Evaluation of Sleep Quality From Passive Data

No Thumbnail Available

Files

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.
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

2024-09-04

Department

Major/Subject

Data Science

Mcode

SCI3095

Degree programme

Aalto Bachelor’s Programme in Science and Technology

Language

en

Pages

22

Series

Abstract

Sleep quality is a complex phenomenon, made up of various sleep metrics. Studies in the past have used multiple methods to detect these sleep metrics. This study utilizes longitudinal data from the Mobile Monitoring of Mood (MoMoMood) study, to collect data from four groups: healthy users, patients with with bipolar disorder, patients with borderline personality disorder, and patients with major depressive disorder. This thesis aims to investigate how sleep patterns differ across healthy users and patients with varying mood disorders. Additionally, sleep patterns from actigraphy and bed sensor data collection methods were analysed to ensure consistent measurements for a reliable study in sleep quality. Moreover, the thesis used subjective data from surveys to test the hypothesis of whether factors like pet ownership and co-sleeping affected the accuracy of sleep measurement results. Results revealed a noticeable dispersion in the data as the sleep duration measured by the two methods differed significantly for some users. Nevertheless, the control group consistently had shorter nocturnal sleep durations in comparison to the mood disorder groups. The Kruskal-Wallis H-statistic tests, conducted at significance levels of 0.05 for both devices, revealed statistically significant differences between the nocturnal sleep durations among the four user groups (actigraphy: H = 22.101, p-value = 6.214e-05, bed sensor: H = 11.105,p-value = 0.011). Actigraphy data exhibited a stronger significance compared to the bed sensor data, indicating more pronounced variations among the groups. Additionally, independent t-tests at a significance level of 0.05 were conducted to examine the influence of pets and co-sleeping on sleep measurement devices. No significant difference in sleep duration was detected due to the ownership of pets for both devices (Actigraphy: t = -0.518, p-value = 0.604, bed sensor: t = 0.999,p-value = 0.318). However, for co-sleeping, results revealed a significant difference with the bed sensor (t = 1.989, p-value = 0.047), but no significant difference was found with actigraphy (t = 1.632, p-value = 0.103). When measured by a bed sensor, the median sleep duration was slightly higher and the box plot had a broader range for those who sleep alone. Furthermore, the results revealed that on average, the sleep duration measured by the bed sensor is 0.78 hours less than the sleep duration measured by the actigraph for those who sleep alone. The discrepancy in sleep duration from both devices suggests that bed sensors may be more sensitive to subtle disturbances triggered by bed-sharing. This highlights the significance of utilising multiple measurement methods for a comprehensive evaluation of sleep quality. Additionally, the results indicated that the nocturnal sleep distribution for the control group is around 8 hours fromboth measurement methods, which aligns with the NSF’s suggested sleep time duration of 7-9 hours for adults. Moreover, the extended sleep durations within mood disorder groups aligns with findings that suggest an association between hypersomnia and depression, specifically amongst individuals with bipolar disorder. However, there are several limitation to this study. It should be considered that while the Kruskal Wallis test displays a significant overall difference between the groups, it does not account for within-subject variability. Furthermore, the study’s focus on nocturnal sleep limits understanding of broader sleep quality factors affecting participants. The reliance solely on nocturnal duration neglects important metrics such as sleep architecture and wakefulness.

Description

Supervisor

Korpi-Lagg, Maarit

Thesis advisor

Aledavood, Talayeh

Keywords

actigraph, bed sensor, mood disorder, sleep quality, sleep duration

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202411197166

Collections

[kand] Perustieteiden korkeakoulu / SCI