The efficacy of canagliflozin in diabetes subgroups stratified by data-driven clustering or a supervised machine learning method: a post hoc analysis of canagliflozin clinical trial data

Personalized glucose-lowering effect of chiglitazar in type 2 diabetes

Chiglitazar (carfloglitazar) is a peroxisome proliferator-activated receptor pan-agonist presenting non-inferior glucose-lowering efficacy with sitagliptin in patients with type 2 diabetes. To delineate the subgroup of patients with greater benefit from chiglitazar, we conducted a machine learning-based post-hoc analysis in two randomized controlled trials. We established a character phenomap based on 13 variables and estimated HbA1c decline to the effects of chiglitazar in reference to sitagliptin. Out of 1,069 patients, 63.3% were found to have greater reduction in HbA1c levels with chiglitazar, while 36.7% showed greater reduction with sitagliptin. This distinction in treatment response was statistically significant between groups (pinteraction<0.001). To identify patients who would gain the most glycemic control benefit from chiglitazar, we developed a machine learning model, ML-PANPPAR, which demonstrated robust performance using sex, BMI, HbA1c, HDL, and fasting insulin. The phenomapping-derived tool successfully identified chiglitazar responders and enabled personalized drug allocation in patients with drug-naïve diabetes.

Machine learning in precision diabetes care and cardiovascular risk prediction

Artificial intelligence and machine learning are driving a paradigm shift in medicine, promising data-driven, personalized solutions for managing diabetes and the excess cardiovascular risk it poses. In this comprehensive review of machine learning applications in the care of patients with diabetes at increased cardiovascular risk, we offer a broad overview of various data-driven methods and how they may be leveraged in developing predictive models for personalized care. We review existing as well as expected artificial intelligence solutions in the context of diagnosis, prognostication, phenotyping, and treatment of diabetes and its cardiovascular complications. In addition to discussing the key properties of such models that enable their successful application in complex risk prediction, we define challenges that arise from their misuse and the role of methodological standards in overcoming these limitations. We also identify key issues in equity and bias mitigation in healthcare and discuss how the current regulatory framework should ensure the efficacy and safety of medical artificial intelligence products in transforming cardiovascular care and outcomes in diabetes.

GLP-1R Signaling and Functional Molecules in Incretin Therapy

Glucagon-like peptide-1 receptor (GLP-1R) is a critical therapeutic target for type 2 diabetes mellitus (T2DM). The GLP-1R cellular signaling mechanism relevant to insulin secretion and blood glucose regulation has been extensively studied. Numerous drugs targeting GLP-1R have entered clinical treatment. However, novel functional molecules with reduced side effects and enhanced therapeutic efficacy are still in high demand. In this review, we summarize the basis of GLP-1R cellular signaling, and how it is involved in the treatment of T2DM. We review the functional molecules of incretin therapy in various stages of clinical trials. We also outline the current strategies and emerging techniques that are furthering the development of novel therapeutic drugs for T2DM and other metabolic diseases.

Association of Estimated Glomerular Filtration Rate With Progression of Albuminuria in Individuals With Type 2 Diabetes

OBJECTIVE

To elucidate the association of glomerular filtration rate (GFR) at baseline with subsequent progression of albuminuria in individuals with type 2 diabetes.

RESEARCH DESIGN AND METHODS

This was a single-center retrospective cohort study of 6,618 Japanese adults with type 2 diabetes and urinary albumin-to-creatinine ratio of <300 mg/g, comprising 2,459 women and 4,159 men with a mean (± SD) age of 60 ± 12 years. The exposure was baseline estimated GFR (eGFR) (mL/min/1.73 m2), treated as a categorical variable and classified into five categories: ≥90, 75-90, 60-75, 45-60, and <45, as well as a continuous variable. The outcome was progression of albuminuria category (i.e., from normoalbuminuria to micro- or macroalbuminuria or from micro- to macroalbuminuria). Hazard ratios (HRs) for the outcome were estimated using the multivariable Cox proportional hazards model. In the analysis treating baseline eGFR as a continuous variable, the multivariable-adjusted restricted cubic spline model was used.

RESULTS

During the median follow-up period of 6.3 years, 1,190 individuals reached the outcome. When those with a baseline eGFR of 75-90 mL/min/1.73 m2 were considered the reference group, HRs (95% CIs) for the outcome in those with a baseline eGFR of ≥90, 60-75, 45-60, or <45 mL/min/1.73 m2 were 1.38 (1.14-1.66), 1.34 (1.14-1.58), 1.81 (1.50-2.20), or 2.37 (1.84-3.05), respectively. Furthermore, the inverse J-shaped curve was more clearly shown by the spline model.

CONCLUSIONS

This study of Japanese adults with type 2 diabetes suggests that both high and low GFRs are implicated in the pathogenesis of albuminuria progression.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.