Selecting the most suitable classification algorithm for supporting assistive technology adoption for people with dementia: A multicriteria framework

Abstract

The number of people with dementia (PwD) is increasing dramatically. PwD exhibit impairments of reasoning, memory, and thought that require some form of self‐management intervention to support the completion of everyday activities while maintaining a level of independence. To address this need, efforts have been directed to the development of assistive technology solutions, which may provide an opportunity to alleviate the burden faced by the PwD and their carers. Nevertheless, uptake of such solutions has been limited. It is therefore necessary to use classifiers to discriminate between adopters and nonadopters of these technologies in order to avoid cost overruns and potential negative effects on quality of life. As multiple classification algorithms have been developed, choosing the most suitable classifier has become a critical step in technology adoption. To select the most appropriate classifier, a set of criteria from various domains need to be taken into account by decision makers. In addition, it is crucial to define the most appropriate multicriteria decision‐making approach for the modelling of technology adoption. Considering the above‐mentioned aspects, this paper presents the integration of a five‐phase methodology based on the Fuzzy Analytic Hierarchy Process and the Technique for Order of Preference by Similarity to Ideal Solution to determine the most suitable classifier for supporting assistive technology adoption studies. Fuzzy Analytic Hierarchy Process is used to determine the relative weights of criteria and subcriteria under uncertainty and Technique for Order of Preference by Similarity to Ideal Solution is applied to rank the classifier alternatives. A case study considering a mobile‐based self‐management and reminding solution for PwD is described to validate the proposed approach. The results revealed that the best classifier was k‐nearest‐neighbour with a closeness coefficient of 0.804, and the most important criterion when selecting classifiers is scalability. The paper also discusses the strengths and weaknesses of each algorithm that should be addressed in future research.

Attitudes Toward Technology and Use of Fall Alert Wearables in Caregiving: Survey Study

“…From our analyses, we have demonstrated that the adapted TAM2 concepts of caregivers provide support for our hypotheses about care recipients' use of fall alert wearables, which is reflective of previous literature [12,[20][21][22][23][24][25]30]. Our model demonstrated that both high perceived usefulness and value of technology for caregiving was associated with greater interest in technologies for caregiving and that greater interest in technology for caregiving was predictive of greater use of fall alert wearables among care recipients, although only 28% (153/548) of our study's care recipients used fall alerts.…”

“…We further based our analyses on specific demographic factors and caregiving contexts available from the data in our survey. In addition, our analyses were based on the following subhypotheses, supported in the literature: (1) younger age among caregivers would predict greater perceived usefulness, perceived value, and interest in using technology; (2) more demanding caregiving situations such as longer caregiving hours and dementia among care recipients would increase caregivers’ interest in technology; (3) older age among care recipients would predict greater health care needs and fall risks, hence more need for and use of fall alert–related technology [ 22 , 23 ]; and (4) use of or preference for using family (ie, unpaid) caregivers is most likely associated with economic status (ie, the ability to pay for caregivers) and the availability of unpaid caregivers as well as care recipients’ health conditions [ 23 , 24 ]. Correlates that predict the use of paid versus unpaid caregivers may also influence the use of fall alert technologies.…”

A Novel Integration of IF-DEMATEL and TOPSIS for the Classifier Selection Problem in Assistive Technology Adoption for People with Dementia

“…The use of ATS in health has been covered extensively with general approaches [13][14][15] and with approaches focusing on specific health problems such as visual impairment [16], disabilities [17,18], and dementia [3,[19][20][21][22][23]. This section provides an insight into recent relevant work in ATS for PwD, which has helped to identify similar approaches to the one presented in this paper, to which to compare to and learn lessons from.…”

“…Nonetheless, technology solutions have been used to improve the quality of life of PwD, to support the work of carers, and to provide more personalized types of treatment. Assistive Technology-based Solutions (ATS) [3] have been commonly prescribed as a form of non-pharmacological treatment to PwD to help them complete everyday activities whilst maintaining a level of independence, yielding health and social benefits for them. Some of the areas in which ATS provide support include memory, mobility, indoor and outdoor safety, independence, and socializing.…”

Attitudes Toward Technology and Use of Fall Alert Wearables in Caregiving: Survey Study (Preprint)

“…We further based our analyses on specific demographic factors and caregiving contexts available from the data in our survey. In addition, our analyses were based on the following subhypotheses, supported in the literature: (1) younger age among caregivers would predict greater perceived usefulness, perceived value, and interest in using technology; (2) more demanding caregiving situations such as longer caregiving hours and dementia among care recipients would increase caregivers' interest in technology; (3) older age among care recipients would predict greater health care needs and fall risks, hence more need for and use of fall alert-related technology [22,23]; and (4) use of or preference for using family (ie, unpaid) caregivers is most likely associated with economic status (ie, the ability to pay for caregivers) and the availability of unpaid caregivers as well as care recipients' health conditions [23,24]. Correlates that predict the use of paid versus unpaid caregivers may also influence the use of fall alert technologies.…”