Developing an accessible dementia assessment tool: Leveraging a residual network, the trail making test, and demographic data.

Journal: Journal of Alzheimer's disease : JAD
Published Date: Jul 17, 2025

Abstract

BackgroundThe global burden of Alzheimer's disease and related dementias is rapidly increasing, particularly in low- and middle-income countries where access to specialized healthcare is limited. Neuropsychological tests are essential diagnostic tools, but their administration requires trained professionals, creating screening barriers. Automated computational assessment presents a cost-effective solution for global dementia screening.ObjectiveTo develop and validate an artificial intelligence-based screening tool using the Trail Making Test (TMT), demographic information, completion times, and drawing analysis for enhanced dementia detection.MethodsWe developed: (1) non-image models using demographics and TMT completion times, (2) image-only models, and (3) fusion models. Models were trained and validated on data from the Framingham Heart Study (FHS) ( = 1252), the Long Life Family Study (LLFS) ( = 1613), and the combined cohort ( = 2865).ResultsOur models, integrating TMT drawings, demographics, and completion times, excelled in distinguishing dementia from normal cognition. In the LLFS cohort, we achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 9862%, with sensitivity/specificity of 8769%/9826%. In the FHS cohort, we obtained an AUC of 9651%, with sensitivity/specificity of 8500%/9675%.ConclusionsOur method demonstrated superior performance compared to traditional approaches using age and TMT completion time. Adding images captures subtler nuances from the TMT drawing that traditional methods miss. Integrating the TMT drawing into cognitive assessments enables effective dementia screening. Future studies could aim to expand data collection to include more diverse cohorts, particularly from less-resourced regions.

Authors

  • Jingmei Yang
    Division of System EngineeringBoston University Boston MA 02246 USA.
  • Samad Amini
    Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, MA, USA.
  • Boran Hao
    Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, MA, USA.
  • Seho Park
    Department of Industrial and Data Engineering, Hongik University, Seoul, South Korea.
  • Cody Karjadi
    Framingham Heart Study, Boston University, Boston, MA, USA.
  • Lance San Souci
    Department of Medicine, Chobanian & Avedisian School of Medicine, Boston University, Boston, MA, USA.
  • Vijaya B Kolachalama
    1Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA 02118 USA.
  • Stephanie Cosentino
    Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA.
  • Stacy L Andersen
    Department of Medicine, Chobanian & Avedisian School of Medicine, Boston University, Boston, MA, USA.
  • Rhoda Au
    Boston University School of Medicine, rhodaau@bu.edu.
  • Ioannis Ch Paschalidis
    Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, MA, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals