Dümmer, Lisa (2020) From Brain Age toward Brain Health Data-driven approach to predicting cognitive performance from sleep EEG. thesis, Medicine.
Full text available on request.Abstract
Healthy ageing is associated with decline in several domains, including cognitive performance, often leading to multimorbidity and frailty. The changes that the human brain undergoes with age are reflected in the nature of the brain’s activity during sleep. These changes are observable using overnight sleep EEG. These changes can be summarized via the "brain age index” (BAI), which compares a model-predicted “brain age” (BA) to chronological age (CA) to indicate the degree of deviation from normal aging(1). In this study, we examine the degree to which BAI can be explained by cognitive performance. We also investigate whether cognitive performance can be directly predicted using brain activity from an overnight sleep EEG, using LASSO regression to propose a series of new model which we call the “brain health index” (BHI). Our study includes 150 patients who underwent an overnight sleep EEG and underwent a battery of cognitive tests. We found that BAI is correlated with crystallized cognition, but not highly correlated with fluid cognition. BHI shows significant correlations with multiple cognitive variables. In summary, cognition is predictable using features derived from an overnight sleep EEG. Our results suggest that overnight sleep EEG holds promise to provide easily accessible biomarkers of brain health.
| Item Type: | Thesis (UNSPECIFIED) |
|---|---|
| Supervisor name: | Westover, MD, PhD, Prof. dr. M.B and van Putten, MD, PhD, Prof. dr. ir. M.J.A.M. |
| Faculty: | Medical Sciences |
| Date Deposited: | 15 Sep 2023 11:43 |
| Last Modified: | 15 Sep 2023 11:43 |
| URI: | https://umcg.studenttheses.ub.rug.nl/id/eprint/3684 |
Actions (login required)
 |
View Item |