EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access

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

Analyse von Mobilitätsindikatoren mit Machine Learning zur Erkennung einer leichten kognitiven Beeinträchtigung: systematisches Scoping-Review

Salamah Alshammari, Munirah Alsubaie, Mathieu Figeys, Adriana Ríos Rincón, Victor Ezeugwu, Shaniff Esmail, Christine Daum, Lili Liu, Antonio Miguel Cruz

Applied Clinical Informatics · 2025-08 · 16 (04) · 974-987

DOI: 10.1055/a-2657-8212 ↗

Auf einen Blick

Ein systematisches Scoping-Review untersuchte technologiegestützte Mobilitätsdaten und Machine-Learning-Algorithmen zur Erkennung von MCI bei Erwachsenen. Wearables waren am häufigsten, Apps am seltensten genutzt.

Fragestellung

Wie werden technologiegestützte Mobilitätsdaten und Machine-Learning-Algorithmen eingesetzt, um MCI bei Erwachsenen zu erkennen?

Methode

Systematisches Scoping-Review; 7 Datenbanken durchsucht; 2.901 Treffer gesichtet; Erwachsene ab 18 Jahren mit MCI.

Ergebnisse

24 Arbeiten erfüllten die Kriterien und berichteten 116 Mobilitätsindikatoren. Am häufigsten waren Wearables; für Gehen war Gehgeschwindigkeit am häufigsten, für Fahren u. a. starkes Bremsen, Nachtfahrten und Geschwindigkeit.

Einschränkungen

Ein deutlicher Forschungsbedarf bestand zu mobilitätsbezogener Überwachung per App.

Schlussfolgerung der Autor:innen

Die Autor:innen heben den Einsatz technologiegestützter Methoden, besonders von Wearables, zur Beurteilung von Mobilität und zur MCI-Erkennung hervor.

Kernaussagen

  • 24 Arbeiten mit 116 Mobilitätsindikatoren
  • Wearables waren die häufigste Datenerhebungsmethode
  • Durchschnittliche Genauigkeit 86,1 %, Sensitivität 84 %, Spezifität 72,8 %

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Scoping Review in der Zeitschrift Applied Clinical Informatics, online erschienen am 03.09.2025. Verfasst von Salamah Alshammari und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada. Hauptthemen laut MEDLINE: Cognitive Dysfunction, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: AGE-WELL Catalyst Funding Program in Healthy Ageing.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cognitive DysfunctionMachine LearningHumans

Autor:innen und Institutionen

  • Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada.
  • Occupational Therapy Program, College of Applied Medical Sciences, King Saud bin Abdulaziz University for Health Sciences, Alahsa, Saudi Arabia.
  • School of Nursing and Midwifery, University of Newcastle, Newcastle, New South Wales, Australia.
  • Department of Physical Therapy, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Alberta, Canada.
  • Faculty of Health, School of Public Health Sciences, University of Waterloo, Waterloo, Ontario, Canada.
  • Glenrose Rehabilitation Research, Innovation and Technology, Glenrose Rehabilitation Hospital, Edmonton, Alberta, Canada.

Förderung

  • AGE-WELL Catalyst Funding Program in Healthy Ageing

Zitieren

APA

Alshammari, S., Alsubaie, M., Figeys, M., Ríos Rincón, A., Ezeugwu, V., Esmail, S., Daum, C., Liu, L., & Miguel Cruz, A. (2025). Analyzing Mobility Indicators Using Machine Learning to Detect Mild Cognitive Impairment: A Systematic Scoping Review. Applied Clinical Informatics, 16(04), 974-987. https://doi.org/10.1055/a-2657-8212

Vancouver

Alshammari S, Alsubaie M, Figeys M, Ríos Rincón A, Ezeugwu V, Esmail S, et al. Analyzing Mobility Indicators Using Machine Learning to Detect Mild Cognitive Impairment: A Systematic Scoping Review. Applied Clinical Informatics. 2025;16(04):974-987. doi:10.1055/a-2657-8212

BibTeX
@article{Alshammari2025,
  author = {Alshammari, Salamah and Alsubaie, Munirah and Figeys, Mathieu and Ríos Rincón, Adriana and Ezeugwu, Victor and Esmail, Shaniff and Daum, Christine and Liu, Lili and Miguel Cruz, Antonio},
  title = {Analyzing Mobility Indicators Using Machine Learning to Detect Mild Cognitive Impairment: A Systematic Scoping Review},
  journal = {Applied Clinical Informatics},
  year = {2025},
  volume = {16},
  number = {04},
  pages = {974--987},
  doi = {10.1055/a-2657-8212}
}
Kostenlos starten →