Evaluation of health factors on artificial intelligence and the internet of things-based older adults healthcare programmes

Abstract

Objective

This study evaluates Artificial intelligence and the Internet of Things-based older adults' healthcare programmes (AI·IoT-OAHPs), which offer non-face-to-face and face-to-face health management to older adults for health promotion.

Methods

The study involved 146 participants, adults over 60 who had registered in AI·IoT-OAHPs. This study assessed the health factors as the outcome of pre- and post-health screening and health management through AI·IoT-OAHPs for six months.

Results

Preand post-health screening and management through AI·IoT-OAHPs were evaluated as significant outcomes in 14 health factors. Notably, the benefits of post-cognitive function showed a twofold increase in older female adults through AI·IoT-OAHPs. Adults over 70 showed a fourfold increase in post-walking days, a threefold in post-dietary practice, and a twofold in post-cognitive function in the post-effects compared with pre via AI·IoT-OAHPs.

Conclusions

AI·IoT-OAHPs seem to be an effective program in the realm of face-to-face and non-face-to-face AI·IoT-based older adults' healthcare initiatives in the era of COVID-19. Consequently, the study suggests that AI·IoT-OAHPs contribute to the upgrade in health promotion of older adults. In future studies, the effectiveness of AI·IoT-OAHPs can be evaluated as a continuous project every year in the short term and every two years in the long term.

Keywords

Artificial intelligence and internet of things older adults health factors health screening and management

Introduction

In the Corona era, many older adults have weak immune systems and are vulnerable to infectious diseases. Older adults need to strengthen their self-health management capabilities and efficiently expand health management services for older adults in the community. Therefore, older adults need to be offered non-face-to-face and face-to-face health management for health promotion through artificial intelligence and the internet of things-based older adults healthcare programmes (AI·IoT-OAHPs). These programmes use various health apps and devices to provide health screening and health management services as health factors for older adults.^1–5 As the primary health programme evaluation of AI·IoT-OAHPs, our most significant concern is the effect on older adults’ health promotion programmes. However, there is little evaluation of the effectiveness of health screening and health management for health promotion in older adults through AI·IoT-OAHPs. Therefore, older adults’ health effects can be evaluated, including health screening and health management services as health factors to health promotion among older adults through AI·IoT-OAHPs.

Due to the convergence of artificial intelligence (AI) and internet of things (IoT) technologies, network-linked biomedical devices with software applications advance older adults’ health factors.² The health promotion of older adults can be evaluated by various health factors, including weight, body mass index, grip strength (GS), equilibrium, systolic and diastolic blood pressures (SBP and DBP), blood sugar (BS), physical activity, and cognitive function through AI·IoT-OAHPs. These health factors can serve as effective indicators that contribute to the progress of strategies aimed at health promotion among older adults.^6,7

Research on AI·IoT-OAHPs has been conducted in various countries.^8–13 However; the health factors influencing health promotion among the older population remain unclear.^14–17 In particular, a retrospective analysis of AI·IoT-OAHPs can contribute to a better understanding of health promotion within older adults, facilitating the identification of the most significant determinants of health factors.^18–20 However, the application of IoT in healthcare remains insufficient.²¹

Recently, in studies, IoT-based systems have been pivotal in ensuring effective and equally accessible rehabilitation for older adults.²² Furthermore, IoT was used in stroke medical care to develop and implement a medical cloud computing system for systematic stroke intervention.²³ In addition, an IoT framework for monitoring and controlling human heartbeat rates has been explored.²⁴ However, there are few research results on health factors for improving the health of older adults through AI·IoT-OAHPs.

Several studies estimating health factors among older adults across various countries between 2020 and 2023 have revealed the weight, GS, and SBP in the context of health promotion of older adults.^25–27 In particular; the increase in GS was linked to improved health among older adults.^25,27–29 Certain studies have explored the impact of blood glucose levels on complications.^30–31 In other areas, they studied the relationship between older adults’ health factors and meal frequency, cognitive function, equilibrium and frailty.^32–33 However, these health factors in health screening and management factors via AI·IoT-OAHPs have rarely been evaluated.

While the determinants of health factors are well established, it remains unclear whether ageing health promotion can influenced by health factors through AI·IoT-OAHPs.^1,34–36 In particular, research on the components of health factors via AI·IoT-OAHPs concerning the health promotion of older adults can be limited. However, health promotion in older adults can be predicted by measuring health factors through AI·IoT-OAHPs, including health screening and health management.^25,37–40

The primary hypothesis presented in this study posits that as health factors can be influenced through AI·IoT-OAHPs, health promotion among older adults will be correspondingly improved.^10,34,41 This study assesses potential health factors for health promotion among older adults, using several health indexes through the AI·IoT-OAHPs that encompass health screening and health management as health factors at the individual level.^{18–20,30–32,42} Consequently, in this study, health factors will be assessed for effect on the health promotion of older adults with various health indicators via AI·IoT-OAHPs.

Therefore, the study observes the pre- and post-checkup of health factors from a health screening and management perspective via AI·IoT-OAHPs. These programmes use various health apps and devices to provide health screening and health management services as health factors for older adults in 6 months. Furthermore, the study has investigated post-checkups in age and gender via AI·IoT-OAHPs. Overall, this study assessed the potential of health factors for health promotion in older adults through AI·IoT-OAHPs.

Methods

The framework of this study

The framework proposed in this study depicts the evaluation of health factors for the health promotion of older adults through AI·IoT-OAHPs. Health promotion among older adults can be assessed in AI·IoT-OAHPs by the various health factors. As a conceptual framework, the health promotion of older adults via AI·IoT-OAHPs may differ in performance in health factors. This study proposes a healthy ageing framework focusing on health factors, including health screening and health management, as targets for promoting health among older adults.^20,43–45 The study assumed that appropriate prevention and promotion of health factors via AI·IoT-OAHPs resulted in changes in health promotion of older adults, such as health factors from a health screening perspective and health factors from a health management perspective.

This study hypothesized that the process [Inputs] and [Progress] predict [Outputs] to assess health factors in older adults (Figure 1). The study set the health factors as follows: (a) [Inputs] is the registration in older Adults who hope to participate in the AI·IoT-OAHPs; (b) [Progress I] is performed pre-health screening evaluation as first face-to-face; [Progress II] involves input health factors executing health management via AI·IoT-OAHPs with non-face-to-face as the distribution of device and APP; [Progress III] is performed post-health screening evaluation as second face-to-face; (c) [Outputs] include post-measurement of all health factors after 6 months, and Evaluation of Pre- & Post-health factors in health screening and health management via AI·IoT-OAHPs (Figure 1). In addition, [Inputs], [Progress], and [Outputs] focus on short-term considerations of all health factors but encompass both short and long-term effects on health promotion in older adults.^20,46 Health promotion of older adults via AI·IoT-OAHPs includes improving self-health management ability, delayed frailty, and improved quality of life as a specific objective.⁴⁷

Figure 1.

The framework of this study.

These assessed effects can explained as variations in health factors. Consequently, the study presented two distinct constructs: A conceptual process model in the evaluated method of health factors via AI·IoT-OAHPs execution and a framework comprising health promotion of older adults linked to these health factors.^20,48 Furthermore, it is worth noting that this study is building upon older adults over 60 as face-to-face and non-face-to-face via AI·IoT-OAHPs. Consequently, the [Outputs] were averaged across individuals and subjected to comparison using standard statistical methods.^6,18,20,49

Data and ethical consideration

The age distribution of the sample is those aged 60–69, 81 people, and 70–83, 65 people. Adults over 70 are a total of 65. The sample of this data evaluated health factors for each health screening and health management performance with 146 older adult participants (males 72 people, female 74 people) in a population group over 60 in AI·IoT-OAHPs registered after consented to presentation and research; consent was obtained from all the subjects. This study has been approved by the Wonkwang University Institutional Review Board (IRB-202212SB-188).

Data collection and health factors

The information and data derived from AI·IoT-OAHPs can be used to estimate and compare the health factors of older adults. This study used health factors from Jeongeup Public Health Center statistical data and databases on pre- and post-health screening and health management executed from November 2022 to April 2023 through AI·IoT-OAHPs.⁴⁷

Health factors are controllable indexes in health screening and health management for health promotion in older adults. These factors can be used to compare health disparity in either personals or groups. Such comparisons inform health promotion of older adults’ policy decisions contingent on changes in health factors.^{6–7,18,20,50–52}

Health factors can be health promotion for older adults by AI·IoT-OAHPs. Health factors that affect healthy ageing have multifactorial traits composed of various indicators.^16,18,20,53 Healthy ageing entails overall health free from disease with functional capacity and experiencing an active life in society.^{19–20,54–55} Therefore, health factors for healthy ageing should include comprehensive attributes.^18–20 However, the study did exclude addressing heredity factors related to health promotion in older adults. Instead, the study focused on upgrading health promotion for older adults as vivid and practical health factor indicators through AI·IoT-OAHPs.

Study design and area of the data

The models used in the design and area of this study assess health factors for each variable to explore the health factors for health promotion among older adults in AI·IoT-OAHPs. These advantages of models can yield a comprehensive framework encompassing various components of the health promotion perspective for older adults.^{18–20,48–51} Two categories of health factors have developed in health screening and health management within the context of the health promotion of older adults. Based on these categories, this study presented the following five models.

[Model 1] of health screening assesses variations in weight, body mass index, GS, equilibrium, SBP and DBP, and BS. [Model 2] of health management evaluates differences in walking days for 30 min, moderate-intensity activity days, strength exercise days a week, dietary practices, overall and social frailty, and cognitive function. [Model 3] assesses differences by classified age 60–69 vs 70–83 of pre- and post-health screening and management via AI·IoT-OAHPs. [Model 4] of health screening and management evaluates the effects of post-SBP and post-cognitive function on the gender of older adults who participated in AI·IoT-OAHPs. Last, [Model 5] assesses disparities by classifying adults over 70 of pre- and post-health screening and management via AI·IoT-OAHPs.

Data analysis

Appraising health factors in AI·IoT-OAHPs induced the five models from health screening and management perspectives. These variables reflect the health factors that promote the health of older adults. The assessment of pre and post-health factors for health promotion among older adults within these models in AI·IoT-OAHPs is assessed using Paired T-tests to estimate the paired difference and interval pot models. The significance level is evaluated based on p < 0.01 and 0.05. Furthermore, the binary logistic regression analysis is used to assess pre and post-health factors for the health screening and management models in AI·IoT-OAHPs.

The 6-step process of AI·IoT-OAHPs

AI·IoT-OAHPs are co-developed by the Ministry of Health and Welfare, the Korea Health Development Promotion Institute and the Korea Social Security Information Service in South Korea.⁴⁷ The AI·IoT-OAHPs execute a step-by-step service process from Step 1 to Step 6 (Figure 2).

Figure 2.

The 6-step process of artificial intelligence and the internet of things-based older adults’ healthcare programmes (AI·IoT-OAHPs).

In 1 Step, one hundred forty-six older adults over 60 living in Jeongeup-gun participated in AI·IoT-OAHPs. In Step 2, after initiating the programmes, pre-measuring health factors of health screening is implemented for two weeks as the first face-to-face. In step 3, the devices are distributed and APP executed, such as a wrist activity metre, Bluetooth scale, · blood pressure and BS metere, and general type AI speaker—older adults living alone and frail.

In Step 4, as non-face-to-face healthcare management, such as health information monitoring once a week, a mission is given and input and checking: walking and exercising, measuring blood pressure and BS daily and dietary practice over 5 days a week. In the non-face-to-face step, the healthy group received monthly monitoring and messages, and the previously frailed group underwent weekly monitoring when biometric abnormalities (SBP ≥ 140 mmHg, DBP ≥ 90 mmHg, fasting BS ≥ 126 mg/dL) via using the devices distributed.⁴⁷ In addition, the missions of health factors in health management included assessing dietary practices of more than 5 days a week, measuring BS and blood pressure, and walking and exercise evaluation. In Step 5, the second face-to-face follow-up is the post-health screening and management assessment. The post-post-health screening and management of health factors in 146 older adults are measured for two weeks after 6 months after participating in the AI·IoT-OAHPs programmes. Health screening, health management, and frailty evaluation as a measure of health factors are as follows (Figure 3)⁴⁷:

Figure 3.

Pre & post-health factors as a measure of artificial intelligence and the internet of things-based older adults’ healthcare programmes (AI·IoT-OAHPs).

Results

Characteristics of health factors of older adults who participated

(Table 1) describes the health factors of older adults who participated in AI·IoT-OAHPs. The average age of participants was approximately 70, and the average BMI was 25.06, indicating stage one obesity, which falls within the range of 25–29.9.⁴⁷ The average GS was 53.8 (standard deviation 8.03), which was weak based on age. The balance measure average of the current participating group is 9 s. Average SBP and DBP were 136.8 mmHg (standard deviation 15.02) and 83.38 mmHg (standard deviation 9.10), respectively, indicating prehypertension.

Table 1.

Characteristics of health factors of older adults who participated in artificial intelligence and the internet of things-based older adults’ healthcare programme (AI·IoT-OAHPs) (N = 146)

Variables	Mean	SD	Minimum	Median	Maximum
Age	69.66	4.716	65	69	83
Weight	65.15	9.403	40.2	65.7	88.1
Body mass index	25.06	3.054	15.96	24.83	34.39
Grip strength	27.96	8.031	12.8	27.2	53.8
Equilibrium	8.993	1.041	7	9	12
Systolic blood pressure	136.8	15.02	100	135	196
Diastolic blood pressure	83.38	9.095	55	82	109
Blood sugar	141.4	47.36	19	130	386
Walking days over 30 min per week	5.904	1.959	0	7	7
Over10 min of Moderate-intensity activity days per week	1.548	2.427	0	0	7
Strength training days per week	0.726	1.814	0	0	7
Dietary practice over 5 days per week	7.911	1.328	4	8	10
Overall frailty	0.562	0.838	0	0	4
Social frailty	0.144	0.352	0	0	1
Cognitive function	4.534	0.645	2	5	5

Furthermore, the mean BS level was 141.4 mg/dL (standard deviation 47.36). Moreover, the average cognitive function of the participants was 4.534. The overall (regular < 2.5) and social fragility (standard = 0) were 0.562 and 0.144, respectively. Therefore, the infirmity and cognitive function, aside from social fragility, were almost normal. Dietary practice of more than 5 days a week was unexceptional. In addition, the average levels of blood glucose were low.

Evaluation for health screening in Al·IoT-OAHPs

The evaluation of Model 1 health factors in health screening for older adults who participated in Al·IoT-OAHPs is presented in (Table 2).

Table 2.

Estimation for health screening of older adults who participated in AI·IoT-OAHPs (N = 146).

Model & health factors	Mean	Difference	SD	95% CI	t-value	p-value
Model 1
Pre and post-health screening
Weight	65.155	0.319	1.63	0.053, 0.585	2.37	0.019
Weight	64.836	0.319	1.63	0.053, 0.585	2.37	0.019
BMI	25.064	0.174	0.84	0.036, 0.312	2.51	0.014
BMI	24.892	0.174	0.84	0.036, 0.312	2.51	0.014
Grip strength	27.961	−1.702	3.94	−2.347, −1.059	−5.22	0.001
Grip strength	29.663	−1.702	3.94	−2.347, −1.059	−5.22	0.001
Equilibrium	8.993	1.601	1.31	1.387, 1.814	14.81	0.001
Equilibrium	7.393	1.601	1.31	1.387, 1.814	14.81	0.001
Systolic blood pressure	136.82	6.011	13.6	3.792, 8.221	5.36	0.001
Systolic blood pressure	130.81	6.011	13.6	3.792, 8.221	5.36	0.001
Diastolic blood pressure	83.386	5.124	9.14	3.624, 6.624	6.75	0.001
Diastolic blood pressure	78.262	5.124	9.14	3.624, 6.624	6.75	0.001
Blood sugar	141.42	7.601	45.8	0.12, 15.10	2.01	0.046
Blood sugar	133.82	7.601	45.8	0.12, 15.10	2.01	0.046

CI: Confidence Interval; AI·IoT-OAHP: artificial intelligence and the internet of things-based older adults’ healthcare programme; BMI: body mass index.

A significant difference was observed between the pre-health screening checkup and the 6-month post-checkup through Al·IoT-OAHPs. It was GS (p < 0.001), equilibrium (p < 0.001), SBP (p < 0.001), DBP (p < 0.001), BMI (p < 0.014), weight (p < 0.019), and BS (p < 0.046).

Body weight and BMI decreased, whereas GS increased except for Equilibrium indicators (Figures 4–7). SBP and DBP diminished, while BS levels were also reduced (Figures 8–10). Therefore, the health screening of older adults who participated in AI·IoT-OAHPs proved effective in health promotion among older adults.

Figure 4.

Weight & Weight1.

Figure 5.

Body mass index and body mass index1.

Figure 6.

Grip strength and grip strength1.

Figure 7.

Equilibrium and equilibrium1.

Figure 8.

Systolic blood pressure and systolic blood pressure1.

Figure 9.

Diastolic blood pressure and diastolic blood pressure1.

Figure 10.

Blood sugar and blood sugar1.

Assessment for health management in Al·IoT-OAHPs

The assessment of Model 2 health factors in health management among older adults who participated in Al·IoT-OAHPs is described in Table 3. In summary, a significant difference was observed between the pre-health management checkup and the 6-month post-checkup health management period.

Table 3.

Estimation for health management of older adults who participated in AI·IoT-OAHPs (N = 146).

