Purpose – This paper presents formulations of decision models for the innovative management of healthcare systems through the application of the Internet of Things (IoT) and Big Data Analytics (BDA). By integrating the technology of IoT and the intelligence of BDA we derive service designs that amplify the personalized, co-creative nature of effective health care. Capturing and interpreting data about patients’ needs and desires, resource availabilities (doctors, nurses, medical equipment, medical supplies and others), treatment options and potential outcomes enables a smart and adaptive health management system for planning, scheduling and coordinating service activities in a jointly managed, co-creative system. From a service-system point of view (Maglio et al., 2009), healthcare systems are configurations of people, information, organizations, and technologies operating together for mutual benefit and common objectives. The traditional approaches to the design of these service system take one of two perspectives: a patient-centric view, oriented to patient health (Polese, 2013) in terms of quality and speed of care; and a provider view, focused on resource utilization and efficiency (patient waiting time or service level is the only consideration given to the patient - Sarno and Nenni, 2016). In the new digitization era, the design and management of healthcare services should structurally incorporate both perspectives under the awareness that service itself means value co-creation among the involved actors (Vargo and Lusch, 2004), personalizing the health care experience for each patient and adapting organizational and planning processes to context variability. Large investments in fixed assets and highly trained staffs severely limit the flexibility in capacity of every healthcare service system. The inertia of the supply chain limits its ability to respond to the non-stationary nature of demand that is driven by individual patient needs. Therefore, resource allocations that are typically used in other service industries to respond to variable demand are not effective in healthcare systems. The use of IoT and BDA to generate more accurate and dynamic updates of parameters that affect demand and resource availability enables a different approach known as demand response (DR). Electric utilities are a good example of an inertia-constrained supply chain that uses IoT and BDA to enable DR (Siano and Sarno, 2016). Although healthcare service systems presently do not adopt the practice of DR, the necessary technologies are in place to do so. An essential requirement of DR is also an innovative feature of this practice – DR requires co-creation. Through the application of finite capacity scheduling (FCS) a healthcare system can utilize real-time data about patient locations, medical conditions and desires to dynamically assign patients and healthcare resources to medical procedures for improved efficiency in the use of healthcare resources and the personalization of patient care. This research formulates the key decision models that will support DR in healthcare systems and take advantage of IoT and BDA. We identify the unique tradeoffs that DR presents to the design and management of healthcare systems, specify the data requirements of the predictive models that are recommended, formulate the mathematical structure of the decision models and describe the changes to the management and culture of the healthcare ecosystem that will be necessary. Design/Methodology/approach – The formulation of adaptive, intelligent decision models for planning, scheduling and controlling health care services will be accomplished through application of the techniques of operations research guided by the perspective of Service Dominant Logic (SDL) and the Viable Systems Approach (VSA). Although these decision models can trace their pedigree to classic resource planning and scheduling models of goods-dominant research, they embody distinctive and essential features of co-creative systems. Our formulations of these models will expose these features. The state of the art in the application of IoT and BDA in healthcare enables the acquisition of massive amounts of detailed data from patient electronic medical records; real-time patient condition monitors; location devices for patients, healthcare personnel, medical equipment; social networks’ comments; resource status reports and schedules; and intelligent medical knowledge bases. Furthermore, cognitive assistants are now providing medical professionals with up-to-date knowledge to support diagnosis and treatment. Our model formulations will be directed at defining the specific model constructs that take advantage of the recent advances in IoT and BDA. Specifically, we will develop a hierarchy of models that exhibit the benefits of utilizing increasing penetrations of big data sources and increasing degrees of decision adaptation (homeostasis). Findings – 1) How can big data inform us about the needs and desires of all of the players in the health care system? 2) How can big data analytics be used in predicting patient needs and desires as well as the intentions of healthcare providers? 3) How can IoT enable the beneficial usage of big data for co-creative healthcare management? Research limitations/implications - This research represents the first step of a wider research project aimed at assessing the feasibility and the convenience of new forms of value co-creation in healthcare management. The suite of models that this research creates will initiate a quantitative evaluation of the relative performance of the models in the suite. However, this evaluation, which will be done via computer simulation, is outside the scope of the current paper. Ultimately, our models will demonstrate the specific ways in which BDA and IoT can be used effectively in healthcare management. Service innovators in the healthcare industry will be able to use the results of this stream of research to see beyond the hype of these new technologies and learn how to leverage them effectively. Originality/value – The advances in the engineering of IoT devices and the development of statistical methods for BDA have been very impressive. The applications of these technologies have been heavily promoted, but there has been very little research into the integration of IoT and BDA into model-based decision support systems. This study will be original in its foundation in decision modeling.
