EVIDENCE Publication Checklist for Studies Evaluating Connected Sensor Technologies: Explanation and Elaboration.

The EVIDENCE (EValuatIng connecteD sENsor teChnologiEs) checklist was developed by a multidisciplinary group of content experts convened by the Digital Medicine Society, representing the clinical sciences, data management, technology development, and biostatistics. The aim of EVIDENCE is to promote high quality reporting in studies where the primary objective is an evaluation of a digital measurement product or its constituent parts. Here we use the terms digital measurement product and connected sensor technology interchangeably to refer to tools that process data captured by mobile sensors using algorithms to generate measures of behavioral and/or physiological function. EVIDENCE is applicable to 5 types of evaluations: (1) proof of concept; (2) verification, (3) analytical validation, and (4) clinical validation as defined by the V3 framework; and (5) utility and usability assessments. Using EVIDENCE, those preparing, reading, or reviewing studies evaluating digital measurement products will be better equipped to distinguish necessary reporting requirements to drive high-quality research. With broad adoption, the EVIDENCE checklist will serve as a much-needed guide to raise the bar for quality reporting in published literature evaluating digital measurements products.

Development of digital measures for nighttime scratch and sleep using wrist-worn wearable devices.

Patients with atopic dermatitis experience increased nocturnal pruritus which leads to scratching and sleep disturbances that significantly contribute to poor quality of life. Objective measurements of nighttime scratching and sleep quantity can help assess the efficacy of an intervention. Wearable sensors can provide novel, objective measures of nighttime scratching and sleep; however, many current approaches were not designed for passive, unsupervised monitoring during daily life. In this work, we present the development and analytical validation of a method that sequentially processes epochs of sample-level accelerometer data from a wrist-worn device to provide continuous digital measures of nighttime scratching and sleep quantity. This approach uses heuristic and machine learning algorithms in a hierarchical paradigm by first determining when the patient intends to sleep, then detecting sleep-wake states along with scratching episodes, and lastly deriving objective measures of both sleep and scratch. Leveraging reference data collected in a sleep laboratory (NCT ID: NCT03490877), results show that sensor-derived measures of total sleep opportunity (TSO; time when patient intends to sleep) and total sleep time (TST) correlate well with reference polysomnography data (TSO: r = 0.72, p < 0.001; TST: r = 0.76, p < 0.001; N = 32). Log transformed sensor derived measures of total scratching duration achieve strong agreement with reference annotated video recordings (r = 0.82, p < 0.001; N = 25). These results support the use of wearable sensors for objective, continuous measurement of nighttime scratching and sleep during daily life.

Development of digital biomarkers for resting tremor and bradykinesia using a wrist-worn wearable device.

Objective assessment of Parkinson's disease symptoms during daily life can help improve disease management and accelerate the development of new therapies. However, many current approaches require the use of multiple devices, or performance of prescribed motor activities, which makes them ill-suited for free-living conditions. Furthermore, there is a lack of open methods that have demonstrated both criterion and discriminative validity for continuous objective assessment of motor symptoms in this population. Hence, there is a need for systems that can reduce patient burden by using a minimal sensor setup while continuously capturing clinically meaningful measures of motor symptom severity under free-living conditions. We propose a method that sequentially processes epochs of raw sensor data from a single wrist-worn accelerometer by using heuristic and machine learning models in a hierarchical framework to provide continuous monitoring of tremor and bradykinesia. Results show that sensor derived continuous measures of resting tremor and bradykinesia achieve good to strong agreement with clinical assessment of symptom severity and are able to discriminate between treatment-related changes in motor states.

Clinical feasibility of a wearable, conformable sensor patch to monitor motor symptoms in Parkinson's disease.

