Wearable Device-Independent Next Day Activity and Next Night Sleep Prediction for Rehabilitation Populations

Abstract

Wearable sensor-based devices are increasingly applied in free-living and clinical settings to collect fine-grained, objective data about activity and sleep behavior. The manufacturers of these devices provide proprietary software that labels the sensor data at specified time intervals with activity and sleep information. If the device wearer has a health condition affecting their movement, such as a stroke, these labels and their values can vary greatly from manufacturer to manufacturer. Consequently, generating outcome predictions based on data collected from patients attending inpatient rehabilitation wearing different sensor devices can be challenging, which hampers usefulness of these data for patient care decisions. In this paper, we present a data-driven approach to combining datasets collected from different device manufacturers. With the ability to combine datasets, we merge data from three different device manufacturers to form a larger dataset of time series data collected from 44 patients receiving inpatient therapy services. To gain insights into the recovery process, we use this dataset to build models that predict a patient's next day physical activity duration and next night sleep duration. Using our data-driven approach and the combined dataset, we obtained a normalized root mean square error prediction of 9.11% for daytime physical activity and 11.18% for nighttime sleep duration. Our sleep result is comparable to the accuracy we achieved using the manufacturer's sleep labels (12.26%). Our device-independent predictions are suitable for both point-of-care and remote monitoring applications to provide information to clinicians for customizing therapy services and potentially decreasing recovery time.

Toward Clinical Adoption of Standardized mHealth Solutions

“…Further research is needed to examine sleep intervention effectiveness and resulting behavior change based on sleep feedback and monitoring. 63,64 The positive correlation of strengths, challenges, and needs was an unexpected finding and suggests the SS group may have increased self-awareness and engagement related to their health. This finding aligns with the literature that women with CVD need and desire information about their condition, ongoing support, and a strengths-based approach to their care.…”

“…Both of these findings suggest that having data regarding women's sleep challenges and needs would inform clinical practice, to ensure that consumers and clinicians have meaningful and relevant conversations regarding sleep health and related interventions, particularly for women with CVD. Further research is needed to examine sleep intervention effectiveness and resulting behavior change based on sleep feedback and monitoring 63,64 …”

Detecting Mental Health Behaviors Using Mobile Interactions: Exploratory Study Focusing on Binge Eating

“…Alternatively, research has indicated that some individuals may engage with certain apps (eg, calorie-tracking apps) in different ways around binge-eating episodes [ 1 ]. Similarly, certain episodes could happen around indicators related to physical activity, sleep disorders, or communication patterns that previous research has had positive results quantifying using smartphones and wearables [ 47 , 59 , 85 - 87 ], which are a more direct measurement of the observed phenomena compared with affect and psychological constructs.…”

Comparative Analysis of Two Methods in Fine-Grained Activity Recognition for Ambient Assisted Living

“…In the literature, the main problem Sangavi S. ( 2019); Alrazzak and Alhalabi (2019); Fellger et al (2020); Kolkar and Geetha (2021); Das et al (2023) inherent in the development of assistive technologies adapted for home care concerns artificial intelligence models allowing real-time recognition of a person's ongoing Activities of Daily Living (ADLs). Few examples could be: preparing a meal, washing hands, taking medication, etc.…”