Exploring behavioral patterns of patients with mental disorders using the MoMo-Mood dataset

Thumbnail Image

Files

master_Ziaei_Bideh_Amirmohammad_2022.pdf (4.44 MB)

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2022-08-22

Department

Major/Subject

Complex Systems

Mcode

SCI3060

Degree programme

Master’s Programme in Life Science Technologies

Language

en

Pages

56+1

Series

Abstract

Mental disorders are major problems for people’s wellbeing in societies due to the increasing the amount of stress and challenges of living in modern cities. Understanding these disorders and diagnosing them in a timely manner is crucial for people to enjoy satisfactory life quality and to function well in society. Previous studies on diagnosing mental disorders and their development over time rely on questionnaires filled by patients and visiting clinicians on a regular basis. For instance, clinicians employ The Standard for Clinicians’ Interview in Psychiatry (SCIP) to interview adult patients and diagnose a psychiatric disorder based on their answers. In recent years, technological advancements and the fact that people are using technologies like mobile phones in their daily lives provide us new opportunities for having a more realistic image of mental disorders. However, since smartphones and digital tools have emerged only recently, their application in the mental health context calls for extensive research. The overall objective of this study is to find interpretable behavioral markers of psychiatric disorders and depressed moods in patients, using digital wearables. More specifically, this work attempts to find differences in disorder and mood levels between healthy controls and patients using features extracted from the data, their correlations, social signature, and daily rhythm analysis. To this end, this study employs the MoMo- Mood dataset, a dataset containing the digital data and mood scores (PHQ9) of 164 individuals categorized into healthy control; major depressive disorder; borderline personality disorder; and bipolar disorder. The results suggest that depressed moods are associated with a smaller but closer social network as well as higher time spent at home and reduced physical activity and variance in the movement.

Description

Supervisor

Aledavood, Talayeh

Thesis advisor

Aledavood, Talayeh

Keywords

mental health, digital phenotyping, depression, statistical methods, behavioral marker

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202208285082

Collections

[dipl] Perustieteiden korkeakoulu / SCI