Sage Journals: Discover world-class research

Abstract

A smart healthcare application can be judged as sustainable if it was already widely used before and will also be prevalent in the future. In contrast, if a smart healthcare application developed during the COVID-19 pandemic is not used after it, then it is not sustainable. Assessing the sustainability of smart healthcare applications is a critical task for their users and suppliers. However, it is also a challenging task due to the availability of data, users’ subjective beliefs, and different perspectives. In response to this problem, this study proposes a multi-perspective fuzzy comprehensive evaluation approach to evaluate the sustainability of a smart healthcare application from qualitative, multi-criteria decision-making and time-series perspectives. The proposed methodology has been used to evaluate the sustainability of eight smart healthcare applications. The experimental results showed that the sustainability of a smart healthcare application evaluated from different perspectives may be different. Nevertheless, another technique can be used to confirm the evaluation result generated using one technique. In other words, these views compensate for each other.

Keywords

Smart healthcare application sustainability evaluation qualitative multi-criteria decision-making time-series

Introduction

Sustainability is a method of consuming resources to meet the needs of the present without compromising the ability to meet the needs of the future.^1,2 Sustainability includes three dimensions: economic, environmental, and social.³ The sustainability of a technology usually means that it contributes to economic growth and its use consumes little energy, does not cause any harm to the environment, and does not deprive others (including future generations) of available resources.⁴ However, such a definition is based on a prerequisite that the technology must be used continuously for a long time.^2,4 Otherwise, there is no need to discuss the sustainability of a technology.

This study aims to assess the sustainability of smart healthcare applications. The motivation is that some smart technologies believed to have great potential for healthcare have proven ineffective during the COVID-19 pandemic,^5,6 raising the question of whether some smart healthcare applications are sustainable and others are not.^4–6 This question is important for the following reasons:

For healthcare service providers, if they do not distinguish the changes in the acceptance of different smart healthcare applications during the COVID-19 pandemic, their investment will be blind and not necessarily return.^7,8

For users, they should choose sustainable smart healthcare applications. Otherwise, it will be difficult to seek support from smart healthcare providers in the future.^9,10

Chen⁴ proposed a fuzzy geometric mean (FGM)–alpha cut operations (ACO)–fuzzy weighted average (FWA) approach to evaluate the sustainability of a smart healthcare application, where FGM was used to aggregate the opinions of multiple experts, ACO was used to derive the fuzzy priorities of criteria, and FWA was used for evaluation. Tat et al.¹¹ evaluated the sustainability of smart textiles, a potential smart healthcare application, in terms of energy harvesting and conservation and personalized temperature regulation. Several studies¹² assert that the market size for related smart healthcare applications continues to grow significantly. However, after the COVID-19 pandemic, some people have lost interest in relevant smart healthcare applications, as such applications were far less effective than physical contact tracing methods.¹³ Chen and Lin⁶ considered the multiple viewpoints that a decision maker might hold on the relative priorities of criteria and proposed an FGM decomposition-based fuzzy technique for ordering preference by similarity to ideal solution (FTOPSIS) approach to assess the sustainability of smart healthcare applications. The fuzzy judgment matrix of the decision maker was decomposed by solving a multiobjective fuzzy integer-nonlinear programming problem^14,15 to discover his/her multiple viewpoints. The most effective smart healthcare applications during the COVID-19 pandemic included robots, smartphone apps, wearable sensors and devices, and remote temperature scanners, while wireless medical sensor networks were less practical, which was different than expected.^16,17 Therefore, Chen and Wang¹⁷ proposed a calibrated FGM (cFGM)–FTOPSIS method to assess the sustainability of smart healthcare applications after the COVID-19 pandemic. By improving the accuracy of deriving fuzzy priorities using cFGM, the evaluation results were more convincing.¹⁸ Chen and Chiu¹⁹ proposed a hybridizing subjective and objective fuzzy group decision-making approach with explainable artificial intelligence to reassess the sustainability of smart healthcare applications based on the evidence gathered during the COVID-19 pandemic, in which a fuzzy nonlinear programming problem was solved to combine subjective judgment and objective evidence in deriving the fuzzy priorities of criteria.

Existing methods have the following problems:

Most existing methods are from a multi-criteria decision-making (MCDM) perspective.^{6,11,17,19–21} Methods from other perspectives are lacking and may yield different evaluation results.

Existing methods have not considered all possible factors affecting the sustainability of a smart healthcare application.^22,23

It would be more flexible if a method could evaluate the sustainability of a smart healthcare application based on various data types and availability.^24,25

In response to these problems, this study proposes a multi-perspective fuzzy comprehensive evaluation method to evaluate the sustainability of smart healthcare applications. The proposed methodology consists of three fuzzy techniques from qualitative,^8,10,26–29 MCDM,^{6,11,17,19–21} and time-series perspectives,^28,30 respectively. Fuzzy techniques are considered suitable because they can easily and naturally deal with the uncertainty of sustainability and incorporate experts’ subjective judgments on it.^31–34 Furthermore, applying various fuzzy techniques simultaneously can deal with problems when data types and availability vary.

The differences between the proposed methodology and some existing methods in this field are summarized in Table 1. A total of 23 relevant references were found by searching Google Scholar using the keyword “sustainability smart healthcare.” After excluding references that are less relevant (e.g. IT-intensive, financial, etc.)^35–38 or have not proposed any method for assessment,^39,40 the methods mentioned in seven references were compared. In addition, in this table, only the properties of these methods are compared based on explicit facts, without subjective judgments.

Table 1.

Differences between the proposed methodology and some existing methods in this field.

Method	Smart healthcare applications	Evaluation method type	Number of evaluation methods simultaneously applied	Considered period
Chen and Lin⁶	All possible applications	MCDM	1	During and after the COVID-19 pandemic
Tat et al.¹¹	Smart textiles	MCDM	1	Before the COVID-19 pandemic
Umair et al.¹²	IoT	Time series	1	During the COVID-19 pandemic
Chen and Wang¹⁷	All possible applications	MCDM	1	After the COVID-19 pandemic
Chen and Chiu¹⁹	All possible applications	MCDM	1	After the COVID-19 pandemic
Aminikhanghahi et al.²⁸	Smart home	Time series	1	Before the COVID-19 pandemic
Lichter et al.²⁹	Smart hospital	Online review	1	Before the COVID-19 pandemic
Proposed methodology	All possible applications	Hybrid	3	After the COVID-19 pandemic

MCDM: multi-criteria decision-making; IoT: internet of things.

Literature review

According to Demirkan,⁴¹ cost-effectiveness and low risk are the key factors for the sustainable development of smart healthcare applications. To this end, he established a system framework to conceptualize data-driven, mobile, and cloud-enabled smart healthcare systems to improve cost-effectiveness and reduce the risk of related applications.

A similar view was also held by Lin et al.⁴² However, sometimes effectiveness far outweighs cost-effectiveness, especially when smart technologies are applied for medical purposes. Furthermore, the cost of smart healthcare applications is determined by their supply and demand, both of which are highly stochastic. Furthermore, the cost-effectiveness of smart healthcare applications cannot be directly assessed. For example, a remote temperature scanner can be used to monitor the body temperature of thousands of customers visiting a department store; therefore, the more customers that visit the store, the more cost-effective the remote temperature scanner will be.

A smart healthcare application is sustainable if it can provide value-added services based on vaccination information or recovery status from the COVID-19 pandemic. In the view of Wu et al.,⁴³ although the demand for vaccination information is now declining, providing different services to travelers with unequal vaccination status can still minimize health risks. Additionally, post-pandemic travel is no longer as convenient and flexible as it used to be due to hotel staff shortages and in-house facilities to be restored. Smartphone apps, such as apps for recommending travel destinations or outdoor recreation, can help people organize relaxing activities that are good for their physical and mental health. However, travel destination or outdoor recreation recommendation apps are less relevant for healthcare, but become stronger due to consideration of vaccination, infection, and regulatory information to address inconvenience and achieve sustainable development during the COVID-19 pandemic.

A similar review was performed by Ramírez-Moreno et al.,⁴⁴ who argued that the sustainability of cities lies in the transition to smart cities, where sensors play an important role. Furthermore, in smart cities, sensors should be widely used to collect information on energy, health, mobility, security, water, and waste management.

Theoretically, methods for assessing the sustainability of smart healthcare applications can be divided into three categories^{6,11,12,17–19,28}:

Qualitative methods: In a qualitative method, the requirements for sustainable smart healthcare applications are listed. The more requirements that a smart healthcare application meets, the stronger the sustainability of the smart healthcare application becomes.

MCDM methods: In an MCDM method, the criteria for assessing the sustainability of smart healthcare applications are established. The performance of a smart healthcare application is then evaluated against each criterion. Subsequently, the evaluation results of all the criteria are aggregated to represent the sustainability of the smart healthcare application.

Time-series methods: The time-series method considers the growth of the market size as a time series, thereby predicting the market size in the next few years based on the past. If the market for a smart healthcare application maintains growth in the foreseeable future, the smart healthcare application can be said to be sustainable.

Proposed methodology

The proposed methodology jointly uses three fuzzy techniques to assess the sustainability of a smart healthcare application. Three fuzzy techniques cover all the previously mentioned categories and are applied according to the availability of various types of data (see Figure 1).

Figure 1.

Applications of the three fuzzy techniques according to the availability of various types of data.

Qualitative technique

The sustainability of smart healthcare applications can be assessed by considering the following criteria^19,23:

If a smart healthcare application can provide value-added services, then it will be sustainable.^19,23,45

Smart healthcare applications are sustainable if they are cost-effective.^19,23,46

Smart healthcare applications are sustainable if they can promote healthy mobility for the public.^{10,19,23,47,48}

A smart healthcare application is sustainable if it is necessary or irreplaceable.^10,19,42,49

Smart healthcare applications are sustainable if they can be combined with other applications to achieve synergies.^{10,19,42,50,51}

Smart healthcare applications are sustainable if they are easy to implement and maintain.^10,19,42

as illustrated in Figure 2.

Based on these criteria, the sustainability of smart healthcare applications is assessed based on the subjective beliefs of decision makers, who can be developers of smart healthcare applications, market analysts, or medical or healthcare professionals seeking opportunities to leverage smart technologies to enhance healthcare delivery. However, smart healthcare application developers care about the wide application of smart healthcare applications. Market analysts consider the sales and profits from the use of the application to provide healthcare services. Healthcare professionals, on the other hand, highlight how the application facilitates healthcare delivery to patients. Their focus is biased toward a few specific aspects of sustainable development, risking imprecise assessments.

Figure 2.

Sustainability of a smart healthcare application.

The more criteria a smart healthcare application meets, the more sustainable it is. However, to increase differentiability, it is better to specify the degree to which a smart healthcare application satisfies each criterion with a linguistic term, as shown in Table 2.

Table 2.

Assessing the sustainability of a smart healthcare application.

Criterion	Totally dissatisfied	Somewhat dissatisfied	Moderate	Somewhat satisfied	Completely Satisfied
Can provide value-added services					X
Is cost-effective	X
Can promote healthy mobility			X
Is necessary or irreplaceable				X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X

Subsequently, these linguistic terms are mapped to triangular fuzzy numbers (TFNs) (in Figure 3) to be aggregated.

Figure 3.

Triangular fuzzy numbers (TFNs) for modeling the satisfaction degree.

Definition 1.

A TFN $A = (A_{1}, A_{2}, A_{3})$ is a fuzzy number with the following membership function:

μ_{A} (x) = {\begin{matrix} \frac{x - A_{1}}{A_{2} - A_{1}} & if & A_{1} \leq x < A_{2} \\ \frac{A_{3} - x}{A_{3} - A_{2}} & if & A_{2} \leq x < A_{3} \\ 0 & otherwise \end{matrix}

(1)

All fuzzy operations in the proposed methodology are based on the arithmetic of TFN. For this reason, some arithmetic operations on TFNs are introduced below:

Fuzzy addition:

A (+) B = (A_{1} + B_{1}, A_{2} + B_{2}, A_{3} + B_{3})

(2)

Fuzzy subtraction:

A (-) B = (A_{1} - B_{3}, A_{2} - B_{2}, A_{3} - B_{1})

(3)

Fuzzy multiplication:

A (\times) B ≅ (A_{1} B_{1}, A_{2} B_{2}, A_{3} B_{3}) if A_{1}, B_{1} \geq 0

(4)

Fuzzy division:

\begin{aligned} A (/) B & ≅ (A_{1} / B_{3}, A_{2} / B_{2}, A_{3} / B_{1}) \\ if A_{1} \geq 0, B_{1} > 0 \end{aligned}

(5)

Let the performance of smart healthcare application q in optimizing criterion i be indicated with

p_{q i}

. For example, according to Table 2 and Figure 2,

p_{q 1} = (4, 5, 5)

. After aggregation using the arithmetic for TFNs,^52,53 the overall performance of the smart healthcare application is derived as

\begin{aligned} O_{q} = (O_{q 1}, O_{q 2}, O_{q 3}) = \frac{1}{n} \sum_{i = 1}^{n} p_{q i} \\ = (\frac{1}{n} \sum_{i = 1}^{n} p_{q i 1}, \frac{1}{n} \sum_{i = 1}^{n} p_{q i 2}, \frac{1}{n} \sum_{i = 1}^{n} p_{q i 3}) \end{aligned}

(6)

A larger

O_{q}

represents a higher sustainability of the smart healthcare application⁵⁴:

Sustainability is “very high” if $O_{q 2}$ is closer to 5 than the cores of the other TFNs.

