Studies have found that people with symptomatic Alzheimer’s disease (AD) often drive shorter distances and visit fewer new places than people without AD. With this in mind, GPS data can serve as biomarkers for identifying preclinical AD, according to the results of a study published in Alzheimer’s Research & Therapy.
The participants – 75 people without preclinical AD and 64 people with preclinical AD – were already enrolled in studies of age, dementia, and driving. Researchers measured Aβ42 and Aβ40 analytes in cerebrospinal fluid and used positron emission tomography to determine preclinical AD.
The researchers installed GPS data loggers with customer-specific software in the participants’ vehicles and recorded driving data for 1 year. The researchers measured driving performance (speed, acceleration, jerk, heavy braking) and driving space (places traveled). The researchers then applied machine learning to the datasets to predict preclinical AD.
Using driving indicators alone, the predictive model achieved a precision value of 0.89, indicating that the model correctly predicted preclinical AD in 89% of cases. The model correctly identified 76% of participants with preclinical AD. The driving characteristics most closely associated with preclinical AD include the amount of night driving and speeding.
One limitation of the study was the inability of the GPS device to detect who was driving the vehicles, be it the participant, a spouse, or a family member. Additional restrictions included all participants residing in the metropolitan area of St. Louis, Missouri; Therefore, the results may not apply to the general population. The study also did not look at socioeconomic status, gender, race, income, or level of education.
“Recent advances in the development of plasma AD biomarkers have led to newly available blood tests for abnormalities in AD-related proteins, and these blood tests could ultimately be widely used in clinical practice to diagnose AD,” the researchers concluded. “Machine learning methods as used here should also be used to determine the optimal combination of driving behavior in order to identify and predict blood-based AD diagnosis.”
Disclosure: Some study authors stated links with biotech, pharmaceutical, and / or device manufacturers. For a full list of the author’s disclosures, see the original reference.
Bayat S., Babulal GM, Schindler SE, et al. GPS driving: a digital biomarker for preclinical Alzheimer’s disease. Alzheimer’s Res Ther. 2021; 13 (1): 115. doi: 10.1186 / s13195-021-00852-1
This article originally appeared on Psychiatry Advisor