Introduction Few studies have explored whether gait measured continuously within a community setting can identify individuals with Alzheimer's disease (AD). This study tests the feasibility of this method to identify individuals at the earliest stage of AD. Methods Mild AD (n = 38) and cognitively normal control (CNC; n = 48) participants from the University of Kansas Alzheimer's Disease Center Registry wore a GT3x+ accelerometer continuously for 7 days to assess gait. Penalized logistic regression with repeated five‐fold cross‐validation followed by adjusted logistic regression was used to identify gait metrics with the highest predictive performance in discriminating mild AD from CNC. Results Variability in step velocity and cadence had the highest predictive utility in identifying individuals with mild AD. Metrics were also associated with cognitive domains impacted in early AD. Discussion Continuous gait monitoring may be a scalable method to identify individuals at‐risk for developing dementia within large, population‐based studies.

Summary We propose a novel method for variable selection in functional linear concurrent regression. Our research is motivated by a fisheries footprint study where the goal is to identify important time‐varying sociostructural drivers influencing patterns of seafood consumption, and hence the fisheries footprint, over time, as well as estimating their dynamic effects. We develop a variable‐selection method in functional linear concurrent regression extending the classically used scalar‐on‐scalar variable‐selection methods like the lasso, smoothly clipped absolute deviation (SCAD) and minimax concave penalty (MCP). We show that in functional linear concurrent regression the variable‐selection problem can be addressed as a group lasso, and their natural extension: the group SCAD or a group MCP problem. Through simulations, we illustrate that our method, particularly with the group SCAD or group MCP, can pick out the relevant variables with high accuracy and has minuscule false positive and false negative rate even when data are observed sparsely, are contaminated with noise and the error process is highly non‐stationary. We also demonstrate two real data applications of our method in studies of dietary calcium absorption and fisheries footprint in the selection of influential time‐varying covariates.

Summary With the advent of continuous health monitoring with wearable devices, users now generate their unique streams of continuous data such as minute-level step counts or heartbeats. Summarizing these streams via scalar summaries often ignores the distributional nature of wearable data and almost unavoidably leads to the loss of critical information. We propose to capture the distributional nature of wearable data via user-specific quantile functions (QF) and use these QFs as predictors in scalar-on-quantile-function-regression (SOQFR). As an alternative approach, we also propose to represent QFs via user-specific L-moments, robust rank-based analogs of traditional moments, and use L-moments as predictors in SOQFR (SOQFR-L). These two approaches provide two mutually consistent interpretations: in terms of quantile levels by SOQFR and in terms of L-moments by SOQFR-L. We also demonstrate how to deal with multi-modal distributional data via Joint and Individual Variation Explained using L-moments. The proposed methods are illustrated in a study of association of digital gait biomarkers with cognitive function in Alzheimers disease. Our analysis shows that the proposed methods demonstrate higher predictive performance and attain much stronger associations with clinical cognitive scales compared to simple distributional summaries.

No abstract

Wearable data is a rich source of information that can provide a deeper understanding of links between human behaviors and human health. Existing modelling approaches use wearable data summarized at subject level via scalar summaries in regression, temporal (time-of-day) curves in functional data analysis (FDA), and distributions in distributional data analysis (DDA). We propose to capture temporally local distributional information in wearable data using subject-specific time-by-distribution (TD) data objects. Specifically, we develop scalar on time-by-distribution regression (SOTDR) to model associations between scalar response of interest such as health outcomes or disease status and TD predictors. Additionally, we show that TD data objects can be parsimoniously represented via a collection of time-varying L-moments that capture distributional changes over the time-of-day. The proposed method is applied to the accelerometry study of mild Alzheimer’s disease (AD). We found that mild AD is significantly associated with reduced upper quantile levels of physical activity, particularly during morning hours. In-sample cross validation demonstrated that TD predictors attain much stronger associations with clinical cognitive scales of attention, verbal memory, and executive function when compared to predictors summarized via scalar total activity counts, temporal functional curves, and quantile functions. Taken together, the present results suggest that SOTDR analysis provides novel insights into cognitive function and AD.