Sustainability is “high” if $O_{q 2}$ is closer to 4.

Sustainability is “moderate” if $O_{q 2}$ is closer to 2.5.

Sustainability is “low” if $O_{q 2}$ is closer to 1.

Sustainability is “very low” if $O_{q 2}$ is closer to 0.

MCDM technique

Many MCDM methods have been to this field, for example, FWA,^4,55 fuzzy analytic hierarchy process (FAHP),^4,6,17,56,57 FTOPSIS,^6,17,58 fuzzy Vise Kriterijumska Optimizacija I Kompromisno Resenje (fuzzy VIKOR),^56,59 fuzzy combinative distance-based assessment,⁵⁷ fuzzy inference systems,^60,61 fuzzy measuring attractiveness by a categorical based evaluation technique (fuzzy MACBETH),⁶² etc. In the proposed methodology, FAHP and fuzzy VIKOR are used. However, other methods can also be applied for similar purposes.

The first step is to derive the fuzzy priorities of criteria for evaluating the overall performance of a smart healthcare application. To this end, the decision maker compares the relative priorities of the criteria in pairs, and constructs a fuzzy judgment matrix $A = [a_{i j}]$ to store the pairwise comparison results. $a_{i j}$ is the relative priority of criterion i over criterion j. $a_{j i} = 1 / a_{i j}$ ; $a_{i i} = 1$ ; i, j = 1 ∼ n. The fuzzy priorities of criteria are derived from the fuzzy judgment matrix by performing a fuzzy eigen analysis⁶³:

\det (A (-) λ I) = 0

(7)

(A (-) λ I) (\times) x = 0

(8)

w = [w_{i}] = N (x)

(9)

where

λ

and

x

are the fuzzy maximal eigenvalue and eigenvector of

A

, respectively;

w_{i}

is the fuzzy priority of criterion i. (−) and (×) denote fuzzy subtraction and multiplication, respectively. N() is the normalization function. The pairwise comparison results are consistent if the consistency ratio of

A

satisfies⁶⁴

C R (A) = \frac{λ - n}{(n - 1) R I} \leq 0.1

(10)

RI is the random consistency index.⁶⁴ The fuzzy eigen analysis aims to minimize the sum of square deviations⁶⁵:

Min Z_{1} = \sum_{i = 1}^{n} {\sum_{j \neq i} (\frac{w_{i}}{w_{j}} (-) a_{i j})}^{2}

(11)

Solutions to the fuzzy eigenanalysis can be derived exactly using ACO⁶⁶ or approximately using FGM,^4,6,23 fuzzy extent analysis,⁶⁷ or fuzzy inverse of column sum method.⁶⁸

Subsequently, the derived fuzzy priorities of criteria, as well as the performances of smart healthcare applications to be compared, are fed into the fuzzy VIKOR method. In the fuzzy VIKOR method, the overall performance of smart healthcare application q is evaluated as^56,59:

\begin{aligned} Q_{q} = ω N (S_{q}) (+) (1 - ω) N (R_{q}) \\ = ω \cdot \frac{S_{q} (-) min_{r} S_{r}}{max (max_{r} S_{r}) - min (min_{r} S_{r})} (+) \\ (1 - ω) \cdot \frac{R_{q} (-) min_{r} R_{r}}{max (max_{r} R_{r}) - min (min_{r} R_{r})} . \end{aligned}

(12)

where

S_{q} = \sum_{i = 1}^{n} (w_{i} (\times) d_{q i})

(13)

R_{q} = max_{i} (w_{i} (\times) d_{q i}) .

(14)

and ω is a pre-specified constant within [0, 1].

d_{q i}

is the distance between smart healthcare application q and a reference point (the ideal solution), which is usually measured as^56,59

d_{q i} = \frac{max_{r} (p_{r i}) (-) p_{q i}}{max_{r} (p_{r i 3}) - min_{r} (p_{r i 1})} .

(15)

Obviously,

d_{q i}

should be the smaller the better, so are

S_{q}

R_{q}

, and

Q_{q}

S_{q}

evaluates the average performance of smart healthcare application q, while

R_{q}

focuses on the worst performance.

Q_{q}

is a compromise between

S_{q}

and

R_{q}

. Basically, the smart healthcare application with the lowest

Q_{q}

has the highest sustainability. Information based on

S_{q}

and

R_{q}

can be used to break possible ties.

Time-series technique

The time-series approach considers the growth of the market size of a smart healthcare application as a time series,⁶⁹ thereby predicting the market size in the coming years based on the past. To this end, stochastic, fuzzy, and gray methods^70–72 can deal with inherent uncertainties. Among them, fuzzy methods are particularly suitable due to their ease of understanding and calculation.⁷³ The time-series technique used in the proposed methodology attempts to fit the relationship between the deseasonalized market size and time with a fuzzy linear regression equation^74–76:

y_{t} = a (+) b t

(16)

where a and b are constant.

y_{t}

is the predicted deseasonalized market size of the smart healthcare application in period t, which is approximated by a TFN.

m_{t}

is the actual value, that is, the deseasonalized market size during period t:

m_{t} = \frac{M_{t}}{φ (t)}

(17)

M_{t}

is the market size of the smart healthcare application in period t;

φ (t)

is the seasonal relative for period t.^77,78

Parameters in equation (16) can be derived by solving a quadratic programming (QP) problem^79,80:

Min Z_{2} = \sum_{t = 1}^{T} α_{t}

(18)

subject to

\sum_{t = 1}^{T} (y_{t 3} - y_{t 1}) \leq T d

(19)

y_{t 1} = a_{1} + b_{1} t; t = 1 \sim T

(20)

y_{t 2} = a_{2} + b_{2} t; t = 1 \sim T

(21)

y_{t 3} = a_{3} + b_{3} t; t = 1 \sim T

(22)

(1 - α_{t}) y_{t 1} + α_{t} y_{t 2} \leq m_{t}; t = 1 \sim T

(23)

m_{t} \leq (1 - α_{t}) y_{t 3} + α_{t} y_{t 2}; t = 1 \sim T

(24)

0 \leq α_{t} \leq 1; t = 1 \sim T

(25)

a_{1} \leq a_{2} \leq a_{3}

(26)

b_{1} \leq b_{2} \leq b_{3}

(27)

where d∈R⁺ is the tolerable width of a fuzzy market size forecast.^81,82 $α_{t}$ indicates the membership of an actual value in the corresponding fuzzy forecast. The objective function is to maximize the average membership (or satisfaction level).

Case study

Background

To illustrate the applicability of the proposed methodology, it has been used to evaluate the sustainability of eight smart healthcare applications (shown in Table 3). These smart healthcare applications were repeatedly mentioned in the literature as the most popular smart healthcare applications before, during, and/or after the COVID-19 pandemic.^2,19,83–86 Whether these smart healthcare applications are sustainable is worth studying.

Table 3.

Smart healthcare applications to be evaluated.

q	Smart technology application
1	Healthcare apps/smartphones
2	Healthcare robots
3	Remote temperature scanners
4	Smart bracelets
5	Smart clothing
6	Smart glasses, spectacles, and contact lenses
7	Smart watches
8	Social-distancing monitors

Application of the proposed methodology

In this case study, the decision maker was a market analysis manager for a healthcare-oriented company that imported and sold wearable devices. First, the qualitative technique was applied to assess the sustainability of the eight smart healthcare applications. To this end, the decision maker filled out the evaluation form (i.e. Table 2) based on his beliefs. The evaluation results are shown in Table 4.

Table 4.

Evaluation results using the qualitative technique.

Criterion	Totally dissatisfied	Somewhat dissatisfied	Moderate	Somewhat satisfied	Completely satisfied
(Healthcare apps/smartphones)
Can provide value-added services					X
Is cost-effective					X
Can promote healthy mobility					X
Is necessary or irreplaceable				X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X
(Healthcare robots)
Can provide value-added services				X
Is cost-effective		X
Can promote healthy mobility				X
Is necessary or irreplaceable		X
Can be combined with other smart technologies			X
Is easy to implement and maintain		X
(Remote temperature scanners)
Can provide value-added services					X
Is cost-effective					X
Can promote healthy mobility				X
Is necessary or irreplaceable		X
Can be combined with other smart technologies				X
Is easy to implement and maintain					X
(Smart bracelets)
Can provide value-added services					X
Is cost-effective					X
Can promote healthy mobility					X
Is necessary or irreplaceable		X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X
(Smart clothing)
Can provide value-added services					X
Is cost-effective		X
Can promote healthy mobility					X
Is necessary or irreplaceable		X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X
(Smart glasses, spectacles, and contact lenses)
Can provide value-added services					X
Is cost-effective	X
Can promote healthy mobility					X
Is necessary or irreplaceable			X
Can be combined with other smart technologies					X
Is easy to implement and maintain	X
(Smart watches)
Can provide value-added services					X
Is cost-effective				X
Can promote healthy mobility					X
Is necessary or irreplaceable		X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X
(Social-distancing monitors)
Can provide value-added services		X
Is cost-effective		X
Can promote healthy mobility					X
Is necessary or irreplaceable				X
Can be combined with other smart technologies					X
Is easy to implement and maintain		X

After aggregating the TFNs for representing these linguistic terms, the overall performance (i.e. sustainability) of each smart healthcare application was derived. The results are summarized in Table 5.

Table 5.

Sustainability evaluation results of smart healthcare applications.

q	Smart technology application	$O_{q}$	Sustainability
1	Healthcare apps/smartphones	(3.17, 4.17, 4.5)	High
2	Healthcare robots	(1.25, 2.25, 3.25)	Moderate
3	Remote temperature scanners	(3, 4, 4.5)	High
4	Smart bracelets	(2.67, 3.67, 4)	High
5	Smart clothing	(2, 3, 3.5)	Moderate
6	Smart glasses, spectacles, and contact lenses	(2.25, 2.92, 3.42)	Moderate
7	Smart watches	(2.5, 3.5, 4)	High
8	Social-distancing monitors	(1.83, 2.83, 3.5)	Moderate

Second, to apply the MCDM technique, the decision maker compared the relative priorities of criteria in terms of the following fuzzy judgment matrix:

A = [\begin{matrix} 1 & (1, 3, 5) & (5, 7, 9) & (1, 3, 5) & (3, 5, 7) & (2, 4, 6) \\ 1 / (1, 3, 5) & 1 & (6, 8, 9) & (1, 3, 5) & (2, 4, 6) & (1, 3, 5) \\ 1 / (5, 7, 9) & 1 / (6, 8, 9) & 1 & 1 / (4, 6, 8) & 1 / (1, 3, 5) & 1 / (5, 7, 9) \\ 1 / (1, 3, 5) & 1 / (1, 3, 5) & (4, 6, 8) & 1 & (1, 1, 3) & 1 / (1, 3, 5) \\ 1 / (3, 5, 7) & 1 / (2, 4, 6) & (1, 3, 5) & 1 / (1, 1, 3) & 1 & 1 / (3, 5, 7) \\ 1 / (2, 4, 6) & 1 / (1, 3, 5) & (5, 7, 9) & (1, 3, 5) & (3, 5, 7) & 1 \end{matrix}]

cFGM⁵⁸ is applied to improve the accuracy and efficiency of approximating the fuzzy priorities of criteria. The results are summarized in Figure 4. The fuzzy consistency ratio was around 0.086.

Figure 4.

Approximated fuzzy priorities of criteria using calibrated fuzzy geometric mean (cFGM).

The performances of smart healthcare applications in and optimizing the various criteria were evaluated and converted into TFNs within [0, 5]. The evaluation results are summarized in Table 6.

Table 6.

