eFurniture for home-based frailty detection using artificial neural networks and wireless sensors

doi:10.1016/j.medengphy.2011.09.010

Medical Engineering & Physics

Volume 35, Issue 2, February 2013, Pages 263-268

https://doi.org/10.1016/j.medengphy.2011.09.010 Get rights and content

Abstract

The purpose of this study is to integrate wireless sensor technologies and artificial neural networks to develop a system to manage personal frailty information automatically. The system consists of five parts: (1) an eScale to measure the subject's reaction time; (2) an eChair to detect slowness in movement, weakness and weight loss; (3) an ePad to measure the subject's balancing ability; (4) an eReach to measure body extension; and (5) a Home-based Information Gateway, which collects all the data and predicts the subject's frailty. Using a furniture-based measuring device to provide home-based measurement means that health checks are not confined to health institutions.

We designed two experiments to obtain optimum frailty prediction model and test overall system performance: (1) We developed a three-step process to adjust different parameters to obtain an optimized neural identification network whose parameters include initialization, L.R. dec and L.R. inc. The post-process identification rate increased from 77.85% to 83.22%. (2) We used 149 cases to evaluate the sensitivity and specificity of our frailty prediction algorithm. The sensitivity and specificity of this system are 79.71% and 86.25% respectively. These results show that our system is a high specificity prediction tool that can be used to assess frailty.

Introduction

Frailty is one of the greatest gerontological challenges faced by modern societies with aging populations. Compared with non-frail persons of similar age, frail elderly people have a much higher risk of suffering related injuries, which could result in disability, hospitalization, institutionalization, or even death. For this reason, early detection of frailty could help delay the onset of frailty and reduce its adverse outcomes. There are several existing frailty measurement methods [1], [2], [3], [4], however, results are often confounded by experimenters’ bias and the inconvenience imposed on subjects [5], [6].

Aging frailty generally occurs in the elderly population and is clinically defined as a state of decreased reserve and resistance to stressors, resulting from cumulative declines across multiple physiological systems. Frailty increases the risk of adverse health outcomes, including mortality, institutionalization, falls and hospitalization [7], [8], [9]. In the United States and Europe, approximately 10–25% of the elderly population over the age of 65 and almost 50% of population over the age of 85 meet the definition of frailty [10]. Depending on the measurement protocol used, the estimated prevalence will vary, generally from 6.9 to 63%. Frailty will be one of the greatest gerontological challenges faced by societies with aging populations in the next 10 years [11]. Fortunately, aging frailty can be prevented and corrected [12], [13]. However, to prevent frailty, physicians need to be able to identify the individuals at risk of frailty before they become frail. Currently there is a lack of effective methods and devices to monitor physical degradation in elderly people over time. Without such tools, it is not possible to help elderly people avoid or mitigate frailty problems.

To slow down the aging rate of the elderly and ensure a healthy lifestyle, the following factors need to be taken into consideration: (1) establishing a body function degeneration analysis mechanism. There has never been a standard definition of aging. To help the elderly understand the status of their body's degeneration, this study attempts to quantify aging standards, and establish an analysis mechanism. (2) Developing a long-term recording and tracking device. In the past, many degenerative indicators have to be measures under the supervision of examiners. The subjects are not able to conduct the tests themselves. In addition, the measurements are easily affected by time and space limitations that in turn cause difficulties in recording long-term aging trends. This study proposes a novel electronic measurement method to improve the accuracy and validity of the data measured by a variety of instruments and equipment. The measurements are used to assist the elderly to establish a personalized body degeneration database.

Section snippets

Methods

This study describes an automatic system to measure general clinical indicators and to assist elderly people to build personal health records [14], [15]. As shown in Fig. 1, the system architecture consists of two parts. (1) A suite of measurement instruments for frailty indicators, including an eScale, an eChair, an ePad, an eReach and electronic questionnaires. We based our system on existing measurement methods, and have integrated similar measurement methods into the electronic measurement

Results

The experiment uses real case data to train the classification model. We attempt to establish an optimized aging estimation model by tuning different network parameters. The cases used in this study were collected from volunteers in Chang Gung Hospital and Rehabilitation center. The degeneration information of 309 people over 65 years of age was collected in this study, 178 of them female and 131 male. With the same ratio between females and males, we randomly selected 160 people as subjects to

Conclusion

Various electronic measuring components were developed in the study to target different aging indicators. The eScale includes a home lighting feature. The eChair is combined with a chair. The ePad employs a software membrane sensor and is integrated in the carpet. The home-based concept is fused into all designs to provide home-based measurement and solve the problem that health checks are limited to taking place in health institutions, as noted above.