Model & health factors	Mean	Difference	SD	95% CI	t-value	p-value
Model 2
Pre and post-health management
Walking days over 30 min per week	5.904	−0.9590	1.8	1.254, 0.664	−6.42	0
Walking days over 30 min per week	6.863	−0.9590	1.8	1.254, 0.664	−6.42	0
Over 10 min of moderate-intensity activity days per week	1.548	−0.2055	0.5	0.293, 0.117	−4.62	0
Over 10 min of moderate-intensity activity days per week	1.753	−0.2055	0.5	0.293, 0.117	−4.62	0
Strength training days per week	0.726	−0.0822	0.4	0.142, 0.023	−2.74	0.01
Strength training days per week	0.808	−0.0822	0.4	0.142, 0.023	−2.74	0.01
Dietary practice over 5 days per week	7.911	−0.7534	1	0.920, 0.586	−8.92	0
Dietary practice over 5 days per week	8.664	−0.7534	1	0.920, 0.586	−8.92	0
Overall frailty	0.562	0.1164	0.6	0.019, 0.213	2.37	0.02
Overall frailty	0.445	0.1164	0.6	0.019, 0.213	2.37	0.02
Social frailty	0.144	0.0342	0.2	0.004, 0.064	2.27	0.03
Social frailty	0.11	0.0342	0.2	0.004, 0.064	2.27	0.03
Cognitive function	4.534	−0.1233	0.4	0.184, 0.063	−4.03	0
Cognitive function	4.658	−0.1233	0.4	0.184, 0.063	−4.03	0

CI: confidence interval.; AI·IoT-OAHP: artificial intelligence and the internet of things-based older adults’ healthcare programme.

The number of days with walking for more than 30 min per week, engaging in moderate-intensity exercise for 10 min or more per week, participating in strength training days per week, and practising dietary habits for more than 5 days per week all significantly increased (Figures 11–14).

Figure 11.

Walking days for 30 min and walking days for 30 min1.

Figure 12.

Moderate-intensity activity and moderate-intensity activity1.

Figure 13.

Strength training of days and strength training of days1.

Figure 14.

Dietary practice and dietary practice1.

Furthermore, there was a decrease in overall frailty and social fragility, with an increase in cognitive function (Figures 15–17). As a result, the health factors of health management programmes for older adults who participated in AI·IoT-OAHPs proved effective in promoting healthy ageing.

Figure 15.

Overall frailty and overall frailty1.

Figure 16.

Social frailty and social frailty_1.

Figure 17.

Cognitive fuction and cognitive fuction_1.

Assessment for health screening and health management by age

The evaluation of Model 3 of health factors in pre- and post-health screening and health management by age of older adults who participated in Al·IoT-OAHPs is described in (Table 4). In summary, a significant difference was observed between pre-and post-health screening and between pre-and post-health management by age.

Table 4.

Estimation for health factors of older adults who participated in AI·IoT-OAHPs (N = 146).

Model & health factors	Mean	Difference	SD	95% CI	t-value	p-value
Model 3
Pre and post-health screening & health management by age
Pre and Post-grip strength
Aged 60–69^a	27.568	−1.637	4.1	−2.543, −0.731	−3.59	0.001
Aged 60–69^a	29.205	−1.637	4.1	−2.543, −0.731	−3.59	0.001
Aged 70–83^a	28.601	−1.634	3.74	−2.561, −0.707	−3.52	0.001
Aged 70–83^a	30.234	−1.634	3.74	−2.561, −0.707	−3.52	0.001
Pre and post-equilibrium
Aged 60–69	9.012	1.934	1.17	1.675, 2.193	14.88	0.001
Aged 60–69	7.078	1.934	1.17	1.675, 2.193	14.88	0.001
Aged 70–83	8.969	1.184	1.36	0.848, 1.521	7.04	0.001
Aged 70–83	7.785	1.184	1.36	0.848, 1.521	7.04	0.001
Pre and post-systolic blood pressure
Aged 60–69	135.71	6.26	14.6	3.02, 9.51	3.85	0.001
Aged 60–69	129.44	6.26	14.6	3.02, 9.51	3.85	0.001
Aged 70–83	138.21	5.69	12.2	2.68, 8.71	3.77	0.001
Aged 70–83	132.51	5.69	12.2	2.68, 8.71	3.77	0.001
Pre and post-diastolic blood pressure
Aged 60–69	80.09	5.83	9.39	3.73, 7.92	5.55	0.001
Aged 60–69	78.26	5.83	9.39	3.73, 7.92	5.55	0.001
Aged 70–83	82.52	4.26	8.81	2.08, 6.44	3.91	0.001
Aged 70–83	78.26	4.26	8.81	2.08, 6.44	3.91	0.001
Pre and post-walking days over 30 min per week
Aged 60–69	5.827	−1.062	1.81	−1.461, −0.663	−5.29	0.001
Aged 60–69	6.889	−1.062	1.81	−1.461, −0.663	−5.29	0.001
Aged 70–83	6.001	−0.892	1.88	−1.358, −0.437	−3.83	0.001
Aged 70–83	6.892	−0.892	1.88	−1.358, −0.437	−3.83	0.001
Pre and post-dietary practice over 5 days per week
Aged 60–69	8.074	−0.667	0.98	−0.882, −0.451	−6.16	0.001
Aged 60–69	8.741	−0.667	0.98	−0.882, −0.451	−6.16	0.001
Aged 70–83	7.708	−0.862	1.07	−1.128, −0.596	−6.47	0.001
Aged 70–83	8.569	−0.862	1.07	−1.128, −0.596	−6.47	0.001
Pre and post-cognitive function
Aged 60–69	4.5309	−0.161	0.402	−0.249, −0.072	−3.60	0.001
Aged 60–69	4.6914	−0.161	0.402	−0.249, −0.072	−3.60	0.001
Aged 70–83	4.5385	−0.092	0.34	−0.176, −0.008	−2.18	0.032
Aged 70–83	4.6308	−0.092	0.34	−0.176, −0.008	−2.18	0.032

CI: confidence interval; AI·IoT-OAHP: artificial intelligence and the internet of things-based older adults’ healthcare programme

The age distribution of the sample is those aged 60–69, 81 people, and 70–83, 65 people.

GS increased (p < 0.001) for all those aged 60–69 and 70–83, equilibrium indicators decreased (p < 0.001), and SBP and DBP diminished (p < 0.001). Therefore, the health screening of all ages of older adults who participated in AI·IoT-OAHPs proved effective in health promotion among older adults.

Pre and post-walking for more than 30 min per week and practising dietary habits for over 5 days increased significantly for all those aged 60–69 and 70–83 (p < 0.001). Furthermore, there was an increase in cognitive function for all those aged 60–69 (p < 0.001) and 70–83 (p < 0.032). As a result, the health factors of health management programmes for older adults who participated in AI·IoT-OAHPs seem adequate in healthy ageing.

Predicting health factors using logistic regression in AI·IoT-OAHPs

The study conducted logistic regression analyses to assess health factors for health promotion in older adults who participated in AI·IoT-OAHPs presented in Models 4 and 5 (Tables 5 and 6).

Table 5.

Logistic regression for health factors of older adults who participated in AI·IoT-OAHPs (N = 146).

Variables	β	SE	Wald test	Exp(β)	95% CI*	p
Model 4
Gender (Female)^a
Post-systolic blood pressure (ref = under 135)	−0.678	0.342	3.925	0.508	0.259, 0.993	0.048
Post-cognitive function (ref = over 5)	0.703	0.351	4.022	2.019	1.016, 4.012	0.045

*CI: Confidence Interval; AI·IoT-OAHP: artificial intelligence and the internet of things-based older adults’ healthcare programme.

Males 72 people, Females 74 people.

Table 6.

Logistic regression for health factors of older adults who participated in AI·IoT-OAHPs (N = 146).

Variables	β	SE	Wald test	Exp(β)	95% CI	p
Model 5
Age (Adults over 70**)
Post- Equilibrium (ref = over 9)	−1.195	0.447	7.166	0.303	0.126, 0.726	0.006
Post- Systolic blood pressure (ref = over 140)	−0.844	0.421	4.344	0.431	0.195, 0.951	0.036
Post-blood sugar (ref = over 100)	−1.065	0.497	4.588	0.346	0.130, 0.913	0.032
Post-walking days (ref = over 7)	1.431	0.689	4.304	4.179	1.082, 16.134	0.038
Post-dietary practice (ref = over 10)	1.176	0.542	4.738	3.238	1.124, 9.327	0.029
Post-cognitive function (ref = over 5)	0.772	0.350	4.845	2.161	1.088, 4.292	0.028

CI: confidence Interval; AI·IoT-OAHP: artificial intelligence and the internet of things-based older adults’ healthcare programme.

*CI: Confidence Interval; ** Adults over 70 are a total of 65.

Model 4 in Table 5, the effects on the Exp (β) for females and males were estimated as health factors for the health promotion of older adults. In comparison to male older adults, female older adults were significantly more likely to have an effect with a nearly two times post-cognitive function (Exp (β) = 2.019, p = 0.045), and female older adults were significantly more an effect 0.5 times post-SBP (Exp (β) = 0.508, p = 0.048) through AI·IoT-OAHPs.

Lastly, Model 5 (Table 6), in comparison to adults under 70, adults over 70 predicted significantly more likely to have effects of post-health factors such as post-SBP (Exp (β) = 0.303, p = 0.036) and more an effect 0.3 times post-BS (Exp (β) = 0.346, p = 0.032), an effect 0.4 times post-equilibrium (Exp (β) = 0.431, p = 0.006) and more effectiveness four times post-walking days (Exp (β) = 4.179, p = 0.038), and an effect three times post-dietary practice (Exp (β) = 3.238, p = 0.029) and more an effect two times post-cognitive function (Exp (β) = 2.161, p = 0.028) via AI·IoT-OAHPs.

Discussion

As a result of the study, findings suggested the substantial impact of health factors on health promotion among older adults in AI·IoT-OAHPs. The discussion focuses on the effect of AI·IoT-OAHPs as determinants of health factors for health promotion among older adults in Models 1, 2, 3, 4 and 5.

The results of Model 1 indicated that older adults undergoing pre- and post-health screening had higher GS and lower BS, weight, BMI and SBP and DBP after the screening through AI·IoT-OAHPs. The transition from pre- to post-health screening through AI·IoT-OAHPs showed significant improvement in the health promotion of older adults over 6 months. Notably, the indices for BS, weight, BMI and SBP and DBP did not increase in the post-health screening phase for older adults.

A recent case study reported that higher GS is associated with a lower incidence of carotid atherosclerosis in older adults,²⁷ and patients with weak GS have reduced survival compared to patients with high GS.⁵⁶ Therefore, the health factors were proven as health prevention service factors for health promotion among older adults. Health factors of health screening in the study have been assessed to remain healthy and stable through AI·IoT-OAHPs despite ageing over 60. Meanwhile, a recent case study reported a positive association between body weight and GS in men.⁵⁷ Additionally, weight and GS exhibited a positive relationship, with GS potentially being influenced by the force of weight. Therefore, if a study investigates additional health factors associated with GS, it is suggested that it be considered a healthy longevity factor in the health promotion of older adults through AI·IoT-OAHPs.²⁰

The results of Model 2 were that older adults with pre- and post-health management had a higher difference in health factors such as walking, dietary practices, and cognitive function. Specifically, there was a noteworthy increase in the frequency of walking for more than 10 min, engaging in moderate-intensity exercise, participating in daily strength training, and adhering to dietary guidelines more than 5 days a week. In particular, in comparison to adults under 70, adults over 70 predicted significantly more effects four times in post-walking days and an effect three times in post-dietary practice via AI·IoT-OAHPs (see Model 5). These findings suggested that AI·IoT-OAHPs over 70 age health management services for the health promotion of older adults were effective.

Model 3 showed that GS increased for all those aged 60–69 and 70–83, Equilibrium indicators decreased, and SBP and DBP diminished; walking and practising dietary increased significantly for all those aged 60–69 and 70–83. Furthermore, there was an increase in cognitive function for all those aged 60–69 and 70–83 (Table 4). As a result, older adults who participated in AI·IoT-OAHPs proved that programmes for all older ages adequately promote healthy ageing.

The results of Model 4 showed that older female adults undergoing pre- and post-health screening and management had lower SBP and higher cognitive function after the screening than older male adults through AI·IoT-OAHPs (Table 5). These findings underscore that females maintain healthy ageing via AI·IoT-OAHPs.

The results of Model 5 were that adults over 70 years older undergoing pre- and post-health factors screening had lower SBP and good equilibrium and more effectiveness four times walking days, three times dietary practice, and two times cognitive function compared with those under 70 via AI·IoT-OAHPs (Table 6). These findings underscore shortcuts to adults over 70 maintaining healthy ageing via AI·IoT-OAHPs.

AI·IoT-OAHPs services could evaluated as key to playing a role in the non-face-to-face Corona era. In a recent study, walking, eating habits, and walking with a companion prevent disease and alleviate loneliness.^58–60 Overall, both recent studies and this study have recognized that physical activity and a healthy diet play a favourable role in reducing frailty and that increased physical activity improves physical fitness and cognitive function in older adults.^61–63 Furthermore, this study showed a decrease in overall frailty and social infirmity, an increment in cognitive function and an accretion of physical activity via AI·IoT-OAHPs. It indicates the success of the health management approach for health promotion for older adults in AI·IoT-OAHPs.

Additionally, older adults dietary practices throughout their life through AI·IoT-OAHPs that the consumption of fish has reduced frailty in older adults, no-skipping meals lead to nutrition, sharing information about healthy food choices, and considering rich dietary habits among older adults.^64–66

In addition, frailty had worse cognition, and older adults with cognitive impairment suffered from falls.^67–68 A recent study improved the cognitive functions of older adults relating to frailty through exercise programmes.^69–70 Cognitive function is one of the most important health factors in older adults. Furthermore, in older adults, brain decline and cognitive function reduce to dementia and the quality of life.⁷¹ Therefore, conducting multilateral studies to improve cognitive function in older adults is necessary.

Therefore, these findings encourage and promote non-face-to-face physical activity through AI·IoT services during the coronavirus disease 2019 (COVID-19) pandemic. AI·IoT-OAHPs services are due to their significant role in improving physical activity, adopting healthy dietary habits, and enhancing cognition in older adults.

Specifically, maintaining SBP can serve as a preventive measure against complications, lowered blood pressure and diabetes.^72,73 Notably, this reveals that decreased SBP is associated with normal blood pressure levels.^61,74 Therefore, in essence, this study on effective management of SBP suggests the potential to prevent various health conditions among older individuals via AI·IoT-OAHPs.

Therefore, the study's results further confirm this AI·IoT-health service effect, revealing increased cognitive function and decreased SBP in female older adults and those over 70. Notably, adults over 70 have two times more cognitive function than those under 70. These insights highlight the role of AI·IoT-OAHPs as a significant health factor in preventing chronic diseases and promoting the overall health of older adults.

Overall, as a result of pre and post-health screening and health management through AI·IoT-OAHPs, the evaluated proved effects of health factors for non-face-to-face and face-to-face health promotion of older adults.

Conclusions

This study assessed the health factors as the outcome of pre- and post-health screening and health management through AI·IoT-OAHPs for 6 months. Pre- and post-health screening and management through AI·IoT-OAHPs were evaluated as significant outcomes in 14 health factors. Notably, the benefits of post-cognitive function showed a twofold increase in older female adults through AI·IoT-OAHPs. Adults over 70 showed a fourfold increase in post-walking days, a threefold in post-dietary practice, and a twofold in post-cognitive function in the post-effects compared with pre via AI·IoT-OAHPs. AI·IoT-OAHPs have proven to be an effective programme in the realm of face-to-face and non-face-to-face AI·IoT-based healthcare initiatives for older adults in the era of COVID-19. The study suggests that AI·IoT-OAHPs can contribute to the upgrade in health promotion of older adults.

Footnotes

Acknowledgements

The authors thank Chief Son Hee-Kyung of the Jeongeup City Public Health Center and related officials for their cooperation in the data research.

Author note

Jong In Kim is currently affiliated with Faculty of Health and Welfare, Wonkwang University, Republic of Korea.

Contributorship

JIK researched literature and conceived the study. JIK and GK were involved in protocol development and data analysis. JIK wrote the first draft of the manuscript. All authors reviewed and edited the manuscript and approved the final version of the manuscript.

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

This study was approved by the Wonkwang University Institutional Review Board (IRB-202212SB-188).

Funding

The authors received the following financial support for the research, authorship, and/or publication of this article: This research is supported Basic Science Research Programme through the National Research Foundation of Korea (NRF), funded by the Ministry of Education (2022R1I1A1A01069140).

Informed consent

All participants gave written informed consent in accordance with the Declaration of Helsinki.

ORCID iD

Jong In Kim

Guarantor

JIK.

Notes

References

Qian

Zhang

Yamamoto

, et al. Artificial intelligence internet of things for the elderly: From assisted living to health-care monitoring. IEEE Signal Process Mag 2021; 38: 78–88.

Manickam

Mariappan

Murugesan

, et al. Artificial intelligence (AI) and internet of medical things (IoMT) assisted biomedical systems for intelligent healthcare. Biosensors 2022; 12: 562.

Thakare

Khire

Kumbhar

. Artificial intelligence (AI) and internet of things (IoT) in healthcare: Opportunities and challenges. ECS Trans 2022; 107: 7941–7951.

Djenouri

Belhadi

Yazidi

, et al. Artificial intelligence of medical things for disease detection using ensemble deep learning and attention mechanism. Expert Syst 2022;41(6): e13093.

KHPI (Korea Health Promotion Institute). AI/IoT-based senior health care programs, https://www.khepi.or.kr/board?menuId=MENU01692&siteId=null-(2023, accessed 20 June. 2023).

Kim

. Country-level socioeconomic indicators associated with healthy life expectancy: Income, urbanization, schooling, and internet users: 2000–2012. Soc Indic Res 2016; 129: 391–402.

Kim

. Relationship between the remaining years of healthy life expectancy in older age and national income level, educational attainment, and improved water quality. Int J Aging Hum Dev 2016; 83: 402–417.

González García

Núñez Valdéz

García Díaz

, et al. A review of artificial intelligence in the internet of things. Int J Interact Multimed Artif Intell 2019; 5(4): 9–20.

Padikkapparambil

Ncube

Singh

, et al. Internet of Things technologies for elderly health-care applications . In: Emergence of pharmaceutical industry growth with industrial IoT approach. Academic Press. 2020. pp. 217–243.

10.

Zeadally

Bello

. Harnessing the power of internet of things based connectivity to improve healthcare. Internet of Things 2021; 14: 100074.

11.

Alfakeeh

Alqarni

Alyoubi

, et al. A complementary automation control for internet of things-based smart home assistance for elder adults. Pers Ubiquitous Comput 2021: 1–13.

12.

Mukati

Namdev

Dilip

, et al. Healthcare assistance to COVID-19 patient using internet of things (IoT) enabled technologies. Mater Today Proc 2023; 80: 3777–3781.

13.

Shafiq

Jamal

, , et al. Smart E-health system for heart disease detection using artificial intelligence and internet of things integrated next-generation sensor networks. J Sens 2023; 2023: 1-7.

14.

Porkodi

Kesavaraja

. Healthcare robots enabled with IoT and artificial intelligence for elderly patients. In: AI And IoT-based intelligent automation in robotics. NJ: Wiley Online Library, 2021, pp. 87–108.

15.

Cha

. Elderly perception on the internet of things-based integrated smart-home system. Sensors 2021; 21: 1284.

16.

Zhang

Long

. Analysis on Influencing Factors of Happiness of Rural Empty Nest Elderly Based on Health Internet of Things Data Mining. In: Application of Intelligent Systems in Multi-modal Information Analytics: The 4th International Conference on Multi-modal Information Analytics. Cham: Springer International Publishing, 2022, pp. 641–648.

17.

Tang

Lam

. Integration of Biot and artificial intelligence for long-term geriatric care management. In: Revolutionizing digital healthcare through blockchain technology applications. UK: IGI Global, 2023. pp. 163–186.

18.

Kim

. Factors affecting the survival probability of becoming a centenarian for those aged 70, based on the human mortality database: Income, health expenditure, telephone, and sanitation. BMC Geriatr 2014a; 14: 1–11.

19.

Kim

. Country-level socioeconomic indicators associated with survival probability of becoming a centenarian among older European adults: Gender inequality, male labour force participation and proportions of women in parliaments. J Biosoc Sci 2017; 49: 239–250.

20.

Kim

. Sociology of longevity: Socioecological factors of survival probability. London: Cambridge Scholars Publishing. 2022, pp.1–310.

21.

Ahmadi

Arji

Shahmoradi

, et al. The application of internet of things in healthcare: A systematic literature review and classification. Univers Access Inf Soc 2019; 18: 837–869.

22.

Mieronkoski

Azimi

Sequeira

, et al. Smart home technology for geriatric rehabilitation and the Internet of Things . In: Smart home technologies and services for geriatric rehabilitation. Netherlands: Elsevier, Academic Press, 2022. pp. 25–42.

23.

Ren

. Medical internet of things to realize elderly stroke prevention and nursing management. J Healthc Eng 2021; 2021: Article ID 9989602.

24.

Abba

Garba

. An IoT-based smart framework for a human heartbeat rate monitoring and control system. Proc AMIA Annu Fall Symp 2020; 42: 36.

25.

Liu

Xue

Wang

, et al. Association between hand grip strength and stroke in China: A prospective cohort study. Aging 2021; 13: 8204–8213.

26.

Wolff

Steinheimer

Warmerdam

, et al. Effects of age, body height, body weight, body mass index and handgrip strength on the trajectory of the plantar pressure stance-phase curve of the gait cycle. Front Bioeng Biotechnol 2023; 11: 1110099.

27.

Zhang

Wang

, et al. The association between grip strength and incident carotid atherosclerosis in middle-aged and older adults: The TCLSIH cohort study. Maturitas 2023; 167: 53–59.

28.

McGrath

Kraemer

Snih

, et al. Handgrip strength and health in aging adults. Sports Med 2018; 48: 1993–2000.

29.

Halaweh

. Correlation between health-related quality of life and hand grip strength among older adults. Exp Aging Res 2020; 46: 178–191.

30.

Schmidt

Stern

. DAGE: A new target for the prevention and treatment of the vascular and inflammatory complications of diabetes. Trends Endocrinal Metal 2000; 11: 368–375.

31.

Ojha

Vidwans

Watve

. Does sugar control arrest complications in type 2 diabetes? Examining rigor in statistical and causal inference in clinical trials. medRxiv 2022; 2022-08.

32.

Eshkoor

Hamid

Mun

, et al. Mild cognitive impairment and its management in older people. Clin Interv Aging 2015; 10: 687–693.

33.

Stalling

Albrecht

Foettinger

, et al. Meal patterns of older adults: Results from the OUTDOOR ACTIVE study. Nutrients 2022; 14: 2784.

34.

Sahu

Pradhan

Khasnobish

, et al. The Internet of Things in geriatric healthcare. J Healthc Eng 2021; 2021: Article ID 6611366.

35.

Nair

Kumar

. An efficient elderly disease prediction and privacy preservation using internet of things. In: The industrial internet of things (IIoT) intelligent analytics for predictive maintenance. NJ: Wiley: 2022, pp. 369–392.

36.

Muralidharan

Vijayalakshmi

. Impact of steady–state genetic algorithm and internet–of–things (IOT) on the enhancement of fall detection system and rehabilitation gaming exercises for elderly people. Int J Intell Syst 2022; 10: 45–55.

37.

Kolbe-Alexander

Lambert

Charlton

. Effectiveness of a community basedlow intensity exercise program for older adults. J Nutr Health Aging 2006; 10: 21.

38.

Millar

Levy

McGowan

, et al. Isometric handgrip training lowers blood pressure and increases heart rate complexity in medicated hypertensive patients. Scand J Med Sci Sports 2013; 23: 620–626.

39.

Bann

Hire

Manini

, , et al. Light intensity physical activity and sedentary behavior in relation to body mass index and grip strength in older adults: Cross-sectional findings from the lifestyle interventions and independence for elders (LIFE) study. PloS one 2015; 10: e0116058.

40.

Meng-Ta

LEE

Tsu-Hsin

HOWE

Chih-Chi

CHEN

, et al. Grip strength differences in middle-aged and older adults and individuals with stroke. Eur J Phys Rehabil Med 2023; 59: 294.

41.

Petrushin

Freddolini

Barresi

, et al. IoT-powered monitoring systems for geriatric healthcare: Overview. In: Scataglini S, Imbesi S and Marques G (eds) Internet of things for human-centered design. Studies in Computational Intelligence. Singapore: Springer, 2022, vol. 1011, pp. 99–122.

42.

Whiteley

Benton

Matwiejczyk

, et al. Determining dietary patterns to recommend for type 2 diabetes: An umbrella review. Nutrients 2023; 15: 861.

