A5045092930- Circadian rhythm and melatonin
- Non-Invasive Vital Sign Monitoring
- Sleep and Wakefulness Research
- Time Series Analysis and Forecasting
- Sleep and related disorders
- Topological and Geometric Data Analysis
- Heart Rate Variability and Autonomic Control
- Remote Sensing in Agriculture
- Context-Aware Activity Recognition Systems
- Behavioral Health and Interventions
- Electromagnetic Fields and Biological Effects
- Spaceflight effects on biology
- Mental Health Research Topics
- Sleep and Work-Related Fatigue
University of Michigan
2023-2024
Laboratory studies have made unprecedented progress in understanding circadian physiology. Quantifying rhythms outside of laboratory settings is necessary to translate these findings into real-world clinical practice. Wearables been considered promising way measure rhythms. However, their limited validation remains an open problem. One major barrier implementing large-scale the lack reliable and efficient methods for assessment from wearable data. Here, we propose approximation-based...
While circadian disruption is recognized as a potential driver of depression, its real-world impact poorly understood. A critical step to addressing this the noninvasive collection physiological time-series data outside laboratory settings in large populations. Digital tools offer promise endeavor. Here, using wearable data, we first quantify degrees disruption, both between different internal rhythms and each rhythm sleep-wake cycle. Our analysis, based on over 50,000 days from 800...
.The circadian clock is an internal timer that coordinates the daily rhythms of behavior and physiology, including sleep hormone secretion. Accurately tracking state clock, or phase, holds immense potential for precision medicine. Wearable devices present opportunity to estimate phase in real world, as they can noninvasively monitor various physiological outputs influenced by clock. However, accurately estimating from wearable data remains challenging, primarily due lack methods integrate...
Wearable devices have become commonplace tools for tracking behavioral and physiological parameters in real-world settings. Nonetheless, the practical utility of these data clinical research applications, such as sleep analysis, is hindered by their noisy, large-scale, multidimensional characteristics. Here, we develop a neural network algorithm that predicts stages topological features (TFs) wearable model-driven clock proxies (CPs) reflecting circadian propensity sleep. To evaluate its...
Summary The accurate estimation of circadian phase in the real‐world has a variety applications, including chronotherapeutic drug delivery, reduction fatigue, and optimal jet lag or shift work scheduling. Recent developed adapted algorithms to predict time‐consuming costly laboratory measurements using mathematical models with actigraphy other wearable data. Here, we validate extend these results home‐based cohort later‐life adults, ranging age from 58 86 years. Analysis this population...
Sleep is a critical component of health and well-being but collecting analyzing accurate longitudinal sleep data can be challenging, especially outside laboratory settings. We propose simple neural network model titled SOMNI (Sleep restOration using Machine learning Non-negative matrix factorIzation [NMF]) for imputing missing rest-activity from actigraphy, which enable clinicians to better handle monitor sleep-wake cycles individuals with highly irregular patterns. The consists two hidden...
Abstract Wearable devices have become commonplace tools for tracking behavioral and physiological parameters in real-world settings. Nonetheless, the practical utility of these data clinical research applications, such as sleep analysis, is hindered by their noisy, large-scale, multidimensional characteristics. Here, we develop a neural network algorithm that predicts stages topological features (TFs) wearable model-driven clock proxies reflecting circadian propensity sleep. To evaluate its...
The circadian clock is an internal timer that coordinates the daily rhythms of behavior and physiology, including sleep hormone secretion. Accurately tracking state clock, or phase, holds immense potential for precision medicine. Wearable devices present opportunity to estimate phase in real world, as they can non-invasively monitor various physiological outputs influenced by clock. However, accurately estimating from wearable data remains challenging, primarily due lack methods integrate...