Project SummarySleep-disordered breathing (SDB) is potential remedial risk factor for hypertension diabetes strokecoronary artery disease and heart failure. The prevalence of SDB is estimated to be between 6.5% and 9%in women and between 17% and 31% in men. During polysomnography which is often required fordiagnosis sleep stages and the frequency of cortical arousals are important metrics. A high frequency ofarousals is indicative of sleep fragmentation. Additionally cortical arousal events are also used to identifyhypopneic events in sleep scoring. Currently type III portable sleep monitors are commonly used fordiagnosing SDB severity instead of more expensive polysomnography. However most portable home sleeptest (HST) monitors do not record electroencephalographic (EEG) data which are required for arousalidentification resulting in an underestimation of SDB severity in manual scoring of SDB events. Thusthere is a critical need to improve portable HST sleep monitors with advanced automatic scoring algorithmsthat can identify arousals associated with SDB events. Studies have found that cortical arousal is associatedwith sympathetic neural surges observed on electrocardiographic (ECG) and blood pressure signals.Additionally changes in respiratory patterns which can be observed from the ECG signal have been foundto be associated with specific EEG patterns. Furthermore different autonomic neural patterns dominate innon-rapid eye movement (NREM) and rapid eye movement (REM) sleep. The RR interval and respiratory-mediated HF components of heart rate variability (HRV) increase from stages N1 to N3. Our hypothesis isthat ECG signals can be used to automatically scoring sleep stages and arousals in HST. In this study weplan to develop a deep learning-based multi-task learning algorithm for automatic arousal and sleep stagescoring. Instead of HRV based algorithms we propose to employ an end-to-end deep learning network toacquire features from the raw ECG data. The proposed model consists of convolutional neural networksrecurrent neural networks and an attention mechanism. It can: (1) accept varying length ECG data; (2)capture long-range dependencies in the ECG data; and (3) share knowledge among scoring tasks for arousaland sleep stages. We use HRVs to further analyze the ECG regions selected by the deep learning model.This is a critical step to understand the underpinnings of associations between sleep events and the ECGsignal discovered by the proposed model. Our specific aims include: (1) developing an end-to-end multitask deep learning model forautomatic arousal and sleep stages scoring by analyzing a modified lead II ECG signal which is commonlyused in sleep studies; (2) advanced interpretation of deep learning model outcomes. Our current effort willevaluate the usability of deep learning approach in sleep medicine and will have a substantive and sustainedimpact on diagnosis outcomes for sleep disorders.