Everyday Driving and Plasma Biomarkers in Alzheimer's Disease: Leveraging Artificial Intelligence to Expand Our Diagnostic Toolkit

Authors

Sayeh Bayat, Department of Biomedical Engineering, University of Calgary, Calgary, Canada.
Catherine M. Roe, Roe Consulting LLC, St. Louis, MO, USA.
Suzanne Schindler, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
Samantha A. Murphy, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
Jason M. Doherty, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
Ann M. Johnson, Center for Clinical Studies, Washington University School of Medicine, St. Louis, MO, USA.
Alexis Walker, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
Beau M. Ances, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
John C. Morris, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.
Ganesh M. Babulal, Department of Neurology, Washington University School of Medicine, St. Louis, MO, USA.

Document Type

Journal Article

Publication Date

3-13-2023

Journal

Journal of Alzheimer's disease : JAD

DOI

10.3233/JAD-221268

Keywords

Alzheimer’s disease; amyloid; artificial intelligence; naturalistic; plasma biomarkers

Abstract

BACKGROUND: Driving behavior as a digital behavior marker and recent developments in blood-based biomarkers show promise as a widespread solution for the early identification of Alzheimer's disease (AD). OBJECTIVE: This study used artificial intelligence methods to evaluate the association between naturalistic driving behavior and blood-based biomarkers of AD. METHODS: We employed an artificial neural network (ANN) to examine the relationship between everyday driving behavior and plasma biomarker of AD. The primary outcome was plasma Aβ 42/Aβ 40, and Aβ 42/Aβ 40 <  0.1013 was used to define amyloid positivity. Two ANN models were trained and tested for predicting the outcome. The first model architecture only includes driving variables as input, whereas the second architecture includes the combination of age, APOE ɛ4 status, and driving variables. RESULTS: All 142 participants (mean [SD] age 73.9 [5.2] years; 76 [53.5%] men; 80 participants [56.3% ] with amyloid positivity based on plasma Aβ 42/Aβ 40) were cognitively normal. The six driving features, included in the ANN models, were the number of trips during rush hour, the median and standard deviation of jerk, the number of hard braking incidents and night trips, and the standard deviation of speed. The F1 score of the model with driving variables alone was 0.75 [0.023] for predicting plasma Aβ 42/Aβ 40. Incorporating age and APOE ɛ4 carrier status improved the diagnostic performance of the model to 0.80 [>0.051]. CONCLUSION: Blood-based AD biomarkers offer a novel opportunity to establish the efficacy of naturalistic driving as an accessible digital marker for AD pathology in driving research.

APA Citation

Bayat, Sayeh; Roe, Catherine M.; Schindler, Suzanne; Murphy, Samantha A.; Doherty, Jason M.; Johnson, Ann M.; Walker, Alexis; Ances, Beau M.; Morris, John C.; and Babulal, Ganesh M., "Everyday Driving and Plasma Biomarkers in Alzheimer's Disease: Leveraging Artificial Intelligence to Expand Our Diagnostic Toolkit" (2023). GW Authored Works. Paper 2590.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/2590

Department

Clinical Research and Leadership