Heart rate variability-based Model for estimating the severity of orthostatic hypotension in patients with REM sleep behavior disorder

Background: Orthostatic hypotension (OH) is a typical autonomic dysfunction in patients with idiopathic REM sleep behavior disorder (iRBD). The Schellong test is a well-known method to evaluate the presence of OH; however, it is burdensome for both patients and the medical staff from the viewpoint of ensuring patient safety. In this study, we developed a machine learning (ML) model to discriminate the presence or absence of OH based on heart rate variability (HRV) in the supine position. Methods: We recruited elderly healthy participants (HC) and iRBD patients and measured participants’ R-R interval (RRI) during the Schellong test. The HRV features were calculated from the RRIs and were used as inputs for the ML model. We trained an ML model that combines two binary classifiers. The first model classifies HC and iRBD, and the second model discriminates the classified patients with iRBD between OH(-) and OH(+). Results: The macro average classification performance was accuracy of 81%, recall of 73%, precision of 82%, and F-measure of 68%. In addition, the sensitivity for OH(+)iRBD was 100%. Conclusion: Utilizing this ML model will help to reduce the burden of the Schellong test.