Identification of degeneration level is not

Conflict of interest

None.

Acknowledgment

The authors would like to thank the National Science Council, Taiwan, R.O.C., for supporting this research under grant NSC-99-2218-E-182-001.

References (16)

C.-C. Lin et al.
A pervasive health monitoring service system based on ubiquitous network technology
International Journal of Medical Informatics
(2008)
K. Rockwood et al.
A global clinical measure of fitness and frailty in elderly people
Canadian Medical Association Journal
(2005)
M. Markle-Reid et al.
Conceptualizations of frailty in relation to older adults
Journal of Advanced Nursing
(2003)
R. Daniels et al.
Interventions to prevent disability in frail community-dwelling elderly: a systematic review
BMC Health Services Research
(2008)
C.S. Blaum et al.
The association between obesity and the frailty syndrome in older women: the women's health and aging studies
Journal of the American Geriatrics Society
(2005)
M.A. Heberta et al.
Moving research into practice: a decision framework for integrating home telehealth into chronic illness care
International Journal of Medical Informatics
(2006)
L.P. Fried et al.
Frailty in older adults: evidence for a phenotype
The Journals of Gerontology
(2001)
F. Aminzadeh et al.
Targeting frail older adults for outpatient comprehensive geriatric assessment and management services: an overview of concepts and criteria
Reviews in Clinical Gerontology
(2002)

There are more references available in the full text version of this article.

Cited by (26)

