Ke Wang
Graduate Trainee, Duke University
3 active projects
Duplicate of DST_Sleep_Analysis
Scientific Questions Being Studied
NA
Project Purpose(s)
- Population Health
Scientific Approaches
NA
Anticipated Findings
NA
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Controlled TierResearch Team
Owner:
- Ke Wang - Graduate Trainee, Duke University
- Hayoung Jeong - Graduate Trainee, Duke University
DST_Sleep_Analysis
Scientific Questions Being Studied
NA
Project Purpose(s)
- Population Health
Scientific Approaches
NA
Anticipated Findings
NA
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Controlled TierResearch Team
Owner:
- Ke Wang - Graduate Trainee, Duke University
- Hayoung Jeong - Graduate Trainee, Duke University
Sleep EDA
Scientific Questions Being Studied
Current sleep detection algorithms on commercial devices consistently demonstrate low performance when a user has sleep disturbances, irregularities or disorders, abnormal behavioral or living patterns. This lack of generalizability is an obstacle for the translation of sleep digital health tools into healthcare. I have identified two main problems: 1) current consumer wearable sleep algorithms have low specificity, meaning that awakenings or non-wear during the sleep period are often mistakenly treated as sleep, overestimating both sleep time and quality and 2) sleep detection algorithms based on heart rate and accelerometry from consumer wearables fail to detect sleep in groups with abnormal sleep patterns, such as shift workers and pregnant people.
Project Purpose(s)
- Disease Focused Research (Obstructive Sleep Apnea)
- Population Health
Scientific Approaches
Aim 1. Use available open source datasets to address the low specificity of current sleep detection algorithms.
Aim 2. Collect data from certain groups prone to sleep disorders or irregular sleep and improve sleep detection algorithm performances on these groups.
Aim 3. Develop digital biomarkers for common sleep disorders. Using both opensource data and data to be collected, I propose to develop digital biomarkers for sleep disorders, including obstructive sleep apnea, narcolepsy, and restless leg syndrome.
Anticipated Findings
The anticipated findings are the population level sleep disorders and sleep irregularities, and potentially better sleep detection algorithms that work well for socioeconomic minorities.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierYou can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.