Leveraging Polysomnographic Physiological Signals for Improved Cardiovascular Risk Stratification in Obstructive Sleep Apnea
2018 Strategic Research Grant
Diego Mazzotti, PhD
University of Kansas
Key Project Outcome
Obstructive sleep apnea (OSA) affects almost a billion people worldwide. One of the consequences of this sleep disorder is an increased cardiovascular risk, especially in most severe cases. In this study, we looked at different physiological signals that are commonly measured in a sleep study to understand their relative contribution in predicting cardiovascular diseases in the Sleep Heart Health Study. We found that adding novel physiological information did not improve cardiovascular risk prediction when compared to conventional cardiovascular risk factors. However, we also found that certain physiological signals are important to the cardiovascular risk prediction, and these should be investigated further. For example, some measures include known respiratory event and oxygen desaturation indices, as well as spindle characteristics not previously described. We are now investigating what is the effect of these measures on cardiovascular risk, when controlling for the conventional risk factors. We are also investigating whether physiological subtypes of patients with OSA can be identified using signals from sleep studies and, if they exist, whether they are useful to inform cardiovascular risk.
During the development of this grant, we were able to contribute to the better understanding of why some people with OSA are at increased cardiovascular risk. We identified that symptom presentation is a very important contributor, particularly in patients with moderate and severe disease (Mazzotti et al., 2019, AJRCCM). We also learned that certain analytical methods such as supervised and unsupervised machine learning can be used to understand the heterogeneity of the disease. Finally, we propose that while using a comprehensive set of physiological markers did not improve cardiovascular risk prediction, our study highlighted potentially novel physiological biomarkers that deserve future investigation. This will be focus of future studies by our group.
Is the Epworth Sleepiness Scale Sufficient to Identify the Excessively Sleepy Subtype of OSA?
Sleep Medicine Reviews
Landscape of biomedical informatics standards and terminologies for clinical sleep medicine research: A systematic review
Journal of Sleep Research
Diabetes and cardiovascular diseases are associated with the worsening of intermittent hypoxemia
Sex differences within symptom subtypes of mild obstructive sleep apnea
Characteristics and reproducibility of novel sleep EEG biomarkers and their variation with sleep apnea and insomnia in a large community-based cohort
Frontiers in Neuroscience
Longer and Deeper Desaturations Are Associated With the Worsening of Mild Sleep Apnea: The Sleep Heart Health Study
American Journal of Respiratory and Critical Care Medicine
Opportunities for Cardiovascular Benefits in Treating Obstructive Sleep Apnea in the Secondary Prevention Scenario
BMC Medical Genomics
Characterization of genetic and phenotypic heterogeneity of obstructive sleep apnea using electronic health records
Sleep Medicine Reviews
Reinventing polysomnography in the age of precision medicine