Integrating the internet of things and big data analytics into decision support models for healthcare management
Sarno D;
2017-01-01
Abstract
Purpose – This paper presents formulations of decision models for the innovative management of healthcare systems through the application of the Internet of Things (IoT) and Big Data Analytics (BDA). By integrating the technology of IoT and the intelligence of BDA we derive service designs that amplify the personalized, co-creative nature of effective health care. Capturing and interpreting data about patients’ needs and desires, resource availabilities (doctors, nurses, medical equipment, medical supplies and others), treatment options and potential outcomes enables a smart and adaptive health management system for planning, scheduling and coordinating service activities in a jointly managed, co-creative system. From a service-system point of view (Maglio et al., 2009), healthcare systems are configurations of people, information, organizations, and technologies operating together for mutual benefit and common objectives. The traditional approaches to the design of these service system take one of two perspectives: a patient-centric view, oriented to patient health (Polese, 2013) in terms of quality and speed of care; and a provider view, focused on resource utilization and efficiency (patient waiting time or service level is the only consideration given to the patient - Sarno and Nenni, 2016). In the new digitization era, the design and management of healthcare services should structurally incorporate both perspectives under the awareness that service itself means value co-creation among the involved actors (Vargo and Lusch, 2004), personalizing the health care experience for each patient and adapting organizational and planning processes to context variability. Large investments in fixed assets and highly trained staffs severely limit the flexibility in capacity of every healthcare service system. The inertia of the supply chain limits its ability to respond to the non-stationary nature of demand that is driven by individual patient needs. Therefore, resource allocations that are typically used in other service industries to respond to variable demand are not effective in healthcare systems. The use of IoT and BDA to generate more accurate and dynamic updates of parameters that affect demand and resource availability enables a different approach known as demand response (DR). Electric utilities are a good example of an inertia-constrained supply chain that uses IoT and BDA to enable DR (Siano and Sarno, 2016). Although healthcare service systems presently do not adopt the practice of DR, the necessary technologies are in place to do so. An essential requirement of DR is also an innovative feature of this practice – DR requires co-creation. Through the application of finite capacity scheduling (FCS) a healthcare system can utilize real-time data about patient locations, medical conditions and desires to dynamically assign patients and healthcare resources to medical procedures for improved efficiency in the use of healthcare resources and the personalization of patient care. This research formulates the key decision models that will support DR in healthcare systems and take advantage of IoT and BDA. We identify the unique tradeoffs that DR presents to the design and management of healthcare systems, specify the data requirements of the predictive models that are recommended, formulate the mathematical structure of the decision models and describe the changes to the management and culture of the healthcare ecosystem that will be necessary. Design/Methodology/approach – The formulation of adaptive, intelligent decision models for planning, scheduling and controlling health care services will be accomplished through application of the techniques of operations research guided by the perspective of Service Dominant Logic (SDL) and the Viable Systems Approach (VSA). Although these decision models can trace their pedigree to classic resource planning and scheduling models of goods-dominant research, they embody distinctive and essential features of co-creative systems. Our formulations of these models will expose these features. The state of the art in the application of IoT and BDA in healthcare enables the acquisition of massive amounts of detailed data from patient electronic medical records; real-time patient condition monitors; location devices for patients, healthcare personnel, medical equipment; social networks’ comments; resource status reports and schedules; and intelligent medical knowledge bases. Furthermore, cognitive assistants are now providing medical professionals with up-to-date knowledge to support diagnosis and treatment. Our model formulations will be directed at defining the specific model constructs that take advantage of the recent advances in IoT and BDA. Specifically, we will develop a hierarchy of models that exhibit the benefits of utilizing increasing penetrations of big data sources and increasing degrees of decision adaptation (homeostasis). Findings – 1) How can big data inform us about the needs and desires of all of the players in the health care system? 2) How can big data analytics be used in predicting patient needs and desires as well as the intentions of healthcare providers? 3) How can IoT enable the beneficial usage of big data for co-creative healthcare management? Research limitations/implications - This research represents the first step of a wider research project aimed at assessing the feasibility and the convenience of new forms of value co-creation in healthcare management. The suite of models that this research creates will initiate a quantitative evaluation of the relative performance of the models in the suite. However, this evaluation, which will be done via computer simulation, is outside the scope of the current paper. Ultimately, our models will demonstrate the specific ways in which BDA and IoT can be used effectively in healthcare management. Service innovators in the healthcare industry will be able to use the results of this stream of research to see beyond the hype of these new technologies and learn how to leverage them effectively. Originality/value – The advances in the engineering of IoT devices and the development of statistical methods for BDA have been very impressive. The applications of these technologies have been heavily promoted, but there has been very little research into the integration of IoT and BDA into model-based decision support systems. This study will be original in its foundation in decision modeling.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
