Machine Learning Model Using Heart Rate Variability for the Prediction of Vasovagal Syncope

Abstract

Vasovagal syncope is a reversible condition that can cause serious events, such as cerebral hemorrhage. Predicting its occurrence is challenging; thus, this study aimed to develop machine learning models that use heart rate variability to predict the occurrence of vasovagal syncope episodes. We investigated 80 patients experiencing syncope who underwent Holter monitoring during the head-up tilt test. Twenty-six machine learning models were examined for the prediction of vasovagal syncope using heart rate variability parameters. We randomly split the subjects into training and testing sets at a 7:3 ratio (training set: 46 positive and 9 negative subjects; testing set: 21 positive and 4 negative subjects). The XGB classifier achieved the highest performance compared with that of the other algorithms (accuracy, 0.72; area under the curve, 0.801; sensitivity, 0.857; specificity, 0.621). When examining the time taken to predict syncope occurrence using the developed prediction model, it was found that the model could forecast an episode approximately 3 min (equivalent to 193.2 beats) prior to the onset of symptoms. The machine learning model, which utilized heart rate variability parameters, was proficient in preemptively predicting vasovagal syncope incidents. In practical applications, this approach may help prevent unexpected events by leveraging the heart rate variability to predict vasovagal syncope.

Keywords

• Head-up tilt test
• heart rate variability
• machine learning
• prediction algorithm
• vasovagal syncope