Deep learning applied to polysomnography to predict blood pressure in obstructive sleep apnea and obesity hypoventilation: a proof-of-concept study.

Researchers

Journal

Modalities

Models

Abstract

Nocturnal blood pressure (BP) profile shows characteristic abnormalities in obstructive sleep apnea (OSA), namely acute post-apnea BP surges and non-dipping BP. These abnormal BP profiles provide prognostic clues indicating increased cardiovascular disease (CVD) risk. We developed a deep neural network model to perform computerized analysis of polysomnography data and predict nocturnal BP profile.
We analyzed concurrently performed polysomnography and non-invasive beat-to-beat BP measurement with a deep neural network model to predict nocturnal BP profiles from polysomnography data in thirteen patients with severe obstructive sleep apnea.
A good correlation was noted between measured and predicted post-apnea systolic and diastolic BP (Pearson’s r ≥ 0.75). Moreover, Bland Altman analyses showed good agreement between the two values. Continuous systolic and diastolic BP prediction by the DNN model was also well-correlated with measured BP values (Pearson’s r ≥ 0.83).
We developed a deep neural network model to predict nocturnal BP profile from clinical polysomnography signals and provide a potential prognostic tool in OSA. Validation of the model in larger samples and examination of its utility in predicting CVD risk in future studies is warranted.
© 2020 American Academy of Sleep Medicine.