IIHP: Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea

Abstract

AbstractObstructive sleep apnea (OSA) increases the risk of hypertension, mainly attributed to intermittent hypoxia and sleep fragmentation. Given the multifaceted pathogenesis of hypertension, accurately predicting incident hypertension in individuals with OSA has posed a considerable challenge. In this study, we leveraged Machine Learning (ML) techniques to develop a predictive model for incident hypertension up to five years after OSA diagnosis by polysomnography. We used data from the Sleep Heart Health Study (SHHS), which included 4,797 participants diagnosed with OSA. After excluding those with pre-existing hypertension and Apnea Hypopnea Index (AHI) values below 21 per hour, we had 671 participants with five-year follow-up data. We adopted two distinct methodologies. We first implemented adaptive convolution layers to extract features from the signals and combined them into a 2D array. The 2D array was further processed by a 2D pre-trained neural network to take advantage of transfer learning. Subsequently, we delved into feature extraction from full-length signals across various temporal frames, resulting in a 2D feature array. We studied the use of various 2D networks such as MobileNet, EfficientNet, and a family of RESNETs. The best algorithm achieved an average area under the curve of 72%. These results suggest a promising approach for predicting the risk of incident hypertension in individuals with OSA, providing tools for practice and public health initiatives.