Stair climb power (SCP) is a clinical measure of leg muscular function assessed in-clinic via the Stair Climb Power Test (SCPT). This method is subject to human error and cannot provide continuous remote monitoring. Continuous monitoring using wearable sensors may provide a more comprehensive assessment of lower-limb muscular function. In this work, we propose an algorithm to classify stair climbing periods and estimate SCP from a lower-back worn accelerometer, which strongly agrees with the clinical standard (r = 0.92, p < 0.001; ICC = 0.90, [0.82, 0.94]). Data were collected in-lab from healthy adults (n = 65) performing the four-step SCPT and a walking assessment while instrumented (accelerometer + gyroscope), which allowed us to investigate tradeoffs between sensor modalities. Using two classifiers, we were able to identify periods of stair ascent with >89% accuracy [sensitivity = >0.89, specificity = >0.90] using two ensemble machine learning algorithms, trained on accelerometer signal features. Minimal changes in model performances were observed using the gyroscope alone (±0–6% accuracy) versus the accelerometer model. While we observed a slight increase in accuracy when combining gyroscope and accelerometer (about +3–6% accuracy), this is tolerable to preserve battery life in the at-home environment. This work is impactful as it shows potential for an accelerometer-based at-home assessment of SCP.

Wearable accelerometers allow for continuous monitoring of function and behaviors in the participant’s naturalistic environment. Devices are typically worn in different body locations depending on the concept of interest and endpoint under investigation. The lumbar and wrist are commonly used locations: devices placed at the lumbar region enable the derivation of spatio-temporal characteristics of gait, while wrist-worn devices provide measurements of overall physical activity (PA). Deploying multiple devices in clinical trial settings leads to higher patient burden negatively impacting compliance and data quality and increases the operational complexity of the trial. In this work, we evaluated the joint information shared by features derived from the lumbar and wrist devices to assess whether gait characteristics can be adequately represented by PA measured with wrist-worn devices. Data collected at the Pfizer Innovation Research (PfIRe) Lab were used as a real data example, which had around 7 days of continuous at-home data from wrist- and lumbar-worn devices (GENEActiv) obtained from a group of healthy participants. The relationship between wrist- and lumbar-derived features was estimated using multiple statistical methods, including penalized regression, principal component regression, partial least square regression, and joint and individual variation explained (JIVE). By considering multilevel models, both between- and within-subject effects were taken into account. This work demonstrated that selected gait features, which are typically measured with lumbar-worn devices, can be represented by PA features measured with wrist-worn devices, which provides preliminary evidence to reduce the number of devices needed in clinical trials and to increase patients’ comfort. Moreover, the statistical methods used in this work provided an analytic framework to compare repeated measures collected from multiple data modalities.

BACKGROUND With the rising prevalence of aging worldwide, there is a necessity for reliable and frequent assessments of older individuals’ health status to manage and potentially prevent age-related complications. Digital health technologies (DHTs), such as wearable devices, provide an opportunity to gather objective, continuous, and unobtrusive measurements, enabling effective health management in everyday life. OBJECTIVE We aimed to evaluate the relationship between digital endpoints and frailty, nutritional status, and patient-reported outcomes (PROs) in older individuals, as well as quantified their compliance and comfort with DHTs. METHODS In two cross-sectional studies, namely the Geriatric Anorexia Studies 1 and 2, including three in-clinic visits and 2-3 weeks of at-home monitoring, 94 participants (mean age 72.98 years, SD 6.28 years) were stratified based on their frailty status (n=39, 41%, nonfrail; n=45, 48%, prefrail; and n=10, 11%, frail) and nutritional status (n=70, 74%, with normal nutrition and n=24, 26%, at risk for malnutrition), as assessed in a clinical setting using the Fried Frailty Score and the Simplified Nutritional Appetite Questionnaire, respectively. We remotely monitored older adults using different DHTs. At home, participants were monitored with a wrist accelerometer for physical activity, continuous glucose monitoring (CGM) for glucose concentration, a digital body scale for weight and body composition, and a digital nutritional scale for meal tracking. Compliance with devices was assessed via wear time and correct at-home usage, while comfort was evaluated using questionnaires. The association between digital endpoints and frailty/nutritional status was investigated via linear regression, followed by ANOVA, and the relationship between digital endpoints collected at home and PROs was evaluated via Spearman’s ρ. Weight and body composition were also assessed during in-clinic visits with a research-grade scale, used to validate the at-home digital body scale measurements, via the intraclass correlation coefficient, Pearson’s R, and Bland-Altman plots with mean bias. RESULTS Physical activity digital endpoints collected at home were significantly different across frailty and nutritional groups and significantly correlated with self-reported appetite, fatigue, and physical function (eg, for mean daily activity in the maximum 60 minutes of activity, ρ=0.28, –0.23, and 0.47, respectively). More than 80% of participants reported that all devices were mostly to very acceptable to wear/use: 95% (88/93) for the body scale, 86% (43/50) for CGM, 80% (40/50) for the nutrition scale, and 91% (84/93) for the wrist accelerometer. Compliance ranged from 60% of monitoring days for the digital nutrition scale to 90% for the wrist accelerometer. CONCLUSIONS Physical activity digital endpoints show clear prognostic significance for frailty and malnutrition in older individuals and reflect self-reported measures. DHTs can be reliably deployed at home for older individuals to measure their physical activity, weight and body composition, glucose concentration, and meal intakes, thus enabling patient-centric, data-centric clinical trials. CLINICALTRIAL ClinicalTrials.gov NCT04858932; https://clinicaltrials.gov/study/NCT04858932; ClinicalTrials.gov NCT05211973; https://clinicaltrials.gov/study/NCT05211973

