BACKGROUND
Early signs of Alzheimer's disease (AD) are difficult to detect, causing diagnoses to be significantly delayed to time points when brain damage has already occurred, and current experimental treatments have little effect on slowing disease progression. Tracking of cognitive decline at early stages is critical to allow patients to make lifestyle changes and consider new and experimental therapies. Frequently studied biomarkers are invasive and costly, and are limited in predicting conversion from normal to mild cognitive impairment (MCI).
OBJECTIVE
Test the use of fitness trackers for predicting MCI status
METHODS
We compared the result of fitness trackers worn for up to a month with regard to physical activity, heart rate and sleep, in 20 participants: twelve MCI and eight age-matched controls. We further developed a machine learning model to predict MCI status.
RESULTS
Our machine learning model was able to perfectly separate between MCI and controls. Our top predictive features include average deep sleep time, total light activity time, and lowest resting heart rate over a month.
CONCLUSIONS
Our results suggest that a longitudinal digital biomarker differentiates between control and MCI patients in a very cost-effective and noninvasive way and hence may be very useful for identifying patients with very early AD who can benefit from clinical trials and new, disease modifying therapies.