Application of machine learning in affordable and accessible insulin management for type 1 and 2 diabetes: A comprehensive review.

Proper insulin management is vital for maintaining stable blood sugar levels and preventing complications associated with diabetes. However, the soaring costs of insulin present significant challenges to ensuring affordable management. This paper conducts a comprehensive review of current literature on the application of machine learning (ML) in insulin management for diabetes patients, particularly focusing on enhancing affordability and accessibility within the United States. The review encompasses various facets of insulin management, including dosage calculation and response, prediction of blood glucose and insulin sensitivity, initial insulin estimation, resistance prediction, treatment adherence, complications, hypoglycemia prediction, and lifestyle modifications. Additionally, the study identifies key limitations in the utilization of ML within the insulin management literature and suggests future research directions aimed at furthering accessible and affordable insulin treatments. These proposed directions include exploring insurance coverage, optimizing insulin type selection, assessing the impact of biosimilar insulin and market competition, considering mental health factors, evaluating insulin delivery options, addressing cost-related issues affecting insulin usage and adherence, and selecting appropriate patient cost-sharing programs. By examining the potential of ML in addressing insulin management affordability and accessibility, this work aims to envision improved and cost-effective insulin management practices. It not only highlights existing research gaps but also offers insights into future directions, guiding the development of innovative solutions that have the potential to revolutionize insulin management and benefit patients reliant on this life-saving treatment.

Prioritizing the glucose-lowering medicines for type 2 diabetes by an extended fuzzy decision-making approach with target-based attributes.

Different therapeutic classes have been authorized for the treatment of hyperglycemia in type 2 diabetic patients, and even more drug classes are under development. This variety of alternative treatments and the general treatment algorithms of the clinical guidelines lead to a nonuniform prescription of drugs by endocrinologists and diabetic specialists. Diabetes medication choice is a multi-objective problem with many difficulties in making rational decisions because of the wide range of hyperglycemia-lowering agents with multiple benefits and multiple risk elements. This paper proposes a group Entropy-CRiteria Importance Through Inter-criteria Correlation (CRITIC)-Weighted Aggregated Sum Product ASsessment (WASPAS) multi-criteria decision-making (MCDM) model with target-based criteria to prioritize and rank the glucose-lowering medicines for type 2 diabetes using the American Diabetes Association and International Diabetes Federation Clinical Guidelines. The proposed model consists of a weighting method comprising both objective and subjective approaches; the two most common objective approaches (i.e., Entropy and CRITIC methods) are used to find the objective weights. Then, these weights are aggregated with the subjective weights that endocrinologists assign to the criteria. Afterward, a WASPAS target-based method is developed to provide the final ranking of the medications. Finally, the close correlation between the final ranking of the proposed methodology and the average priority order of the medications obtained by different MCDM methods implies the strength and validity of the model performance.

A Markov decision process for modeling adverse drug reactions in medication treatment of type 2 diabetes.

Type 2 diabetes has an increasing prevalence and high cost of treatment. The goal of type 2 diabetes treatment is to control patients' blood glucose level by pharmacological interventions and to prevent adverse disease-related complications. Therefore, it is important to optimize the medication treatment plans for type 2 diabetes patients to enhance the quality of their lives and to decrease the economic burden of this chronic disease. Since the treatment of type 2 diabetes relies on medication, it is vital to consider adverse drug reactions. Adverse drug reaction is undesired harmful reactions that may result from some certain medications. Therefore, a Markov decision process is developed in this article to model the medication treatment of type 2 diabetes, considering the possibility of adverse drug reaction occurring adverse drug reaction. The optimal policy of the proposed Markov decision process model is compared with clinical guidelines and existing models in the literature. Moreover, a sensitivity analysis is conducted to address the manner in which model behavior depends on model parameterization and then therapeutic insights are obtained based on the results. The satisfying results show that the model has the capability to offer an optimal treatment policy with an acceptable expected quality of life by utilizing fewer medications and provide significant implications in endocrinology and metabolism applications.