43.

McLeroy

Bibeau

Steckler

, et al. An ecological perspective on health promotion programs. Health Educ Q 1988; 15: 351–377.

44.

Albahri

Alwan

Taha

, et al. IoT-based telemedicine for disease prevention and health promotion: State-of-the-art. J Netw Comput Appl 2021; 173: 102873.

45.

Han

Xing

Huang

, et al. Associated factors of health-promoting lifestyle of the elderly based on the theory of social ecosystem. Atención PrIMaria 2023; 55: 102679.

46.

Kim

Choi

. Effects of air pollution on children from a socioecological perspective. BMC Pediatr 2019; 19: 1–9.

47.

MHW (Ministry of Health and Welfare, The Korea Health Development Promotion Institute, The Korea social security information service). 2023 AI·IoT-based elderly health management programs guide. Seoul: KM Communication, 2023, pp.1–73.

48.

Kim

. Effects on inequality in life expectancy from a social ecology perspective. BMC Public Health 2018; 18: –8.

49.

Kim

. Socio-ecological perspective of older age life expectancy: Income, gender inequality, and financial crisis in Europe. Global Health 2017b; 13: –8.

50.

Kim

. Labor force participation and secondary education of gender inequality index (GII) associated with healthy life expectancy (HLE) at birth. Int J Equity Health 2014b; 13: 1–8.

51.

Kim

. Social structural influences on healthy aging: Community-level socioeconomic conditions and survival probability of becoming a centenarian for those aged 65 to 69 in South Korea. Int J Aging Hum Dev 2015; 81: 241–259.

52.

Schmauck-Medina

Molière

Lautrup

, et al. New hallmarks of ageing: A 2022 Copenhagen ageing meeting summary. Aging 2022; 14: 6829.

53.

Candore

Balistreri

Listi

, et al. Immunogenetics, gender, and longevity. Ann N Y Acad Sci 2006; 1089: 516–537.

54.

Rowe

Kahn

. Human aging: Usual and successful. Science 1987; 237: 143–149.

55.

Hsu

. Impact of morbidity and life events on successful aging. Asia Pacific Journal of Public Health 2011; 23: 458–469.

56.

Dai

Laber

Chen

, et al. Hand grip strength predicts mortality and quality of life in heart failure: Insights from the Singapore cohort of patients with advanced heart failure. J Card Fail 2023; 29: 911–918.

57.

Mitsionis

Pakos

Stafilas

, et al. Normative data on hand grip strength in a Greek adult population. Int Orthop 2009; 33: 713–717.

58.

Hsu

Yang

Chen

, et al. Accumulated short bouts of walking in older adults with type 2 diabetes: Effects on glycosylated hemoglobin (HbA1c) and homeostasis model assessment of insulin resistance (HOMA-IR). Res Gerontol Nurs 2023; 16(5): 250–258.

59.

Chia

Huang

, et al. Promoting healthy behaviors in older adults to optimize health-promoting lifestyle: An intervention study. Int J Environ Res Public Health 2023; 20: 1628.

60.

Mizuta

Uchida

Sawa

, et al. Context of walking and loneliness among community-dwelling older adults: A cross-sectional study. BMC Geriatr 2023; 23: 1–6.

61.

Huang

Meng

Liu

, , et al. Global burden of disease attributable to high systolic blood pressure in older adults, 1990–2019: An analysis for the global burden of disease study 2019. Eur J Prev Cardiol 2023; 30: 917–927.

62.

Huang

Chou

Liang

, et al. Physical activity plays a crucial role in multidomain intervention for frailty prevention. Aging Clin Exp Res 2023; 35(6):1283–1292.

63.

Galle

Deijen

Milders

, et al. The effects of a moderate physical activity intervention on physical fitness and cognition in healthy elderly with low levels of physical activity: A randomized controlled trial. Alzheimers Res Ther 2023; 15: 1–23.

64.

Yokoro

Otaki

Imamura

, et al. Association between social network and dietary variety among community-dwelling older adults. Public Health Nutr 2023; 26(11): 2441–2449.

65.

Konglevoll

Andersen

Hopstock

, et al. Fish intake and pre-frailty in Norwegian older adults-a prospective cohort study: The tromsø study 1994–2016. BMC Geriatr 2023; 23: 411.

66.

Wild

Baek

Shah

, et al. The socioecological correlates of meal skipping in community-dwelling older adults: A systematic review. Nutr Rev 2023; 81: 168–179.

67.

Fhon

JRS

Silva

ARF

Lima

EFC

, et al. Association between sarcopenia, falls, and cognitive impairment in older people: A systematic review with meta-analysis. Int J Environ Res Public Health 2023; 20: 4156.

68.

Tsai

Chang

Lin

, et al. Physical frailty related to cognitive impairment and COPD exacerbation: A cross-sectional study. Respir Med 2023; 208: 107129.

69.

Zhu

Lin

Yang

, et al. Effects of exergaming on cognitive functions and loneliness of older adults with cognitive frailty. Int J Geriatr Psychiatry 2023; 38: e5944.

70.

Callisaya

Jayakody

Vaidya

, et al. A novel cognitive-motor exercise program delivered via a tablet to improve mobility in older people with cognitive impairment–StandingTall cognition and mobility. Exp Gerontol 2021; 152: 111434.

71.

Bray

Pieruccini-Faria

Witt

, et al. Frailty and functional brain connectivity (FBC) in older adults with mild cognitive impairment (MCI): Baseline results from the SYNERGIC trial. GeroScience 2023; 45: 1033–1048.

72.

Hata

Ushigome

Hosomi

, et al. Impact of continued high blood pressure on the progression of diabetic nephropathy after 10 years: KAMOGAWA-HBP study. Hypertens Res 2023; 46: 565–574.

73.

Mageed

SSA

Doghish

Ismail

, et al. The role of miRNAs in insulin resistance and diabetic macrovascular complications–A review. Int J Biol Macromol 2023; 230: 123189.

74.

Yamaguchi

Katayama

Lee

, et al. Association of sarcopenia and systolic blood pressure with mortality: A 5-year longitudinal study. Arch Gerontol Geriatr 2023; 110: 104988.