Artificial Intelligence in Current Diabetes Management and Prediction

Purpose of Review Artificial intelligence (AI) can make advanced inferences based on a large amount of data. The mainstream technologies of the AI boom in 2021 are machine learning (ML) and deep learning, which have made significant progress due to the increase in computational resources accompanied by the dramatic improvement in computer performance. In this review, we introduce AI/ML-based medical devices and prediction models regarding diabetes. Recent Findings In the field of diabetes, several AI-/ML-based medical devices and regarding automatic retinal screening, clinical diagnosis support, and patient self-management tool have already been approved by the US Food and Drug Administration. As for new-onset diabetes prediction using ML methods, its performance is not superior to conventional risk stratification models that use statistical approaches so far. Summary Despite the current situation, it is expected that the predictive performance of AI will soon be maximized by a large amount of organized data and abundant computational resources, which will contribute to a dramatic improvement in the accuracy of disease prediction models for diabetes.

Autoimmune Inflammation and Insulin Resistance: Hallmarks So Far and Yet So Close to Explain Diabetes Endotypes

Purpose of Review Diabetes mellitus can be categorized into two major variants, type 1 and type 2. A number of traits such as clinical phenotype, age at disease onset, genetic background, and underlying pathogenesis distinguish the two forms. Recent Findings Recent evidence indicates that type 1 diabetes can be accompanied by insulin resistance and type 2 diabetes exhibits self-reactivity. These two previously unknown conditions can influence the progression and outcome of the disease. Unlike most conventional considerations, diabetes appears to consist of a spectrum of intermediate phenotypes that includes monogenic and polygenic loci linked to inflammatory processes including autoimmunity, beta cell impairment, and insulin resistance. Summary Here we discuss why a shift of the classical bi-modal view of diabetes (autoimmune vs. non-autoimmune) is necessary in favor of a model of an immunological continuum of endotypes lying between the two extreme “insulin-resistant” and “autoimmune beta cell targeting,” shaped by environmental and genetic factors which contribute to determine specific immune-conditioned outcomes.

Regulating Polyamine Metabolism by miRNAs in Diabetic Cardiomyopathy

Purpose of Review Insulin is at the heart of diabetes mellitus (DM). DM alters cardiac metabolism causing cardiomyopathy, ultimately leading to heart failure. Polyamines, organic compounds synthesized by cardiomyocytes, have an insulin-like activity and effect on glucose metabolism, making them metabolites of interest in the DM heart. This review sheds light on the disrupted microRNA network in the DM heart in relation to developing novel therapeutics targeting polyamine biosynthesis to prevent/mitigate diabetic cardiomyopathy. Recent Findings Polyamines prevent DM-induced upregulation of glucose and ketone body levels similar to insulin. Polyamines also enhance mitochondrial respiration and thereby regulate all major metabolic pathways. Non-coding microRNAs regulate a majority of the biological pathways in our body by modulating gene expression via mRNA degradation or translational repression. However, the role of miRNA in polyamine biosynthesis in the DM heart remains unclear. Summary This review discusses the regulation of polyamine synthesis and metabolism, and its impact on cardiac metabolism and circulating levels of glucose, insulin, and ketone bodies. We provide insights on potential roles of polyamines in diabetic cardiomyopathy and putative miRNAs that could regulate polyamine biosynthesis in the DM heart. Future studies will unravel the regulatory roles these miRNAs play in polyamine biosynthesis and will open new doors in the prevention/treatment of adverse cardiac remodeling in diabetic cardiomyopathy.

Retinal Neurodegeneration in Diabetes: an Emerging Concept in Diabetic Retinopathy

Purpose of Review Diabetic retinopathy (DR), the leading cause of blindness in working-aged adults, remains clinically defined and staged by its vascular manifestations. However, early retinal neurodegeneration may precede vascular pathology, suggesting that this neuronal damage may contribute to disease pathogenesis and represent an independent target for intervention. This review will discuss the evidence and implications for diabetic retinal neurodegeneration. Recent Findings A growing body of literature has identified progressive retinal thinning and visual dysfunction in patients with diabetes even prior to the onset of DR, though advances in retinal vascular imaging suggest that vascular remodeling and choroidal changes occur during these early stages as well. Animal models of diabetes and in vitro studies have also suggested that diabetes may directly affect the retinal neural and glial tissue, providing support to the concept that diabetic retinal neurodegeneration occurs early in the disease and suggesting potentially relevant molecular pathways. Summary Diabetic retinal neurodegeneration may represent a “preclinical” manifestation of diabetic retinal disease and remains an active area of investigation. As the natural history and molecular mechanisms become increasingly understood, it may lead to upcoming developments in not only the treatment options but also the clinical definition of DR.