Performances of smart healthcare applications.

q	$p_{q 1}$	$p_{q 2}$	$p_{q 3}$	$p_{q 4}$	$p_{q 5}$	$p_{q 6}$
1	(3, 4, 5)	(1.5, 2.5, 3.5)	(4, 5, 5)	(3, 4, 5)	(4, 5, 5)	(3, 4, 5)
2	(1.5, 2.5, 3.5)	(0, 0, 1)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(0, 1, 2)
3	(3, 4, 5)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(3, 4, 5)	(1.5, 2.5, 3.5)
4	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(0, 1, 2)	(3, 4, 5)	(4, 5, 5)	(1.5, 2.5, 3.5)
5	(0, 1, 2)	(0, 1, 2)	(0, 1, 2)	(0, 1, 2)	(4, 5, 5)	(3, 4, 5)
6	(4, 5, 5)	(0, 0, 1)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(4, 5, 5)	(0, 0, 1)
7	(3, 4, 5)	(1.5, 2.5, 3.5)	(4, 5, 5)	(3, 4, 5)	(4, 5, 5)	(3, 4, 5)
8	(3, 4, 5)	(1.5, 2.5, 3.5)	(1.5, 2.5, 3.5)	(3, 4, 5)	(4, 5, 5)	(1.5, 2.5, 3.5)

The sustainability of each smart healthcare application was then evaluated using fuzzy VIKOR. The evaluation results are summarized in Table 7. After defuzzifying $Q_{q}$ using the center-of-gravity (COG) method⁸⁷:

D (Q_{q}) = \frac{Q_{q 1} + Q_{q 2} + Q_{q 3}}{3}

(28)

Table 7.

Sustainability evaluation results using fuzzy Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR).

q	$S_{q}$	$R_{q}$	$Q_{q}$	$D (Q_{q})$	Rank
1	(0, 0.08, 0.67)	(0, 0.08, 0.27)	(0, 0, 0.44)	0.109	1
2	(0.02, 0.39, 1.27)	(0.02, 0.2, 0.46)	(0, 0.2, 0.77)	0.292	7
3	(0, 0.14, 0.83)	(0, 0.08, 0.27)	(0, 0, 0.45)	0.114	4
4	(0.02, 0.22, 0.91)	(0.02, 0.2, 0.43)	(0, 0.19, 0.69)	0.266	6
5	(0.08, 0.5, 1.46)	(0.07, 0.32, 0.61)	(0, 0.38, 1)	0.441	8
6	(0, 0.15, 0.87)	(0, 0.11, 0.46)	(0, 0.05, 0.75)	0.209	5
7	(0, 0.08, 0.67)	(0, 0.08, 0.27)	(0, 0, 0.44)	0.109	1
8	(0, 0.09, 0.71)	(0, 0.08, 0.27)	(0, 0, 0.44)	0.111	3

The sustainability of smart healthcare applications was ranked.

Third, to apply the time-series technique, the global market size of smart watches, in terms of global shipments of organic light-emitting diode smart watches by panel suppliers,⁸⁸ was used as an example (see Table 8). There was seasonality in the data. The seasonal relatives were derived. The data after removing seasonality is shown in Table 9.

Table 8.

Market size of smart watches.

Period #	Period	Market size (millions)*
1	2017 Q1	6
2	2017 Q2	6.8
3	2017 Q3	7.4
4	2017 Q4	9.5
5	2018 Q1	7
6	2018 Q2	7.8
7	2018 Q3	13.5
8	2018 Q4	22.8
9	2019 Q1	14
10	2019 Q2	14.4
11	2019 Q3	30.1
12	2019 Q4	33.8
13	2020 Q1	22.7
14	2020 Q2	26.5
15	2020 Q3	41.5
16	2020 Q4	44.7

* approximated in terms of global shipments from O’Brien.⁸⁸

Table 9.

Market size after removing seasonality.

Period #	Period	Market size after removing seasonality (millions)
1	2017 Q1	7.70
2	2017 Q2	9.35
3	2017 Q3	6.91
4	2017 Q4	7.19
5	2018 Q1	8.99
6	2018 Q2	10.73
7	2018 Q3	12.60
8	2018 Q4	17.25
9	2019 Q1	17.97
10	2019 Q2	19.81
11	2019 Q3	28.09
12	2019 Q4	25.57
13	2020 Q1	29.14
14	2020 Q2	36.45
15	2020 Q3	38.73
16	2020 Q4	33.81

The QP problem was formulated and solved using Lingo based on the data after removing seasonality. The data from the first eight quarters were used to build the forecasting model, and the remaining data were left to evaluate the forecasting performance (d = 10). The optimal solution was

a = (0.101, 0.101, 10.101)

b = (1.771, 1.771, 1.771)

Subsequently, the seasonal relatives were multiplied by the corresponding fuzzy forecasts. The forecasting results are shown in Figure 5.

Figure 5.

Forecasting results.

Discussion

Based on the experimental results, the following discussion was made:

As expected, when the qualitative technique was applied, the smart healthcare application achieving the highest sustainability was healthcare apps/smartphones. Remote temperature scanners took second place due to their success during the COVID-19 pandemic. In contrast, despite the success of healthcare robots in the same period, the decision maker subjectively believed that they would not be very sustainable.

Both the qualitative and MCDM techniques suggested that healthcare apps/smartphones were the most sustainable. Smart watches were also recommended by the MCDM technique, which gave a reason to use a third technique, the time-series technique, to confirm the sustainability of smart watches.

In time-series techniques, the fitted linear regression model had a positive slope, indicating continued growth in market size. However, the slope was essentially low ( $a_{2} = 0.101$ ) and subject to a lot of uncertainty ( $a_{3}$ was up to 10.101).

The sustainability of smart watches evaluated using various techniques (from different perspectives) were different:

Qualitative viewpoint: high (the fourth);

MCDM viewpoint: highest;

Time series: positive but highly uncertain.

The fuzzy market size forecast for each period in test data was defuzzified using the COG method, and then compared with the actual value to evaluate the forecasting accuracy in terms of mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE):

MAE = \frac{\sum_{t = 1}^{T} | m_{t} - COG (y_{t}) |}{T}

(29)

MAPE = \frac{\sum_{t = 1}^{T} | m_{t} - COG (y_{t}) | / m_{t}}{T} \cdot 100 %

(30)

RMSE = \sqrt{\frac{\sum_{t = 1}^{T} {(m_{t} - COG (y_{t}))}^{2}}{T}}

(31)

The evaluation result is

MAE = 3.61 (millions)

MAPE = 12%

RMSE = 4.59 (millions)

Conclusion

Applying smart technologies to healthcare has become a trend, and various new smart healthcare applications have been launched one after another. After the COVID-19 pandemic, some smart healthcare applications have been shown to be ineffective or inefficient. The sustainability of a smart healthcare application thus becomes an issue. Several studies have been devoted to assessing the sustainability of a smart healthcare application. However, most existing methods are from an MCDM perspective. Methods from other perspectives are lacking and may yield different evaluation results. In addition, it would be more flexible if the evaluation method could handle various data types and availability. For these reasons, this study proposes a multi-perspective fuzzy comprehensive evaluation method to evaluate the sustainability of smart healthcare applications from qualitative, MCDM, and time-series perspectives.

