Phenotype and outcome prediction of depression patients using digital twins

No Thumbnail Available

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Master's thesis

Date

2024-01-22

Department

Major/Subject

Biomedical Engineering

Mcode

SCI3059

Degree programme

Master’s Programme in Life Science Technologies

Language

en

Pages

5+38

Series

Abstract

Depression is a heterogeneous disorder comprising different subtypes that need different treatment approaches. Understanding the relationships between subgroups and associated biomarkers is essential for personalized treatment. Studying brain oscillations to identify biomarkers is promising for facilitating the precision of diagnosis and treatment. However, mapping structural data to functional data is challenging. Computational models that reproduce activity similar to brain signals can show possible relationships through model fitting. Parameters of personalized models can provide additional information on brain oscillations. This work utilizes the parameters of the Hierarchical Kuramoto model to phenotyping and predicting outcomes of patients with depression. The fitted parameters in specific functional subsystems, such as Control, Default, Salience Ventral Attention, and Limbic, correlate with depression severity. In addition, the model parameters can predict the treatment outcomes with an accuracy of 60%.

Description

Supervisor

Palva, Matias

Thesis advisor

Palva, Satu
Myrov, Vladislav

Keywords

depression, phenotyping, prediction, personalization

Other note

Citation