PDF icon Download PDF
Appl Clin Inform 2025; 16(04): 974-987
DOI: 10.1055/a-2657-8212
Review Article

Analyzing Mobility Indicators Using Machine Learning to Detect Mild Cognitive Impairment: A Systematic Scoping Review

Salamah Alshammari
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
2   Occupational Therapy Program, College of Applied Medical Sciences, King Saud bin Abdulaziz University for Health Sciences, Alahsa, Saudi Arabia
,
Munirah Alsubaie
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
2   Occupational Therapy Program, College of Applied Medical Sciences, King Saud bin Abdulaziz University for Health Sciences, Alahsa, Saudi Arabia
,
Mathieu Figeys
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
3   School of Nursing and Midwifery, University of Newcastle, Newcastle, New South Wales, Australia
,
Adriana Ríos Rincón
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
,
Victor Ezeugwu
4   Department of Physical Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
,
Shaniff Esmail
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
,
Christine Daum
5   Faculty of Health, School of Public Health Sciences, University of Waterloo, Waterloo, Ontario, Canada
,
Lili Liu
5   Faculty of Health, School of Public Health Sciences, University of Waterloo, Waterloo, Ontario, Canada
,
Antonio Miguel Cruz
1   Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada
5   Faculty of Health, School of Public Health Sciences, University of Waterloo, Waterloo, Ontario, Canada
6   Glenrose Rehabilitation Research, Innovation and Technology, Glenrose Rehabilitation Hospital, Edmonton, Alberta, Canada
› Author Affiliations
Funding This work was supported by the AGE-WELL Catalyst Funding Program in Healthy Ageing (award number: AW-CAT-2023-08).
› Further Information
Also available ateRef
   Permissions and Reprints
Preview

Abstract

Background

The global aging population is rapidly increasing, and the prevalence of age-related cognitive conditions, such as mild cognitive impairment (MCI), is becoming more common. This condition, which represents intermediate stages between normal aging and dementia, underscores the importance of early detection and timely intervention to address the growing demand for health services. Traditional cognitive assessments have limitations, such as the consistency of results, prompting the need for innovative technology-based solutions.

Objective

This study aimed to examine how technology-based mobility data collection methods and machine learning algorithms are used to detect MCI in adults.

Methods

A systematic scoping review was conducted to identify papers that analyzed mobility-related data using machine learning algorithms, focusing on adults aged 18 or older with MCI. Seven databases were searched: MEDLINE, EMBASE, IEEE Xplore, PsycINFO, Scopus, Web of Science, and ACM Digital Library, yielding 2,901 papers.

Results

Twenty-four papers met the inclusion criteria, highlighting 116 mobility indicators used to classify or indicate MCI. Wearable devices were the most common data collection method, with mobile applications being the least utilized. The most frequently reported mobility indicator for walking was walking speed. For driving, indicators included the number of hard braking events, the number of night trips, and speed. Logistic regression, random forest, and neural networks were the most used machine learning algorithms. Overall, the mean accuracy, sensitivity, and specificity of all the algorithms were 86.1% (standard deviation [SD] = 6.7%), 84% (SD = 6.5%), and 72.8% (SD = 12%), respectively. The mean area under the curve and the harmonic mean of precision and recall scores (F1) were 0.77 (SD = 0.08) and 0.83 (SD = 0.16), respectively.

Conclusion

This review highlights the use of technology-based methods, particularly wearable devices, in assessing mobility and applying machine learning algorithms to detect MCI. However, a notable gap in research on mobile app-based mobility monitoring suggests a promising direction for future studies.

Keywords

mobility - machine learning - mild cognitive impairment - wearable device - neural network

Protection of Human and Animal Subjects

This scoping review did not involve direct research with human participants. All data analyzed in this study were obtained from previously published sources. Therefore, ethical approval and informed consent were not required.


Supplementary Material



Publication History

Received: 18 March 2025

Accepted: 16 July 2025

Article published online:
03 September 2025

© 2025. Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany