JMIR Diabetes

Over the past few decades, diabetes has become a serious public health concern worldwide, particularly in Bangladesh. The advancement of artificial intelligence can be reaped in the prediction of blood glucose levels for better health management. However, the practical validity of machine learning (ML) techniques for predicting health parameters using data from low- and middle-income countries, such as Bangladesh, is very low. Specifically, Bangladesh lacks research using ML techniques to predict blood glucose levels based on basic noninvasive clinical measurements and dietary and sociodemographic information.

Reduced or delayed medical follow-ups have been reported during the COVID-19 pandemic, which may lead to worsening clinical outcomes for patients with diabetes. The Japanese government granted special permission for medical institutions to use telephone consultations and other remote communication modes during the COVID-19 pandemic.

Gestational diabetes mellitus (GDM) is an increasing health risk for pregnant women as well as their children. Telehealth interventions targeted at the management of GDM have been shown to be effective, but they still require health care professionals for providing guidance and feedback. Feedback from wearable sensors has been suggested to support the self-management of GDM, but it is unknown how self-tracking should be designed in clinical care.

Effective self-management of diabetes is crucial for improving clinical outcomes by maintaining glucose levels and preventing the exacerbation of the condition. Mobile health (mHealth) has demonstrated its significance in enhancing self-management practices. However, only 20% of Malaysians are familiar with mHealth technologies and use them for health management.

Mobile health (mHealth) apps can be an evidence-based approach to improve health behavior and outcomes. Prior literature has highlighted the need for more research on mHealth personalization, including in diabetes and pregnancy. Critical gaps exist on the impact of personalization of mHealth apps on patient engagement, and in turn, health behaviors and outcomes. Evidence regarding how personalization, engagement, and health outcomes could be aligned when designing mHealth for underserved populations is much needed, given the historical oversights with mHealth design in these populations. This viewpoint is motivated by our experience from designing a personalized mHealth solution focused on Medicaid-enrolled pregnant individuals with uncontrolled type 2 diabetes, many of whom also experience a high burden of social needs. We describe fundamental components of designing mHealth solutions that are both inclusive and personalized, forming the basis of an evidence-based framework for future mHealth design in other disease states with similar contexts.

The Hypoglycaemia – MEasurement, ThResholds and ImpaCtS (Hypo-METRICS) smartphone app was developed to investigate the impact of hypoglycemia on daily functioning in adults with type 1 diabetes mellitus or insulin-treated type 2 diabetes mellitus. The app uses ecological momentary assessments, thereby minimizing recall bias and maximizing ecological validity. It was used in the Hypo-METRICS study, a European multicenter observational study wherein participants wore a blinded continuous glucose monitoring device and completed the app assessments 3 times daily for 70 days.

The BlueStar (Welldoc) digital health solution for people with diabetes incorporates data from multiple devices and generates coaching messages using artificial intelligence. The BlueStar app syncs glucose data from the G6 (Dexcom) real-time continuous glucose monitoring (RT-CGM) system, which provides a glucose measurement every 5 minutes.

There is evidence in the literature that the use of sensor-augmented insulin pumps in patients with high-complexity diabetes improves metabolic control. However, there is no long-term information on clinical outcomes such as hospitalization or admission to the emergency room. This study describes outcomes for metabolic control, incidence of hospitalizations, and emergency room visits in a specific population using this technology.

Medication nonadherence is a problem that impacts both the patient and the health system.

In the United States, there are over 37 million people with diabetes but only 8000 endocrinologists. Therefore, many people with diabetes receive care exclusively from primary care providers (PCPs). To democratize knowledge regarding insulin-requiring diabetes through tele-education, Stanford University and the University of Florida developed Project Extension for Community Healthcare Outcomes (ECHO) Diabetes.

Digital health interventions have the potential to improve the physical and psychosocial health of people living with type 2 diabetes. However, research investigating the long-term (≥1 year) retention and engagement of users within these programs is limited.

Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D).