INTRODUCTION: Clinical assessment of motor symptoms in Parkinson's disease (PD) is subjective and may not reflect patient real-world experience. This two-part pilot study evaluated the accuracy of the NIMBLE wearable biosensor patch (containing an accelerometer and electromyography sensor) to record body movements in clinic and home environments versus clinical measurement of motor symptoms. METHODS: Patients (Hoehn & Yahr 2-3) had motor symptom fluctuations and were on a stable levodopa dose. Part 1 investigated different sensor body locations (six patients). In Part 2, 21 patients wore four sensors (chest, and most affected side of shin, forearm and back-of-hand) during a 2-day clinic- and 1-day home-based evaluation. Patients underwent Unified Parkinson's Disease Rating Scale assessments on days 1-2, and performed pre-defined motor activities at home on day 3. An algorithm estimated motor-symptom severity (predicted scores) using patch data (in-clinic); this was compared with in-clinic motor symptom assessments (observed scores). RESULTS: The overall correlation coefficient between in-clinic observed and sensor algorithm-predicted scores was 0.471 (p = 0.031). Predicted and observed scores were identical 45% of the time, with a predicted score within a ±1 range 91% of the time. Exact accuracy for each activity varied, ranging from 32% (pronation/supination) to 67% (rest-tremor-amplitude). Patients rated the patch easy-to-use and as providing valuable data for managing PD symptoms. Overall patch-adhesion success was 97.2%. The patch was safe and generally well tolerated. CONCLUSIONS: This study showed a correlation between sensor algorithm-predicted and clinician-observed motor-symptom scores. Algorithm refinement using patient populations with greater symptom-severity range may potentially improve the correlation.

A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis.

Gait speed is a powerful clinical marker for mobility impairment in patients suffering from neurological disorders. However, assessment of gait speed in coordination with delivery of comprehensive care is usually constrained to clinical environments and is often limited due to mounting demands on the availability of trained clinical staff. These limitations in assessment design could give rise to poor ecological validity and limited ability to tailor interventions to individual patients. Recent advances in wearable sensor technologies have fostered the development of new methods for monitoring parameters that characterize mobility impairment, such as gait speed, outside the clinic, and therefore address many of the limitations associated with clinical assessments. However, these methods are often validated using normal gait patterns; and extending their utility to subjects with gait impairments continues to be a challenge. In this paper, we present a machine learning method for estimating gait speed using a configurable array of skin-mounted, conformal accelerometers. We establish the accuracy of this technique on treadmill walking data from subjects with normal gait patterns and subjects with multiple sclerosis-induced gait impairments. For subjects with normal gait, the best performing model systematically overestimates speed by only 0.01 m/s, detects changes in speed to within less than 1%, and achieves a root-mean-square-error of 0.12 m/s. Extending these models trained on normal gait to subjects with gait impairments yields only minor changes in model performance. For example, for subjects with gait impairments, the best performing model systematically overestimates speed by 0.01 m/s, quantifies changes in speed to within 1%, and achieves a root-mean-square-error of 0.14 m/s. Additional analyses demonstrate that there is no correlation between gait speed estimation error and impairment severity, and that the estimated speeds maintain the clinical significance of ground truth speed in this population. These results support the use of wearable accelerometer arrays for estimating walking speed in normal subjects and their extension to MS patient cohorts with gait impairment.

Skin mounted accelerometer system for measuring knee range of motion.

Sufficient range of motion of the knee joint is necessary for performing many activities of daily living. Ambulatory monitoring of knee function can provide valuable information about progression of diseases like knee osteoarthritis and recovery after surgical interventions like total knee arthroplasty. In this paper, we describe a skin-mounted, conformal, accelerometer-based system for measuring knee angle and range of motion that does not require a skilled operator to apply devices. We establish the accuracy of this technique with respect to clinical gold standard goniometric measurements on a dataset collected from normative subjects during the performance of repeated bouts of knee flexion and extension tests. Results show that knee angle and range of motion estimates are highly correlated with goniometer measurements, and track differences in knee angle and range of motion to within 1%. These results demonstrate the ability of this system to characterize knee angle and range of motion, enabling future longitudinal monitoring of knee motion in naturalistic environments.

A wearable computing platform for developing cloud-based machine learning models for health monitoring applications.

Wearable sensors have the potential to enable clinical-grade ambulatory health monitoring outside the clinic. Technological advances have enabled development of devices that can measure vital signs with great precision and significant progress has been made towards extracting clinically meaningful information from these devices in research studies. However, translating measurement accuracies achieved in the controlled settings such as the lab and clinic to unconstrained environments such as the home remains a challenge. In this paper, we present a novel wearable computing platform for unobtrusive collection of labeled datasets and a new paradigm for continuous development, deployment and evaluation of machine learning models to ensure robust model performance as we transition from the lab to home. Using this system, we train activity classification models across two studies and track changes in model performance as we go from constrained to unconstrained settings.