The proposed methodology has been applied to evaluate the sustainability of eight smart healthcare applications. According to the experimental results, the following conclusions were drawn:

The sustainability of a smart healthcare application evaluated from different perspectives may be different. For example, smart watches were assessed as the most sustainable from an MCDM perspective, but far less sustainable from a qualitative perspective than healthcare apps/smartphones, remote temperature scanners, and smart bracelets.

Nevertheless, the evaluation results generated using a technique can be confirmed using another technique. For example, both qualitative and MCDM perspectives evaluated healthcare apps/smartphones as the most sustainable smart healthcare applications. The correlation coefficient between the ranking results from the two perspectives is 0.50, which was not necessarily high enough so different viewpoints should complement each other.

The qualitative technique required the least amount of data (only the subjective evaluations of decision makers), while the MCDM technique required the largest amount of data (including both the performances of smart technology applications and the subjective evaluations of decision makers). In addition, the data required by the time-series technique was dynamic and one-dimensional, while the data required by the MCDM technique was static and multi-dimensional. Decision makers should base their selection on available data and their own requirements.

There are many methods from every perspective. Choosing different methods to evaluate the sustainability of smart healthcare applications for each perspective is a future research topic. In addition, when there are multiple decision makers, whether the evaluation results from different perspectives will diverge further or not needs to be investigated. These issues constitute suggestions for future research.

Footnotes

Contributorship

All authors contributed equally to the writing of this paper.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Ethical approval

Not required.

Informed consent statement

Not applicable.

Funding

The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: The publication fee of this paper was supported by National Science Council, Taiwan.

Guarantor

Not required.

ORCID iDs

Tin-Chih Toly Chen

Min-Chi Chiu

References

CBSA-ASFC. Sustainable development strategy, http://www.cbsa-asfc.gc.ca/agency-agence/reports-rapports/sds-sdd/sds-sdd-11-13-eng.pdf (2011, accessed 23 December 2022).

Chen

Wang

Chiu

. A multi-granularity approach for estimating the sustainability of a factory simulation model: semiconductor packaging as an example. Operat Res 2018; 18: 711–729.

Mollenkamp

. What is sustainability? How sustainabilities work, benefits, and example, https://www.investopedia.com/terms/s/sustainability.asp (2022, accessed 22 December 2022).

Chen

TCT

. Evaluating the sustainability of a smart technology application to mobile health care: the FGM–ACO–FWA approach. Complex Intell Syst 2020; 6: 109–121.

Khan

Malik

Zafar

, et al. Challenges for sustainable smart city development: a conceptual framework. Sustain Dev 2020; 28: 1507–1518.

Chen

TCT

Lin

. An FGM decomposition-based fuzzy MCDM method for selecting smart technology applications to support mobile health care during and after the COVID-19 pandemic. Appl Soft Comput 2022; 121: 108758.

Ahad

Tahir

Aman Sheikh

, et al. Technologies trend towards 5G network for smart health-care using IoT: a review. Sensors 2020; 20: 4047.

Chen

TCT

Chaovalitwongse

O’Grady

, et al. Editorial: smart technologies for improving the quality of mobile health care. Health Care Manag Sci 2020; 23: 171–172.

Wang

Park

Chung

, et al. Influential factors of smart health users according to usage experience and intention to use. Wirel Pers Commun 2014; 79: 2671–2683.

10.

Chen

Chiu

. Smart technologies for assisting the life quality of persons in a mobile environment: a review. J Ambient Intell Humaniz Comput 2018; 9: 319–327.

11.

Tat

Chen

Zhao

, et al. Smart textiles for healthcare and sustainability. ACS Nano 2022; 16: 13301–13313.

12.

Umair

Cheema

, et al. Impact of COVID-19 on IoT adoption in healthcare, smart homes, smart buildings, smart cities, transportation and industrial IoT. Sensors 2021; 21: 3838.

13.

Waheed A and Shafi J. Successful role of smart technology to combat COVID-19. In: 2020 fourth international conference on IoT in social, mobile, analytics and cloud, Palladam, India, 7–9 October 2020, pp. 772–777. IEEE.

14.

Wang

Chen

TCT

. An FNLP approach for planning energy-efficient manufacturing: wafer fabrication as an example. Procedia Manuf 2019; 38: 439–446.

15.

Chen

Lin

. INLP-BPN approach for recommending hotels to a mobile traveler. J Ambient Intell Humaniz Comput 2018; 9: 329–336.

16.

Kakderi

Oikonomaki

Papadaki

. Smart and resilient urban futures for sustainability in the post COVID-19 era: a review of policy responses on urban mobility. Sustainability 2021; 13: 6486.

17.

Chen

Wang

. Recommending suitable smart technology applications to support mobile healthcare after the COVID-19 pandemic using a fuzzy approach. Healthcare 2021; 9: 1461.

18.

Gelman

. Setting priorities for data accuracy improvements in satisficing decision-making scenarios: a guiding theory. Decis Support Syst 2010; 48: 507–520.

19.

Chen

TCT

Chiu

. Evaluating the sustainability of smart technology applications in healthcare after the COVID-19 pandemic: a hybridising subjective and objective fuzzy group decision-making approach with explainable artificial intelligence. Digit Health 2022; 8: 20552076221136381.

20.

Stević

Pamučar

Puška

, et al. Sustainable supplier selection in healthcare industries using a new MCDM method: measurement of alternatives and ranking according to COmpromise solution (MARCOS). Comput Ind Eng 2020; 140: 106231.

21.

Chen

TCT

. Introduction to fuzzy group decision-making. In: Advances in fuzzy group decision making, 2021. pp. 29–53. Cham: Springer.

22.

Guisado-Fernández

Giunti

Mackey

, et al. Factors influencing the adoption of smart health technologies for people with dementia and their informal caregivers: scoping review and design framework. JMIR Aging 2019; 2: e12192.

23.

Chen

. Assessing factors critical to smart technology applications to mobile health care − the fgm-fahp approach. Health Policy Technol 2020; 9: 194–203.

24.

Demaerschalk

Blegen

Ommen

. Scalability of telemedicine services in a large integrated multispecialty health care system during COVID-19. Telemed e-Health 2021; 27: 96–98.