Background: With the rising prevalence of aging worldwide, there is a necessity for reliable and frequent assessments of older individuals’ health status to manage and potentially prevent age-related complications. Digital health technologies (DHTs), such as wearable devices, provide an opportunity to gather objective, continuous, and unobtrusive measurements, enabling effective health management in everyday life. Objective: We aimed to evaluate the relationship between digital endpoints and frailty, nutritional status, and patient-reported outcomes (PROs) in older individuals, as well as quantified their compliance and comfort with DHTs. Methods: In two cross-sectional studies, namely the Geriatric Anorexia Studies 1 and 2, including three in-clinic visits and 2-3 weeks of at-home monitoring, 94 participants (mean age 72.98 years, SD 6.28 years) were stratified based on their frailty status (n=39, 41%, nonfrail; n=45, 48%, prefrail; and n=10, 11%, frail) and nutritional status (n=70, 74%, with normal nutrition and n=24, 26%, at risk for malnutrition), as assessed in a clinical setting using the Fried Frailty Score and the Simplified Nutritional Appetite Questionnaire, respectively. We remotely monitored older adults using different DHTs. At home, participants were monitored with a wrist accelerometer for physical activity, continuous glucose monitoring (CGM) for glucose concentration, a digital body scale for weight and body composition, and a digital nutritional scale for meal tracking. Compliance with devices was assessed via wear time and correct at-home usage, while comfort was evaluated using questionnaires. The association between digital endpoints and frailty/nutritional status was investigated via linear regression, followed by ANOVA, and the relationship between digital endpoints collected at home and PROs was evaluated via Spearman’s ρ. Weight and body composition were also assessed during in-clinic visits with a research-grade scale, used to validate the at-home digital body scale measurements, via the intraclass correlation coefficient, Pearson’s R, and Bland-Altman plots with mean bias. Results: Physical activity digital endpoints collected at home were significantly different across frailty and nutritional groups and significantly correlated with self-reported appetite, fatigue, and physical function (eg, for mean daily activity in the maximum 60 minutes of activity, ρ=0.28, –0.23, and 0.47, respectively). More than 80% of participants reported that all devices were mostly to very acceptable to wear/use: 95% (88/93) for the body scale, 86% (43/50) for CGM, 80% (40/50) for the nutrition scale, and 91% (84/93) for the wrist accelerometer. Compliance ranged from 60% of monitoring days for the digital nutrition scale to 90% for the wrist accelerometer. Conclusions: Physical activity digital endpoints show clear prognostic significance for frailty and malnutrition in older individuals and reflect self-reported measures. DHTs can be reliably deployed at home for older individuals to measure their physical activity, weight and body composition, glucose concentration, and meal intakes, thus enabling patient-centric, data-centric clinical trials. Trial Registration: ClinicalTrials.gov NCT04858932; https://clinicaltrials.gov/study/NCT04858932; ClinicalTrials.gov NCT05211973; https://clinicaltrials.gov/study/NCT05211973