Early diagnosis of frailty: Technological and non-intrusive devices for clinical detection
2021, Ageing Research Reviews
Citation Excerpt :
For instance, a light-emitting diode (LED) screen and a wireless sensor module inside a lamp for measuring reaction time and speed of the movements or a chair with pressure sensors for measuring weakness and weight (Chang et al., 2013). Another tool is based on several pads hidden under the carpet for gait and balance control (Chang et al., 2013) (Fig. 10). The tools described above are based on standard furniture improved with sensors, but it is also possible to add new furniture or devices to analyse different phenotypes.
This work analyses different concepts for frailty diagnosis based on affordable standard technology such as smartphones or wearable devices. The goal is to provide ideas that go beyond classical diagnostic tools such as magnetic resonance imaging or tomography, thus changing the paradigm; enabling the detection of frailty without expensive facilities, in an ecological way for both patients and medical staff and even with continuous monitoring. Fried's five-point phenotype model of frailty along with a model based on trials and several classical physical tests were used for device classification. This work provides a starting point for future researchers who will have to try to bridge the gap separating elderly people from technology and medical tests in order to provide feasible, accurate and affordable tools for frailty monitoring for a wide range of users.
Digital Health Interventions among People Living with Frailty: A Scoping Review
2021, Journal of the American Medical Directors Association
Citation Excerpt :
RCT studies that showed good efficacy were an exercise program based on a game system,29,30 another exercise program in a tablet and a night pad light to prevent falls.31 Among cross-sectional studies, DHI that showed good frailty prediction or efficacy were a set of e-furniture (frailty assessment),32 a balance quality tester (falls),33 and a single wrist sensor (frailty detection).34 A longitudinal study that showed good efficacy was a DHI with a light path for preventing falls35 (Table 2).
Digital health interventions (DHIs) are interesting resources to improve various health conditions. However, their use in the older and frail population is still sparse. We aimed to give an overview of DHI used in the frail older population.
Scoping review with PRISMA guidelines based on Population, Concept, and Context.
We included original studies in English with DHI (concept) on people described as frail (population) in the clinical or community setting (context) and no limitation on date of publication. We searched 3 online databases (PubMed, Scopus, and Web of Science).
We described DHI in terms of purpose, delivering, content and assessment. We also described frailty assessment and study design.
We included 105 studies that fulfilled our eligibility criteria. The most frequently reported DHIs were with the purpose of monitoring (45; 43%), with a delivery method of sensor-based technologies (59; 56%), with a content of feedback to users (34; 32%), and for assessment of feasibility (57; 54%). Efficacy was reported in 31 (30%) studies and usability/feasibility in 57 (55%) studies. The most common study design was descriptive exploratory for new methodology or technology (24; 23%). There were 14 (13%) randomized controlled trials, with only 4 of 14 studies (29%) showing a low or moderate risk of bias. Frailty assessment using validated scales was reported in only 47 (45%) studies.
There was much heterogeneity among frailty assessments, study designs, and evaluations of DHIs. There is now a strong need for more standardized approaches to assess frailty, well-structured randomized controlled trials, and proper evaluation and report. This work will contribute to the development of better DHIs in this vulnerable population.
E-health for active ageing; A systematic review
2018, Maturitas
Enabling successful active ageing is an international priority to meet the challenges of increasing life expectancy. Digital strategies, such as telemedicine and e-health, offer the potential to deliver active ageing in a cost-effective manner at scale. This article aims to establish the extent to which the research literature considers e-health-based and telemedicine-based active ageing interventions. A systematic review was conducted according to PRISMA standards. Independently, two authors searched the Cochrane, EMBASE & CINAHL databases, with subsequent independent extraction and semi-quantitative analysis. We report a considerable breadth in digital active ageing research, which is truly international in its scope. There is a diverse range of both interventions and technologies, including a reassuring focus on community-based interventions. Whilst there are a number of quantitative studies, sample sizes are small, with a limited amount of statistical testing of the results. There is significant variation in the outcome measures reported and little consensus as to the most effective intervention strategies. Overall, whilst there is considerable breadth to the research published in the literature, there is a clear restriction in the depth of this research. There is little overall consensus. This lack of depth and consensus may be due to the need to recognize the important role of technical research elements alongside more traditional research methodologies, such as randomized controlled trials. Enabling both technical and clinical research methods to be recognized, in tandem, has enormous potential to support individuals, communities, clinicians and policy makers to make more informed decisions in relation to active ageing.
A novel user authentication and key agreement scheme for heterogeneous ad hoc wireless sensor networks, based on the Internet of Things notion
2014, Ad Hoc Networks
Citation Excerpt :
At that time the WSN research papers focused only on the theoretical and broad applicative uses of WSNs (e.g. military, environment, healthcare), but the research and applicative use of WSN has significantly increased over the last few years. Today we talk about the use of WSN for traffic monitoring [3], pipeline monitoring [4], landslide detection [5], methane leak detection [6], border patrol [7], precision agriculture [8], rehabilitation applications [9], laboratory tutoring [10], asset tracking [11], real-time soccer playing monitoring [12] and many more [13–16]. A list of real-life applicative WSN projects was summed up by Romer and Mattern [2].
The idea of the Internet of Things (IOT) notion is that everything within the global network is accessible and interconnected. As such Wireless Sensor Networks (WSN) play a vital role in such an environment, since they cover a wide application field. Such interconnection can be seen from the aspect of a remote user who can access a single desired sensor node from the WSN without the necessity of firstly connecting with a gateway node (GWN). This paper focuses on such an environment and proposes a novel user authentication and key agreement scheme for heterogeneous ad hoc wireless sensor networks. The proposed scheme enables a remote user to securely negotiate a session key with a general sensor node, using a lightweight key agreement protocol. The proposed scheme ensures mutual authentication between the user, sensor node, and the gateway node (GWN), although the GWN is never contacted by the user. The proposed scheme has been adapted to the resource-constrained architecture of the WSN, thus it uses only simple hash and XOR computations. Our proposed scheme tackles these risks and the challenges posed by the IOT, by ensuring high security and performance features.
Real-Time Water Quality Assessment via IoT: Monitoring pH, TDS, Temperature, and Turbidity
2023, Ingenierie des Systemes d'Information
Architecture of a Non-Intrusive IoT System for Frailty Detection in Older People
2023, Electronics (Switzerland)

View all citing articles on Scopus

View full text

eFurniture for home-based frailty detection using artificial neural networks and wireless sensors

Abstract

Introduction

Section snippets

Methods

Results

Conclusion

Conflict of interest

Acknowledgment

International Journal of Medical Informatics

A global clinical measure of fitness and frailty in elderly people

Canadian Medical Association Journal

Conceptualizations of frailty in relation to older adults

Journal of Advanced Nursing

Interventions to prevent disability in frail community-dwelling elderly: a systematic review

BMC Health Services Research

The association between obesity and the frailty syndrome in older women: the women's health and aging studies

Journal of the American Geriatrics Society

Moving research into practice: a decision framework for integrating home telehealth into chronic illness care

International Journal of Medical Informatics

Frailty in older adults: evidence for a phenotype

The Journals of Gerontology

Targeting frail older adults for outpatient comprehensive geriatric assessment and management services: an overview of concepts and criteria

Reviews in Clinical Gerontology