AI + Sleep Health

AI + Sleep Health

 

AI for Predicting Sleep and Mental Health Problems

Joshua J Gooley, Neuroscience and Behavioural Disorders
Enrico Petretto, Centre for Computational Biology (CCB) 

Healthy sleep is important for students’ learning performance and wellbeing. Sleep problems often emerge during adolescence and early adulthood and may contribute to the onset of depression. Hence, early treatment of sleep problems may help to decrease the incidence of depressive disorders. In this project, we seek to identify early markers of poor sleep health that can be used to identify individuals at risk of depression. We will use data from surveys, wearables, and digital traces to predict students’ wellbeing and academic performance. We envisage that AI-guided classification of sleep and diurnal activity phenotypes can be used to identify at-risk students in whom early intervention may prevent mental health problems and academic difficulties.
for Enrico website - dark border

[1] Yeo, S.C. et al. Early morning university classes are associated with impaired sleep and academic performances. Nat Hum Behav. 2023;7(4):502-514. https://doi.org/10.1038/s41562-023-01531-x
[2] Yeo, S.C. et al. University students’ diurnal learning-directed behaviour is strongly influenced by school start times with implications for grades. Sleep. 2023;46(7):zsad141. https://doi.org/10.1093/sleep/zsad141
[3] Loke, Y.M. et al. Development and testing of the Sleep Health And Wellness Questionnaire (SHAWQ) in adolescents and university students: composite SHAWQ scores are associated with sleep problems, depression symptoms, and academic performance. Front Sleep. 2023;2:1188424. https://doi.org/10.3389/frsle.2023.1188424

Browser not supported

Modern websites need modern browsers

To enjoy the full experience, please upgrade your browser

Try this browser