People with Alzheimer’s disease often drive shorter distances and visit fewer new places than people without it . With this in mind, GPS data can serve as a biomarker to identify preclinical Alzheimer’s, according to the results of a study published in Alzheimer’s Research & Therapy .
The participants, 75 people without preclinical Alzheimer’s and 64 people with it, were already enrolled in studies on aging, dementia and driving.
Data analyzed by machine learning
The researchers installed GPS data loggers with custom software in the participants’ vehicles and recorded 1 year of driving data. The researchers then measured driving performance (speed, acceleration, jerks, hard braking) and driving space (places traveled). The data sets were then used by machine learning to predict disease .
Using only the driving indicators, the predictive model achieved a precision score of 0.89, indicating that the model correctly predicted the disease 89% of the time . The model correctly identified 76% of the participants with preclinical Alzheimer’s. The driving characteristics most closely related to this condition included the amount of night driving and speeding.
A limitation of the study was the inability of the GPS device to detect who was driving the vehicles, whether it was the participant, a spouse or a family member. Additional limitations included all participants residing in the St. Louis, Missouri metropolitan area; therefore, the results may not apply to the general population. The study also did not examine socioeconomic status, gender, race, income, or educational level .