|
Activity Number:
|
205
- Digital Phenotyping
|
|
Type:
|
Topic-Contributed
|
|
Date/Time:
|
Tuesday, August 10, 2021 : 1:30 PM to 3:20 PM
|
|
Sponsor:
|
Mental Health Statistics Section
|
|
Abstract #317256
|
|
|
Title:
|
Distributional Data Analysis via Quantile Functions and Its Application to Modeling Digital Biomarkers of Gait in Alzheimer’s Disease
|
|
Author(s):
|
Rahul Ghosal* and Vijay R. Varma and Dmitri Volfson and Inbar Hillel and Jacek Urbanek and Jeffrey M. Hausdorff and Amber Watts and Vadim Zipunnikov
|
|
Companies:
|
Johns Hopkins Bloomberg School of Public Health and National Institute on Aging (NIA), National Institutes of Health (NIH) and Neuroscience Analytics, Computational Biology, Takeda, Cambridge, MA, USA and Tel Aviv Sourasky Medical Center, Tel Aviv, Israel and Johns Hopkins University School of Medicine and Tel Aviv University, Tel Aviv, Israel and Department of Psychology, University of Kansas and Johns Hopkins Bloomberg School of Public Health
|
|
Keywords:
|
Wearable data;
Quantile functions;
L-Moments;
Alzheimer’s disease;
Gait
|
|
Abstract:
|
With the advent of continuous health monitoring via wearable devices, users now generate their unique streams of continuous data such as minute-level physical activity or heart rate. Aggregating these streams into scalar summaries ignores the distributional nature of data and often leads to the loss of critical information. We propose to capture the distributional properties of wearable data via user-specific quantile functions that are further used in functional regression and multi-modal distributional modelling. In addition, we propose to encode user-specific distributional information with user-specific L-moments, robust rank-based analogs of traditional moments, offering mutually consistent functional and distributional interpretation of the results. The proposed methods are illustrated in a study of association of accelerometry-derived digital gait biomarkers with Alzheimer’s disease (AD) and in people with normal cognitive function. Our analysis shows that the proposed quantile-based representation results in a much higher predictive performance compared to simple distributional summaries and attains much stronger associations with clinical cognitive scales.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
