Dataset Information

Fall Risk Classification in Community-Dwelling Older Adults Using a Smart Wrist-Worn Device and the Resident Assessment Instrument-Home Care: Prospective Observational Study.

ABSTRACT:

Background

Little is known about whether off-the-shelf wearable sensor data can contribute to fall risk classification or complement clinical assessment tools such as the Resident Assessment Instrument-Home Care (RAI-HC).

Objective

This study aimed to (1) investigate the similarities and differences in physical activity (PA), heart rate, and night sleep in a sample of community-dwelling older adults with varying fall histories using a smart wrist-worn device and (2) create and evaluate fall risk classification models based on (i) wearable data, (ii) the RAI-HC, and (iii) the combination of wearable and RAI-HC data.

Methods

A prospective, observational study was conducted among 3 faller groups (G₀, G₁, G₂₊) based on the number of previous falls (0, 1, ?2 falls) in a sample of older community-dwelling adults. Each participant was requested to wear a smart wristband for 7 consecutive days while carrying out day-to-day activities in their normal lives. The wearable and RAI-HC assessment data were analyzed and utilized to create fall risk classification models, with 3 supervised machine learning algorithms: logistic regression, decision tree, and random forest (RF).

Results

Of 40 participants aged 65 to 93 years, 16 (40%) had no previous falls, whereas 8 (20%) and 16 (40%) had experienced 1 and multiple (?2) falls, respectively. Level of PA as measured by average daily steps was significantly different between groups (P=.04). In the 3 faller group classification, RF achieved the best accuracy of 83.8% using both wearable and RAI-HC data, which is 13.5% higher than that of using the RAI-HC data only and 18.9% higher than that of using wearable data exclusively. In discriminating between {G₀+G₁} and G₂₊, RF achieved the best area under the receiver operating characteristic curve of 0.894 (overall accuracy of 89.2%) based on wearable and RAI-HC data. Discrimination between G₀ and {G₁+G₂₊} did not result in better classification performance than that between {G₀+G₁} and G₂₊.

Conclusions

Both wearable data and the RAI-HC assessment can contribute to fall risk classification. All the classification models revealed that RAI-HC outperforms wearable data, and the best performance was achieved with the combination of 2 datasets. Future studies in fall risk assessment should consider using wearable technologies to supplement resident assessment instruments.

SUBMITTER: Yang Y

PROVIDER: S-EPMC6716444 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Fall Risk Classification in Community-Dwelling Older Adults Using a Smart Wrist-Worn Device and the Resident Assessment Instrument-Home Care: Prospective Observational Study.

Yang Yang Y Hirdes John P JP Dubin Joel A JA Lee Joon J

JMIR aging 20190607 1

<h4>Background</h4> Little is known about whether off-the-shelf wearable sensor data can contribute to fall risk classification or complement clinical assessment tools such as the Resident Assessment Instrument-Home Care (RAI-HC).<h4>Objective</h4> This study aimed to (1) investigate the similarities and differences in physical activity (PA), heart rate, and night sleep in a sample of community-dwelling older adults with varying fall histories using a smart wrist-worn device and (2) create and e ...[more]

PMID: 31518278

Similar Datasets

Project description:Wearable activity trackers are newly emerging technologies with the anticipation for successfully supporting aging-in-place. Consumer-grade wearable activity trackers are increasingly ubiquitous in the market, but the attitudes toward, as well as acceptance and voluntary use of, these trackers in older population are poorly understood.The aim of this study was to assess acceptance and usage of wearable activity trackers in Canadian community-dwelling older adults, using the potentially influential factors as identified in literature and technology acceptance model.A mixed methods design was used. A total of 20 older adults aged 55 years and older were recruited from Southwestern Ontario. Participants used 2 different wearable activity trackers (Xiaomi Mi Band and Microsoft Band) separately for each segment in the crossover design study for 21 days (ie, 42 days total). A questionnaire was developed to capture acceptance and experience at the end of each segment, representing 2 different devices. Semistructured interviews were conducted with 4 participants, and a content analysis was performed.Participants ranged in age from 55 years to 84 years (mean age: 64 years). The Mi Band gained higher levels of acceptance (16/20, 80%) compared with the Microsoft Band (10/20, 50%). The equipment characteristics dimension scored significantly higher for the Mi Band (P<.05). The amount a participant was willing to pay for the device was highly associated with technology acceptance (P<.05). Multivariate logistic regression with 3 covariates resulted in an area under the curve of 0.79. Content analysis resulted in the formation of the following main themes: (1) smartphones as facilitators of wearable activity trackers; (2) privacy is less of a concern for wearable activity trackers, (3) value proposition: self-awareness and motivation; (4) subjective norm, social support, and sense of independence; and (5) equipment characteristics matter: display, battery, comfort, and aesthetics.Older adults were mostly accepting of wearable activity trackers, and they had a clear understanding of its value for their lives. Wearable activity trackers were uniquely considered more personal than other types of technologies, thereby the equipment characteristics including comfort, aesthetics, and price had a significant impact on the acceptance. Results indicated that privacy was less of concern for older adults, but it may have stemmed from a lack of understanding of the privacy risks and implications. These findings add to emerging research that investigates acceptance and factors that may influence acceptance of wearable activity trackers among older adults.

Project description:BACKGROUND:One way of measuring the quality of home care are quality indicators (QIs) derived from data collected with the Resident Assessment Instrument-Home Care (RAI-HC). In order to produce meaningful results for quality improvement and quality comparisons across home care organizations (HCOs) and over time, RAI-HC QIs must be valid and reliable. The aim of this systematic review was to identify currently existing RAI-HC QIs and to summarize the scientific knowledge on the validity and reliability of these QIs. METHODS:A systematic review was performed using the electronic databases PubMed, CINAHL, Embase, PsycINFO and Cochrane Library. Studies describing the development process or the psychometric characteristics of RAI-HC QIs were eligible. The data extraction involved a general description of the included studies as well as the identified RAI-HC QIs and information on validity and reliability. The methodological quality of the identified RAI-HC QI sets was assessed using the Appraisal of Indicators through Research and Evaluation (AIRE) instrument. RESULTS:Four studies out of 659 initial hits met the inclusion criteria. The included studies described the development and validation process of three RAI-HC QI sets comprising 48 unique RAI-HC QIs, which predominantly refer to outcome of care. Overall, the validity and reliability of the identified RAI-HC QIs were not sufficiently tested. The methodological quality of the three identified RAI-HC QI sets varied across the four AIRE instrument domains. None of the QI sets reached high methodological quality, defined as scores of 50% and higher in all four AIRE instrument domains. CONCLUSIONS:This is the first review that systematically summarized and appraised the available scientific evidence on the validity and reliability of RAI-HC QIs. It identified insufficient reporting of RAI-HC QIs validation processes and reliability as well as missing state-of-the-art methodologies. The review provides guidance as to what additional validity and reliability testing are needed to strengthen the scientific soundness of RAI-HC QIs. Considering that RAI-HC QIs are already implemented and used to measure and compare quality of home care, further investigations on RAI-HC QIs reliability and validity is recommended.

Dataset Information

Fall Risk Classification in Community-Dwelling Older Adults Using a Smart Wrist-Worn Device and the Resident Assessment Instrument-Home Care: Prospective Observational Study.

Background

Objective

Methods

Results

Conclusions

Publications

Fall Risk Classification in Community-Dwelling Older Adults Using a Smart Wrist-Worn Device and the Resident Assessment Instrument-Home Care: Prospective Observational Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets