Document text
Principal Investigator: Oguz Akbilgic
Organization: UNIVERSITY OF WASHINGTON
Fiscal Year: 2024
Award: $92,786
Funding agency: National Heart Lung and Blood Institute
Project Summary
Atrial fibrillation (AF) is the most common cardiac arrhythmia responsible for significant morbidity and mortality
burden. Obstructive sleep apnea (OSA) is a common sleep disorder but disproportionately more common in
patients with AF. OSA has been proposed as a risk for AF. However, clarifying the association between the
OSA and AF has been challenging due to many commonly shared risk factors such as obesity. No studies
have demonstrated whether information about OSA improves prediction of future risk of AF. In particular,
identifying who “among those with OSA” would be at risk for AF is unclear. Better identification of the group
most vulnerable to developing AF among those with OSA will inform clinicians and patients of critical
information needed for therapeutic decision making. One major challenge in OSA evaluation is that
conventional metrics used in the evaluation, such as the apnea hypopnea index (AHI) do not adequately
capture downstream cardiovascular (CV) responses. We and others have identified promising physiologically-
driven polysomnography (PSG) markers that better capture the severity of OSA and improve CV risk
stratification. Specifically related to AF, our preliminary study shows that heart rate response (HRR) to OSA
events, but not AHI, is associated with incident AF in community dwelling elderly men. Electrocardiography
(ECG) is a readily available diagnostic tool that captures electrical activity of the heart. Deep learning (DL) has
shown great promise in detection and risk prediction of various clinical outcomes including AF from `awake'
ECGs alone. `Sleep' ECG is affected by sleep state, respiration and particularly by pathological respiration
such as OSA events. Based on this, we propose Aim 1: To evaluate whether novel HRR-based OSA metrics
improves risk prediction of AF beyond the current AF risk prediction model. We will use a combined
prospective cohort of Atherosclerosis Risk in Communities Study (ARIC)-Sleep Heart Health Study (SHHS),
Cardiovascular Health Study (CHS)-SHHS and Multi-Ethnic Study of Atherosclerosis (MESA) (N~5000, AF
events~800). Aim 2: To develop and test the DL model using an awake ECG (10 sec 12 lead) and sleep ECG
(single lead) to predict a new onset AF in general population “with OSA”. We will develop a convolutional
neural network (CNN) model utilizing ARIC + CHS cohorts (combined N with OSA~1500, AF events ~400) and
externally validate in MESA cohort (OSA~1000, AF events ~100). The performance will be compared with the
CHARGE-AF risk prediction model. Aim 3: Same as Aim 2 except it will be the DL model in prediction of new
onset AF patients with OSA in clinical practice. Building upon the CNN model from Aim 2, we will develop a
separate CNN model using clinical ECG data from a single academic medical center (N= 2000, AF~200) that
may be more relevant in real world clinical practice. 50% of the dataset will be used for training and 50% for
validation. The findings of this study will provide critical information about the future application of DL in
improving CV risk stratification of people with OSA.
Terms: <Ablation><Academic Medical Centers><Affect><Anticoagulation><Apnea><Arrhythmia><Atherosclerosis Risk in Communities><Atrial><Atrial Fibrillation><Auricular Fibrillation><Cardiac Arrhythmia><Cardiac Atrium><Cardiac Chronotropism><Cardiac health><Cardiovascular><Cardiovascular Body System><Cardiovascular Organ System><Cardiovascular system><Cell Communication and Signaling><Cell Signaling><Characteristics><Clinical><Clinical Data><Clinical Trials><Cohort Studies><Communities><Concurrent Studies><Connectionist Models><ConvNet><Data><Data Set><Decision Making><Detection><Development><ECG><EKG><Elderly man><Electrocardiogram><Electrocardiography><Electrophysiology><Electrophysiology (science)><Evaluation><Event><Future><General Population><General Public><Heart><Heart Arrhythmias><Heart Atrium><Heart Rate><Heart Vascular><Heart health><Hypertension><Individual><Intracellular Communication and Signaling><Ischemic Stroke><Lead><Link><Maps><Mechanics><Morbidity><Morbidity - disease rate><Multi-Ethnic Study of Atherosclerosis><Neural Network Models><Neural Network Simulation><Neurophysiology / Electrophysiology><Obesity><Obstructive Sleep Apnea><Oral><Outcome><Pathologic><Patients><Pattern><Pb element><Perceptrons><Performance><Personalized medical approach><Persons><Physiologic><Physiological><Polysomnography><Population><Predicting Risk><Predictive Value><Predisposition><Property><Prospective cohort><Recurrence><Recurrent><Respiration><Risk><Risk Assessment><Risk Factors><Severities><Signal Transduction><Signal Transduction Systems><Signaling><Sleep><Sleep Apnea><Sleep Apnea Syndromes><Sleep Disorders><Sleep Hypopnea><Sleep Monitoring><Sleep-Disordered Breathing><Somnography><Stretching><Susceptibility><Syndrome, Sleep Apnea, Obstructive><Testing><Therapeutic><Training><United States><Universities><University Medical Centers><Validation><Vascular Hypertensive Disease><Vascular Hypertensive Disorder><Virginia><adiposity><atrium><awake><biological signal transduction><cardiac electrical activity><cardiovascular health><cardiovascular risk><cardiovascular risk factor><circulatory system><clinical practice><cohort><computer based prediction><convolutional network><convolutional neural nets><convolutional neural network><corpulence><deep learning><deep learning based model><deep learning method><deep learning model><deep learning strategy><design><designing><developmental><diagnostic tool><efficacy testing><electrophysiological><forecasting risk><heart electrical activity><heavy metal Pb><heavy metal lead><high blood pressure><hyperpiesia><hyperpiesis><hypertensive disease><hypertensive disorder><improved><improvement on sleep><indexing><individualized approach><malleable risk><mechanic><mechanical><modifiable risk><mortality><new marker><novel><novel biomarker><novel marker><personalized approach><polysomnographic><precision approach><predict risk><predict risks><predicted risk><predicted risks><predicting risks><predictive modeling><predictive risk><predicts risk><prevent><preventing><respiratory mechanism><response><risk prediction><risk prediction algorithm><risk prediction model><risk predictions><risk sharing><risk stratification><screening><screenings><sleep diseases><sleep dysfunction><sleep illness><sleep improvement><sleep measurement><sleep polysomnography><sleep problem><sleep-related breathing disorder><stratify risk><tailored approach><validations>