitivity was 66.4% and specificity was 77.4%; with a sensitivity of 76.8% and specificity of 39.6% in patients with baseline arrhythmia; and a sensitivity of 39% and a specificity of 81% in patients without baseline arrhythmia. The analysis for the patient subgroup without prior history of AF yielded a 69% sensitivity and an 80% specificity.

Conclusions:

This model was capable of predicting short-term increases or decreases in arrhythmic episodes with reasonable sensitivity and specificity, using data collected through remote monitoring of implantable devices. The model’s performance is expected to improve progressively as more data samples become available, including demographic and clinical records. Clinical Trial: Trial code: IA-Pacing Spain Fundación FFDIS in collaboration with Arrhythmia Network Technology SL.