25.

Chen

Honda

. Solving data preprocessing problems in existing location-aware systems. J Ambient Intell Humaniz Comput 2018; 9: 253–259.

26.

von Humboldt

Mendoza-Ruvalcaba

Arias-Merino

, et al. Smart technology and the meaning in life of older adults during the COVID-19 public health emergency period: a cross-cultural qualitative study. Int Rev Psychiatry 2020; 32: 713–722.

27.

Chen

TCT

. Quality control in a 3D printing-based ubiquitous manufacturing system. In: 3D printing and ubiquitous manufacturing, Switzerland, 2020, pp. 83–95. Springer.

28.

Aminikhanghahi

Wang

Cook

. Real-time change point detection with application to smart home time series data. IEEE Trans Knowl Data Eng 2018; 31: 1010–1023.

29.

Lichter

Maniar

Husain

, et al. Are national cancer centers prepared to deliver climate-smart, resilient healthcare? An overview and analysis of organizations’ sustainability plans. Int J Radiat Oncol Biol Phys 2022; 114: e339.

30.

Chen

Wang

. Hybrid big data analytics and Industry 4.0 approach to projecting cycle time ranges. Int J Adv Manuf Technol 2022; 120: 279–295.

31.

Nadeem

Hussain

Khan

, et al. Analysis of smart citizens: A fuzzy based approach. In: 2019 international conference on electrical, communication, and computer engineering, Swat, Pakistan, 24–24 July 2019, pp. 1–5. New York: IEEE.

32.

Chen

TCT

Honda

. Three-mode fuzzy co-clustering and collaborative framework. In: Fuzzy collaborative forecasting and clustering: methodology, system architecture, and applications. Cham: Springer, 2020, pp. 73–88.

33.

Anand

Singh

. Cloud based secure watermarking using IWT-Schur-RSVD with fuzzy inference system for smart healthcare applications. Sustain Cities Soc 2021; 75: 103398.

34.

Chen

. Ambient intelligence and ergonomics in Asia. J Ambient Intell Humaniz Comput 2019; 10: 4785–4787.

35.

Joshi

Rambola

. IoT-enabled vehicle assistance system of highway resourcing for smart healthcare and sustainability. In: emerging technologies for healthcare: Internet of things and deep learning models (eds M Mangla, N Sharma, P Mittal, VM Wadhwa, K Thirunavukkarasu and S Khan), 2021, pp. 337–358. MA, USA: Scrivener Publishing LLC.

36.

Debnath

Das

, et al. Edge computing-based smart healthcare system for home monitoring of quarantine patients: Security threat and sustainability aspects. In: intelligent modeling, prediction, and diagnosis from epidemiological data (ed S Bhattacharyya), 2021, pp. 189–210. London: Rouledge.

37.

Ren

Yang

. Application of smart healthcare in LTCI, outpatient mutual-aid guarantee mechanism, and sustainability of medical insurance fund for urban employees. J Healthc Eng 2022; 2022: 3406977.

38.

Chi

, et al. Knowledge management in healthcare sustainability: a smart healthy diet assistant in traditional Chinese medicine culture. Sustainability 2018; 10: 4197.

39.

Zhang

Ren

Yuan

, et al. Evaluation of smart healthcare systems and novel UV-oriented solution for integration, resilience, inclusiveness and sustainability. In: 2020 5th international conference on universal village, 24–27 October, 2020, pp. 1–28. Boston, NY: IEEE.

40.

Ouhbi

Idri

Fernández-Alemán

. Standards-based sustainability requirements for healthcare services in smart cities. In: Smart cities: development and governance frameworks (ed Z Mahmood), 2018, pp. 299–317. Cham: Springer.

41.

Demirkan

. A smart healthcare systems framework. IT Prof 2013; 15: 38–45.

42.

Lin

Wang

Chen

TCT

, et al. Evaluating the suitability of a smart technology application for fall detection using a fuzzy collaborative intelligence approach. Mathematics 2019; 7: 1097.

43.

Wang

Chen

TCT

. Assessing and comparing COVID-19 intervention strategies using a varying partial consensus fuzzy collaborative intelligence approach. Mathematics 2020; 8: 1725.

44.

Ramírez-Moreno

Keshtkar

Padilla-Reyes

, et al. Sensors for sustainable smart cities: a review. Appl Sci 2021; 11: 8198.

45.

Research and Markets. Mobile health (mHealth) market–Growth, trends, COVID-19 impact, and forecasts (2021–2026), https://www.researchandmarkets.com/reports/4520220/mobile-health-mhealth-market-growth-trends (2021, accessed 20 December 2022).

46.

Chen

. A flexible way of modelling the long-term cost competitiveness of a semiconductor product. Robot Comput Integr Manuf 2013; 29: 31–40.

47.

Demiris

Rantz

Aud

, et al. Older adults’ attitudes towards and perceptions of ‘smart home’ technologies: a pilot study. Med Inform Internet Med 2004; 29: 87–94.

48.

Chen

. A fuzzy parallel processing scheme for enhancing the effectiveness of a dynamic just-in-time location-aware service system. Entropy 2014; 16: 2001–2022.

49.

Jordan

. What is ‘smart’ technology?, http://knowit.co.nz/2011/08/what-is-smart-technology (2011, accessed 26 October 2022).

50.

Markoff

. Google cars drive themselves, in traffic, http://www.nytimes.com/2010/10/10/science/10google.html?_r=0 (2010, accessed 1 December 2022).

51.

Smith

Avis

Assmann

. Distinguishing between quality of life and health status in quality of life research: a meta-analysis. Qual Life Res 1999; 8: 447–459.

52.

Chen

TCT

. Aggregation mechanisms. In: Advances in fuzzy group decision making, 2021, pp. 73–90. Cham: Springer.

53.

Hanss

. Applied fuzzy arithmetic. Berlin, Heidelberg: Springer-Verlag, 2005.

54.

Chen

. Obtaining the optimal cache document replacement policy for the caching system of an EC website. Eur J Oper Res 2007; 181: 828–841.

55.

Chen

Wang

Chiu

. Assessing the robustness of a factory amid the COVID-19 pandemic: a fuzzy collaborative intelligence approach. Healthcare 2020; 8: 481.

56.

Lin

Chen

TCT

. Leisure agricultural park selection for traveler groups amid the COVID-19 pandemic. Agriculture 2022; 12: 111.

57.

