https://www.mdu.se/

mdu.sePublications
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
EARLY DETECTION OF ALZHEIMER’S DISEASE USING MOTION DATA
Mälardalen University, School of Innovation, Design and Engineering.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Alzheimer’s disease (AD) is a neurodegenerative disease that causes a decrease in cognitive and motor skills. Early diagnosis of the disease helps reduce the financial burden and facilitate care. Researchers are increasingly exploring machine learning techniques for the early detection of AD. Existing diagnostic methods which are often costly and invasive, create a need for accessible, non-invasive screening approaches. This study investigates the feasibility of using motion data collected from a handheld smart ball device, PALLO, to distinguish between healthy individuals and those diagnosed with AD. Ten participants (6 healthy, 4 with AD) performed three types of movement tasks: walking, hand-raising, and memory-based movement in a controlled environment. Two machine learning approaches were implemented: a hybrid Convolutional Neural Network Long Short-Term Memory (hybrid CNN- LSTM) and a feature-based machine learning model (random forest classifier, gradient boosting, logistic regression, and support vector machine). The CNN–LSTM achieved the best classification performance, with 96% accuracy and an F1 score of 0.97. Among feature-based models, gradient boosting achieved the highest accuracy of 81%. Both approaches were more effective at classifying AD participants than healthy controls. Despite the small dataset, these findings demonstrate the potential of motion-sensor data combined with machine learning techniques for early AD screening. The proposed approach is simple, non-invasive, and could be extended to real-world settings or adapted for other conditions affecting motor function.

Place, publisher, year, edition, pages
2025. , p. 65
Keywords [en]
Early Alzheimer's Detection, Motion Data, Movement Data, Machine Learning, Deep Learning, LOSO-CV
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-73545OAI: oai:DiVA.org:mdh-73545DiVA, id: diva2:2004302
External cooperation
Ai2Ai Oy, Turku, Finland
Subject / course
Computer Science
Supervisors
Examiners
Available from: 2025-10-08 Created: 2025-10-07 Last updated: 2025-10-10Bibliographically approved

Open Access in DiVA

fulltext(33597 kB)56 downloads
File information
File name FULLTEXT01.pdfFile size 33597 kBChecksum SHA-512
9b88f5e503d2ef0d9dafbb812af1c6ece4a1972f766ffd7eef1a7f299ca2e4e24ea85994ef847f40ee4523898a55ee0afc81c9b01a0868542b3eab70090475f9
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Dhakal, Puja
By organisation
School of Innovation, Design and Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 954 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf