Patient-Driven Diabetes Care of the Future in the Technology Era

Abstract

The growing burden of diabetes is fueled by obesity-inducing lifestyle behaviors including high-calorie diets and lack of physical activity. Challenges in access to diabetes specialists and educators, low adherence to medications, and inadequate motivational support for proper disease self-management contribute to poor glycemic control in patients with diabetes. Simultaneously, high patient volumes and low reimbursement rates limit physicians' time spent on lifestyle behavior counseling. These barriers to efficient diabetes care lead to high rates of diabetes-related complications, driving healthcare costs up and reducing the quality of patients' lives. Considering recent advancements in healthcare delivery technologies such as smartphone applications, telemedicine, m-health, device connectivity, machine-learning technology, and artificial intelligence, there is significant opportunity to achieve better efficiency in diabetes care and increase patient involvement in diabetes self-management, which ultimately may put an end to soaring diabetesrelated healthcare expenditures. This review explores the patient-driven diabetes care of the future in the technology era.

Health Technology Readiness Profiles Among Danish Individuals With Type 2 Diabetes: Cross-Sectional Study

“…Self-management is a crucial and ubiquitous element of T2D treatment [ 1 ]. In this context, digitalization is expected to promote the individual’s engagement in their own disease and health [ 2 , 3 ]. It is commonly held that digitalization strengthens the health professional–patient relationship, provides remote support, and increases time- and cost-efficiency [ 1 - 3 ].…”

“…It is commonly held that digitalization strengthens the health professional–patient relationship, provides remote support, and increases time- and cost-efficiency [ 1 - 3 ]. Moreover, digitalization may facilitate the increasing person-centered and person-driven approach of health care, placing individuals in control of their own disease and treatment [ 2 ]. The use of IT is increasing among older populations (such as those who are ≥ 50 years), providing an easily accessible resource for remotely supported health care of individuals with T2D [ 4 ].…”

Potential predictors of type-2 diabetes risk: machine learning, synthetic data and wearable health devices

“…At present, computational tools which exploit the availability of massive data collected by personal assistant devices employing ML techniques are the focus of a great deal of research efforts. Considering recent improvements in healthcare delivery technologies like smartphone applications, device connectivity, artificial intelligence and machine-learning technology there is strong opportunity to reach better efficiency in pre-diabetes and diabetes care, and ameliorate patient involvement in diabetes self-management, which can decrease the surge of diabetes-related healthcare expenditures, paving the way to the future scenario of patient-driven diabetes care in the technology era [ 66 ]. Also, this new approach has great potential as a low-cost monitoring tool for nutritional habits and physical activity of different segments of the population, permitting their users to achieve knowledge hardly comprehensible by even the best expert.…”

Refining Healthcare in Terms of Diabetic Care: Future Area of Scope for Artificial Intelligence

“…Many research options are under developments in which Bi-hormonal artificial pancreas using switching Economic predictive control model which consist of insulin subsystem and glucose subsystem can be predictively controlled by switching PID controller. Another model which is based on a nonlinear control system based on (TS) Fuzzy model which consists of an effective and exact representation of a complex nonlinear system with a compact set of variable [18][19][20][21][22][23][24].By the above methods successful implementation of artificial pancreas or insulin pumps depends upon exact calculations of activity monitoring, measurement of glucose, carbohydrate intake in the body. Basic structure of artificial pancreas will be explained by Figure no.6.…”

“…With this strong relationship between insulin and glucose contents. We can develop a mathematical model with the help of artificial intelligence or closed loop control system with the help of switching PID predictive control [18][19][20][21][22][23][24]. Also, we can make model of nonlinear differential equations to develop artificial pancreas.…”