Document text
Principal Investigator: Victor Borza
Organization: VANDERBILT UNIVERSITY
Fiscal Year: 2024
Award: $34,164
Funding agency: National Heart Lung and Blood Institute
PROJECT SUMMARY
Obstructive sleep apnea (OSA) is a sleep-related breathing disorder associated with major co-morbidities and is
estimated to affect nearly one billion people worldwide. Moreover, there are differences in prevalence, diagnosis
rates, and co-morbid outcomes for OSA based on the demographics of a patient, such as age, race, and gender.
The diversity of the clinical manifestations, objective measurements, and outcomes – the phenotype – of OSA
underscores the opportunity for predictive models to improve care of patients with OSA. Predicting future (i.e. 5-
year post-diagnosis) risks of OSA co-morbid outcomes and predicting how different treatments for OSA affect
these risks can help clinicians and patients choose the best treatment strategies.
Current OSA outcomes research has key limitations. Prior studies have characterized groups of OSA patients
that exhibit similar characteristics, referred to as sub-phenotypes of OSA. However, these studies have been
limited by analyzing relatively few variables obtainable from questionnaires. To address this limitation, we will
use rich longitudinal electronic medical records (EMR) data to characterize OSA sub-phenotypes and to predict
OSA outcome risks for individual patients. To extract insights from EMR data, we will leverage modern
computational methods based in machine learning (ML). A second major limitation of existing OSA research is
worse predictive model performance for some groups. Model biases have real-world negative implications. The
ubiquitous STOP-BANG questionnaire used to screen patients for further OSA testing performs worse for women
and Asian individuals, leading to potential delayed, under-, or misdiagnosis of OSA in these groups. To address
this limitation, this proposed project will assess and mitigate biases present in our predictive models.
To better understand patient factors associated with OSA outcomes, this project has two aims. In Aim 1
clustering methods will be applied to identify groups of OSA patients who share similar sub-phenotypes
according to combinations of clinical features and objective measurements present in EMR data. Then, sub-
phenotypes will be compared by the rates at which they exhibit different OSA outcomes, providing intuition into
potential underlying pathophysiologic differences. In Aim 2, ML classifiers will be applied to build and validate
algorithmically fair predictive models for future OSA outcome risks as well as effects of OSA treatments. Patient-
specific factors that are consistently associated with differences in OSA outcome risks through Aims 1 and 2 will
provide both personalized insights into treatment options and stronger evidence of underlying pathophysiology
worthy of further investigation.
Terms: <Accounting><Acute><Address><Affect><Age><Algorithms><Amentia><Asian group><Asian individual><Asian people><Asian population><Asians><Automobile collision><Automobile crash><COVID-19><CPAP><CPAP Ventilation><CV-19><Car collision><Car crash><Cardiovascular Diseases><Characteristics><Chronic><Classification><Clinical><Clinical Data><Computer Models><Computerized Medical Record><Computerized Models><Computing Methodologies><Continuous Positive Airway Pressure><Coronavirus Infectious Disease 2019><Data><Data Set><Dementia><Diabetic Kidney Disease><Diabetic Nephropathy><Diagnosis><Disease><Disorder><Disparities><Disparity><Drowsy Driving><Dysfunction><Electronic Medical Record><Ethnic Origin><Ethnicity><Exhibits><Foundations><Functional disorder><Future><Gender><Geographic Area><Geographic Locations><Geographic Region><Geographical Location><Grant><Individual><Intervention><Intervention Strategies><Intuition><Investigation><Machine Learning><Measurement><Metabolic syndrome><Methods><Modeling><Modernization><Motor vehicle collision><Motor vehicle crash><Obstructive Sleep Apnea><Operative Procedures><Operative Surgical Procedures><Outcome><Outcomes Research><Patient Care><Patient Care Delivery><Patient Compliance><Patients><Pattern><Performance><Persons><Phenotype><Physicians><Physiopathology><Population><Predicting Risk><Prevalence><Process><Questionnaires><Race><Races><Recommendation><Research><Research Ethics><Research Resources><Resources><Risk><Severities><Sleep Apnea><Sleep Apnea Syndromes><Sleep Hypopnea><Sleep-Disordered Breathing><Socio-economic status><Socioeconomic Status><Subgroup><Surgical><Surgical Interventions><Surgical Procedure><Symptoms><Syndrome, Sleep Apnea, Obstructive><Systematics><Testing><Time><Translating><Vehicle crash><Vehicular collision><Vehicular crash><Woman><ages><benefit sharing><cardiovascular disorder><care for patients><care of patients><career><caring for patients><clinical practice><clinically actionable><co-morbid><co-morbidity><comorbidity><computational methodology><computational methods><computational modeling><computational models><computer based method><computer based models><computer based prediction><computer methods><computerized modeling><computing method><coronavirus disease 2019><coronavirus disease-19><coronavirus infectious disease-19><demographics><disparate effect><disparate impact><disparate result><forecasting risk><geographic site><improved><individual patient><inequitable effect><inequitable impact><inequitable outcome><insight><interventional strategy><intuitive><machine based learning><machine learning based classifier><machine learning based prediction model><machine learning based predictive model><machine learning classifier><machine learning prediction><machine learning prediction model><model building><neuropsychiatric disease><neuropsychiatric disorder><outcome disparities><outcome inequality><outcome inequity><pathophysiology><patient adherence><patient cooperation><patient screening><predict risk><predict risks><predicted risk><predicted risks><predicting risks><predictive modeling><predictive risk><predicts risk><racial><racial background><racial origin><response to therapy><response to treatment><risk prediction><risk predictions><skills><sleep-related breathing disorder><socio-economic position><socioeconomic position><surgery><therapeutic response><therapy response><traffic collision><traffic crash><treatment effect><treatment guidelines><treatment response><treatment responsiveness><treatment strategy><unequal effect><unequal impact><unequal outcome>