University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Predicting Depression and Sleep Disturbances from Circadian Rhythm Biomarkers with Machine Learning
Overmars, Nikki (2025) Predicting Depression and Sleep Disturbances from Circadian Rhythm Biomarkers with Machine Learning.
|
PDF
6MB |
| Abstract: | This study investigated the association between circadian rhythm disruptions and depression among young adults in the United States, while also validating those disruptions with sleep disturbances. Objective circadian rhythm features were derived from 4-7 days of accelerometer data, with a daily wear time of more than 16 hours, collected from 392 participants. These features included the Relative Amplitude, Intradaily Variability, Interdaily Stability, Midline Estimated Statistic Of Rhythm, amplitude, and the acrophase. Participants were classified as experiencing heightened depressive symptoms or experiencing sleep disturbances via self-reported questionnaires. Multiple classification models were used to predict depression and sleep disturbances. The models were compared on several performance metrics. Removing equivocal zones improved metrics for all models. Plots of variable importance showed that the circadian rhythm features contributed minimally to both outcome predictions. No significant differences were found in circadian rhythm features between the depression group and the healthy controls; thus, no clear association was found between circadian rhythm disruptions and depression. Besides some significant differences in circadian rhythm features between the sleep disturbances group and the healthy controls, no other clear association was found between circadian rhythm disruptions and sleep disturbances. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 42 biology, 54 computer science, 77 psychology |
| Programme: | Biomedical Technology BSc (56226) |
| Link to this item: | https://purl.utwente.nl/essays/107615 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page