Büyüközkan

Mukul

. Evaluation of smart health technologies with hesitant fuzzy linguistic MCDM methods. J Intell Fuzzy Syst 2020; 39: 6363–6375.

58.

Chen

Wang

. Analyzing the impact of vaccine availability on alternative supplier selection amid the COVID-19 pandemic: a cFGM-FTOPSIS-FWI approach. Healthcare 2021; 9: 71.

59.

Lin

Chen

TCT

. An intelligent system for assisting personalized COVID-19 vaccination location selection: Taiwan as an example. Digit Health 2022; 8: 20552076221109062.

60.

Hussain

Wenbi

Xiaosong

, et al. Personal home healthcare system for the cardiac patient of smart city using fuzzy logic. J Adv Inf Technol 2016; 7: 58–64. doi:10.12720/jait.7.1.58-64

61.

Agana

Ofem

Ele

. A framework for a fuzzy smart home IoT e-health support system. Lect Notes Netw Syst 2020; 69: 432–447.

62.

Pamucar

Torkayesh

Biswas

. Supplier selection in healthcare supply chain management during the COVID-19 pandemic: a novel fuzzy rough decision-making approach. Ann Oper Res 2023: 328: 977–1019.

63.

Chen

. Enhancing the efficiency and accuracy of existing FAHP decision-making methods. EURO J Decis Process 2020; 8: 177–204.

64.

Saaty

. Axiomatic foundation of the analytic hierarchy process. Manage Sci 1986; 32: 841–855.

65.

. Fuzzy least-squares priority method in the analytic hierarchy process. Fuzzy Sets Syst 2000; 112: 395–404.

66.

Chen

Lin

Chiu

. Approximating alpha-cut operations approach for effective and efficient fuzzy analytic hierarchy process analysis. Appl Soft Comput 2019; 85: 105855.

67.

Chang

. Applications of the extent analysis method on fuzzy AHP. Eur J Oper Res 1996; 95: 649–655.

68.

Ahmed

Kilic

. Fuzzy analytic hierarchy process: a performance analysis of various algorithms. Fuzzy Sets Syst 2019; 362: 110–128.

69.

Chen

. Applying a fuzzy and neural approach for forecasting the foreign exchange rate. In: computer engineering: Concepts, methodologies, tools and applications (ed M Khosrow), 2012, pp. 412–425. Pennsylvania: IGI Global.

70.

Rodrigues

Endo

Silva

. Stochastic model for evaluating smart hospitals performance. In: 2019 IEEE Latin-American conference on communications, Salvador, Brazil, 11–13 November, 2019, pp. 1–6. New York: IEEE.

71.

Chen

TCT

. Deriving the priorities of criteria. In: advances in fuzzy group decision making, 2021, pp. 29–53. Cham: Springer.

72.

Patan

Ghantasala

Sekaran

, et al. Smart healthcare and quality of service in IoT using grey filter convolutional based cyber physical system. Sustain Cities Soc 2020; 59: 102141.

73.

Chen

TCT

Honda

. Collaborative framework for fuzzy co-clustering. In: Fuzzy collaborative forecasting and clustering: Methodology, system architecture, and applications, 2020, pp. 59–62. Cham: Springer.

74.

Kazemi

Hosseinzadeh

. A multi-level fuzzy linear regression model for forecasting industry energy demand of Iran. Procedia-Soc Behav Sci 2012; 41: 342–348.

75.

Chen

. A fuzzy-neural knowledge-based system for job completion time prediction and internal due date assignment in a wafer fabrication plant. Int J Syst Sci 2009; 40: 889–902.

76.

Zheng

Hui

Yang

. Hospital trust or doctor trust? A fuzzy analysis of trust in the health care setting. J Bus Res 2017; 78: 217–225.

77.

Chen

TCT

. Capacity planning for a ubiquitous manufacturing system based on three-dimensional printing. In: 3D printing and ubiquitous manufacturing, 2020, pp. 47–61.

78.

Hylleberg

. Seasonality in regression. Massachusetts, USA: Academic Press, 2014.

79.

Peters

. Fuzzy linear regression with fuzzy intervals. Fuzzy Sets Syst 1994; 63: 45–55.

80.

Chen

Lin

. A fuzzy-neural system incorporating unequally important expert opinions for semiconductor yield forecasting. Int J Uncertain Fuzziness Knowl-Based Syst 2008; 16: 35–58.

81.

Jeang

Hwan

Chen

. A statistical dimension and tolerance design for mechanical assembly under thermal impact. Int J Adv Manuf Technol 2002; 20: 907–915.

82.

Chen

. A tailored non-linear fluctuation smoothing rule for semiconductor manufacturing factory scheduling. Proc IMechE, Part I: J Systems Control Engineering 2009; 223: 149–160.

83.

Abbas

Michael

. COVID-19 contact trace app deployments: Learnings from Australia and Singapore. IEEE Consum Electron Mag 2020; 9: 65–70.

84.

Chen

Lin

. Smart and automation technologies for ensuring the long-term operation of a factory amid the COVID-19 pandemic: an evolving fuzzy assessment approach. Int J Adv Manuf Technol 2020; 111: 3545–3558.

85.

Kaiser

Al Mamun

Mahmud

, et al. Healthcare robots to combat COVID-19. In: COVID-19: Prediction, decision-making, and its impacts (eds KC Santosh and A Joshi), 2021, pp. 83–97. Singapore: Springer.

86.

Nichols

. Disinfecting robots to fight coronavirus run into travel bans, https://www.zdnet.com/article/disinfecting-robots-to-fight-coronavirus-run-into-travel-bans/ (2021, accessed 23 December 2022).

87.

Van Broekhoven

De Baets

. Fast and accurate center of gravity defuzzification of fuzzy system outputs defined on trapezoidal fuzzy partitions. Fuzzy Sets Syst 2006; 157: 904–918.

88.

O’Brien

. OLED panel revenues surging to all time high in Q4 2020, https://www.displaysupplychain.com/blog/oled-panel-revenues-surging-to-all-time-high-in-q4-2020 (2020, accessed 21 December 2022).

Assessing the sustainability of smart healthcare applications using a multi-perspective fuzzy comprehensive evaluation approach

Abstract

Keywords

Introduction

Literature review

Proposed methodology

Qualitative technique

MCDM technique

Time-series technique

Case study

Background

Application of the proposed methodology

Discussion

Conclusion

Footnotes

Contributorship

Declaration of conflicting interests

Ethical approval

Informed consent statement

Funding

Guarantor

ORCID iDs

References