**6.2 Manate et al.**

Collecting data from things, devices and multiple sources presents a significant problem. Patients can be classified into those patients who are having elective treatment and those emergency patients who require immediate treatment [57]. Those elective patients who do not require emergency treatment may experience health deterioration and eventually require emergency treatment or tests. A hospital setting is characterised by dynamic uncertainty and a frequent need to dynamically change the treatment pathway. Manate et al. proposed the intelligent context-aware

#### **Figure 6.** *Cloud-IoT-based healthcare framework [56].*

#### **Figure 7.**

*Actors in the cloud-IoT-based healthcare framework [56].*

**Figure 8.** *Model of a typical ICADS [31].*

decision support (ICADS) system, which provides an effective basis for rescheduling and prioritising essential services while maximising the effectiveness of the staff in knowing the health status of their patients, planning emergency treatment requirements and providing quality care. Even though this system can produce exciting benefits for the stakeholders of the healthcare industry, several complexities and challenges in hospital settings need to be addressed before implementing ICADS [31]. **Figure 8** summarises this system.

#### **6.3 Datta et al.**

Many mobile health applications are still operating offline and are yet to be integrated into the semantic Web technologies for e-Health services [58].

**53**

**6.5 Roy et al.**

this framework.

**Figure 9.**

**6.4 Prayoga and Abraham**

*IOT Service Utilisation in Healthcare*

*Operational flow of the M3 framework [58].*

*DOI: http://dx.doi.org/10.5772/intechopen.86014*

Moreover, a unified rationale for developing healthcare development applications and middleware solutions is lacking. Therefore, users must build generic IoT applications to combine several domains. Datta et al. proposed the machine-tomachine (M3) framework, which enables the provision of smart, connected and personalised healthcare and wellness services to people living in smart homes [59]. This framework involves the use of wearable devices that collect patient data, which are then transmitted to smartphones that act as intermediate gateways. These data are then transmitted to remote cloud Web interfaces to maintain end-to-end security. The cloud computing platform is mainly targeted to manage patient data. However, this method does not allow patients to receive a high-level abstraction of the data collected by wearable devices [58]. **Figure 9** summarises

Prayoga and Abraham iteratively tested, applied, refined and validated the behavioural intention in technology acceptance model (TAM) as one of the most prominent models used in Greater Jakarta to identify those variables that could predict the intention of individuals to utilise IoT health devices and integrate them into a theoretical model [60]. They analysed technology acceptance from the perspective of TAM and used perceived usefulness as the main predictor of behavioural intention. They also proposed a theoretical model to outline some important predictors of the behavioural intention of individuals to use IoT health devices. They performed a questionnaire survey among 186 college students from different faculties to test the hypothesised relationships between factors. As shown in the survey results, 91% of the respondents agreed that health trackers can help them achieve their personal health goals, 89% believed that these devices can change their health patterns and 90% thought that these devices will revolutionise healthcare systems. Although 87% of these respondents had searched for health-related information online while 35% had heard about such technology, only 13% of them had actually used health track-

ers [60]. **Figure 10** summarises the IoT behavioural intention model.

Roy et al. proposed a model that facilitates the adoption of IoT-based innovations in urban poor communities [21]. This model identifies five sources of innovation,

#### **Figure 9.**

*Internet of Things (IoT) for Automated and Smart Applications*

*Actors in the cloud-IoT-based healthcare framework [56].*

**52**

**6.3 Datta et al.**

**Figure 8.**

**Figure 7.**

*Model of a typical ICADS [31].*

ICADS [31]. **Figure 8** summarises this system.

decision support (ICADS) system, which provides an effective basis for rescheduling and prioritising essential services while maximising the effectiveness of the staff in knowing the health status of their patients, planning emergency treatment requirements and providing quality care. Even though this system can produce exciting benefits for the stakeholders of the healthcare industry, several complexities and challenges in hospital settings need to be addressed before implementing

Many mobile health applications are still operating offline and are yet to be integrated into the semantic Web technologies for e-Health services [58].

Moreover, a unified rationale for developing healthcare development applications and middleware solutions is lacking. Therefore, users must build generic IoT applications to combine several domains. Datta et al. proposed the machine-tomachine (M3) framework, which enables the provision of smart, connected and personalised healthcare and wellness services to people living in smart homes [59]. This framework involves the use of wearable devices that collect patient data, which are then transmitted to smartphones that act as intermediate gateways. These data are then transmitted to remote cloud Web interfaces to maintain end-to-end security. The cloud computing platform is mainly targeted to manage patient data. However, this method does not allow patients to receive a high-level abstraction of the data collected by wearable devices [58]. **Figure 9** summarises this framework.

#### **6.4 Prayoga and Abraham**

Prayoga and Abraham iteratively tested, applied, refined and validated the behavioural intention in technology acceptance model (TAM) as one of the most prominent models used in Greater Jakarta to identify those variables that could predict the intention of individuals to utilise IoT health devices and integrate them into a theoretical model [60]. They analysed technology acceptance from the perspective of TAM and used perceived usefulness as the main predictor of behavioural intention. They also proposed a theoretical model to outline some important predictors of the behavioural intention of individuals to use IoT health devices. They performed a questionnaire survey among 186 college students from different faculties to test the hypothesised relationships between factors. As shown in the survey results, 91% of the respondents agreed that health trackers can help them achieve their personal health goals, 89% believed that these devices can change their health patterns and 90% thought that these devices will revolutionise healthcare systems. Although 87% of these respondents had searched for health-related information online while 35% had heard about such technology, only 13% of them had actually used health trackers [60]. **Figure 10** summarises the IoT behavioural intention model.

#### **6.5 Roy et al.**

Roy et al. proposed a model that facilitates the adoption of IoT-based innovations in urban poor communities [21]. This model identifies five sources of innovation,

**Figure 10.**

*IoT behavioural intention model [60].*

namely, nutrition, healthcare, employment, education and finances. They also argued that IoT can positively affect the urban poor by providing them access to various types of services, including healthcare, education and food security. Their study was conducted in four stages, including a literature review, a survey of the target users, interviews with experts and a usability test of a prototype technology system. They assumed that the implemented system needs to provide quality service to its users and that users should experience tangible benefits and receive some training. These factors can help service providers deliver excellent services to their consumers and subsequently drive a higher consumer satisfaction [21]. This model is summarised in **Figure 11**.

#### **6.6 Jagatheesan et al.**

Jagatheesan et al. argued that multiple sensors with various applications from each manufacturer are easily configurable yet are generally not preferred by their users [61]. Therefore, they proposed the multiple producer multiple consumer (MPMC) network that aggregates human interfaces to allow users to control any part of the data distribution framework. This framework includes a scenario where IoT-based multiple sensors are used as producers of data and multiple IoT services are used as consumers of these data. Their findings highlighted how the experiences and perspectives of users affect the data framework design in MPMC environments by using the drop data framework infrastructure. However, this network does not serve the needs of IoT users, and service providers are unable to choose among multiple options and the security or actual data transfer protocols are usually lacking [61]. The MPMC framework is illustrated in **Figure 12**.

#### **6.7 Bui et al.**

The researchers investigated a case of a diabetic patient in an emergency situation [29]. They proposed the IoT communication framework as the main enabler of distributed worldwide healthcare applications. The main actors in this model include the monitored patients, physicians and distributed information databases. Their findings contribute to the actual implementation of a comprehensive healthcare system within IoT. They also highlighted the importance of using different devices, networks and processes in analysing diabetes progression. However, this framework is not yet completely available, the components presented in the use case are at different stages of realisation and the proposed framework does not integrate runtime sensing information into healthcare records [29]. This model is summarised in **Figures 13** and **14**.

**55**

**6.8 Manashty et al.**

*Model of IoT-based innovations for the urban poor [21].*

**Figure 11.**

Manashty et al. aimed to fill the gap between symptoms and diagnosis trend data in order to predict health anomalies accurately and quickly [62]. Not one of the existing systems can act as a bridge between different systems to facilitate knowledge transfer and to enhance their detection and prediction capabilities. These systems are also unable to use the data and knowledge provided by similar systems due to the complexity involved in the data sharing process. Storing information also presents a challenge due to the high volume of data generated by each sensor. Therefore, Manashty et al. proposed the healthcare event aggregation lab (HEAL) model, a platform that provides services to developers and leverages the previously processed data and the corresponding detected symptoms. The proposed architecture is cloud-based and provides services for input sensors, IoT devices and context providers. The HEAL platform is an integrated system for high-level behaviour monitoring that supports many users and systems in their long-term analysis, thereby bridging the gap among many systems. However, Manashty et al. did not

*IOT Service Utilisation in Healthcare*

*DOI: http://dx.doi.org/10.5772/intechopen.86014*

*IOT Service Utilisation in Healthcare DOI: http://dx.doi.org/10.5772/intechopen.86014*

*Internet of Things (IoT) for Automated and Smart Applications*

namely, nutrition, healthcare, employment, education and finances. They also argued that IoT can positively affect the urban poor by providing them access to various types of services, including healthcare, education and food security. Their study was conducted in four stages, including a literature review, a survey of the target users, interviews with experts and a usability test of a prototype technology system. They assumed that the implemented system needs to provide quality service to its users and that users should experience tangible benefits and receive some training. These factors can help service providers deliver excellent services to their consumers and subsequently drive a higher consumer satisfaction [21]. This model is

Jagatheesan et al. argued that multiple sensors with various applications from each manufacturer are easily configurable yet are generally not preferred by their users [61]. Therefore, they proposed the multiple producer multiple consumer (MPMC) network that aggregates human interfaces to allow users to control any part of the data distribution framework. This framework includes a scenario where IoT-based multiple sensors are used as producers of data and multiple IoT services are used as consumers of these data. Their findings highlighted how the experiences and perspectives of users affect the data framework design in MPMC environments by using the drop data framework infrastructure. However, this network does not serve the needs of IoT users, and service providers are unable to choose among multiple options and the security or actual data transfer protocols are usually lack-

The researchers investigated a case of a diabetic patient in an emergency situation [29]. They proposed the IoT communication framework as the main enabler of distributed worldwide healthcare applications. The main actors in this model include the monitored patients, physicians and distributed information databases. Their findings contribute to the actual implementation of a comprehensive healthcare system within IoT. They also highlighted the importance of using different devices, networks and processes in analysing diabetes progression. However, this framework is not yet completely available, the components presented in the use case are at different stages of realisation and the proposed framework does not integrate runtime sensing information into healthcare records [29]. This model is summarised in **Figures 13** and **14**.

ing [61]. The MPMC framework is illustrated in **Figure 12**.

**54**

**6.7 Bui et al.**

summarised in **Figure 11**.

*IoT behavioural intention model [60].*

**6.6 Jagatheesan et al.**

**Figure 10.**

**Figure 11.** *Model of IoT-based innovations for the urban poor [21].*

#### **6.8 Manashty et al.**

Manashty et al. aimed to fill the gap between symptoms and diagnosis trend data in order to predict health anomalies accurately and quickly [62]. Not one of the existing systems can act as a bridge between different systems to facilitate knowledge transfer and to enhance their detection and prediction capabilities. These systems are also unable to use the data and knowledge provided by similar systems due to the complexity involved in the data sharing process. Storing information also presents a challenge due to the high volume of data generated by each sensor. Therefore, Manashty et al. proposed the healthcare event aggregation lab (HEAL) model, a platform that provides services to developers and leverages the previously processed data and the corresponding detected symptoms. The proposed architecture is cloud-based and provides services for input sensors, IoT devices and context providers. The HEAL platform is an integrated system for high-level behaviour monitoring that supports many users and systems in their long-term analysis, thereby bridging the gap among many systems. However, Manashty et al. did not

**Figure 12.** *MPMC framework [61].*

**Figure 13.** *IoT e-Health system model [29].*

**57**

*IOT Service Utilisation in Healthcare*

summarised in **Figure 15**.

*Cloud-based HEAL platform model [62].*

**6.9 Sheriff et al.**

**Figure 15.**

**6.10 Pir et al.**

*DOI: http://dx.doi.org/10.5772/intechopen.86014*

perform multiple case studies to evaluate the performance of the proposed system in complex heterogeneous scenarios with knowledge sharing [62]. This model is

Sheriff et al. proposed a reference framework for healthcare informatics and analytics by integrating IoT, complex event processing (CEP) and big data analytics [63]. This framework can serve as a reference in implementing a holistic healthcare informatics and analytics ecosystem. Integrating IoT, CEP and big data analytics technologies can solve specific problems. Specifically, CEP can support the realtime and near-real-time analytical processing of patient events from different sources by using big data and ubiquitous communication via IoT. In the future, Sheriff et al. are planning to use this framework as a foundation for developing a healthcare application system that can address the informatics and analytic needs of healthcare and other dependent industries. However, they did not test the perfor-

mance of this framework [63]. This framework is illustrated in **Figure 16**.

Pir et al. developed the HMIS framework with context awareness for developing the management systems of smart hospitals based on IoT [64]. They introduced context awareness as a middleware of the IoT architecture to overcome the problems in large data management. This framework consists of three layers, including a physical layer, network layer and application layer. The physical layer, also known as the perception layer, collects data and communicates them to the network layer. The network layer then processes and transmits these data to the application layer. Context awareness, which is located above the network layer as middleware, analyses the data and transfers only the required data to the application layer. Afterwards, the application layer defines the context of the data based on the

**Figure 14.** *IoT e-Health process model [29].*

### *IOT Service Utilisation in Healthcare DOI: http://dx.doi.org/10.5772/intechopen.86014*

*Internet of Things (IoT) for Automated and Smart Applications*

**56**

**Figure 14.**

**Figure 13.**

*IoT e-Health system model [29].*

**Figure 12.**

*MPMC framework [61].*

*IoT e-Health process model [29].*

**Figure 15.** *Cloud-based HEAL platform model [62].*

perform multiple case studies to evaluate the performance of the proposed system in complex heterogeneous scenarios with knowledge sharing [62]. This model is summarised in **Figure 15**.
