Diagnostic performance of actigraphy in Alzheimer's disease using a machine learning classifier - a cross-sectional memory clinic study.

Abstract

Background: Movement patterns, activity levels and circadian rhythm are altered in Alzheimer's disease (AD) and can be assessed by actigraphy using wearable sensors. We aimed to determine the diagnostic performance of actigraphy in AD in a memory clinic population by using a machine-learning classifier.

Methods: In our single-center cross-sectional study, 70 patients with AD (MCI-moderate dementia), dementia with Lewy bodies (DLB) (N = 29) and cerebrovascular disease (CVD) (N = 23), and 48 elderly healthy controls were included. Participants underwent actigraphy at home using two body-worn sensors (SENS Motion^®) for 1 week. We derived movement patterns (walking, running, resting, etc.) from raw accelerometry data using a proprietary algorithm. By evaluating the movement patterns during day and nighttime, we calculated 510 activity-related features, including robustness and fragmentation of the circadian rhythm. These features were used to train a machine learning (ML) classifier using logistic regression. We evaluated the performance of our classifier by assessing the accuracy and precision of predictions.

Results: We found that movement patterns as well as the robustness and fragmentation of the circadian rhythm differed significantly between groups. During the daytime, patients with AD performed less moderate activity and walked less than the healthy group. While we achieved a modest accuracy of 68.8% for differentiating AD and healthy, the performance was highest (accuracy: 80-89%; precision: 69-84%) when ML was applied to actigraphy data to differentiate dementia etiologies (AD vs. DLB + AD vs. CVD).

Conclusion: Actigraphy accurately identifies different dementia etiologies and could serve as a supplement to diagnostic investigations in patients with suspected AD for differential diagnostic purposes.