Enhancing severe hypoglycemia prediction in type 2 diabetes mellitus through multi-view co-training machine learning model for imbalanced dataset.

Patients with type 2 diabetes mellitus (T2DM) who have severe hypoglycemia (SH) poses a considerable risk of long-term death, especially among the elderly, demanding urgent medical attention. Accurate prediction of SH remains challenging due to its multifaced nature, contributed from factors such as medications, lifestyle choices, and metabolic measurements. In this study, we propose a systematic approach to improve the robustness and accuracy of SH predictions using machine learning models, guided by clinical feature selection. Our focus is on developing long-term SH prediction models using both semi-supervised learning and supervised learning algorithms. Using the action to control cardiovascular risk in diabetes trial, which includes electronic health records for over 10,000 individuals, we focus on studying adults with T2DM. Our results indicate that the application of a multi-view co-training method, incorporating the random forest algorithm, improves the specificity of SH prediction, while the same setup with Naive Bayes replacing random forest demonstrates better sensitivity. Our framework also provides interpretability of machine learning models by identifying key predictors for hypoglycemia, including fasting plasma glucose, hemoglobin A1c, general diabetes education, and NPH or L insulins. The integration of data routinely available in electronic health records significantly enhances our model's capability to predict SH events, showcasing its potential to transform clinical practice by facilitating early interventions and optimizing patient management. By enhancing prediction accuracy and identifying crucial predictive features, our study contributes to advancing the understanding and management of hypoglycemia in this population.

Rising global burden of cancer attributable to high BMI from 2010 to 2019.

BACKGROUND: High body mass index (BMI) is a major risk factor for cancer development, but its impact on the global burden of cancer remains unclear. METHODS: We estimated global and regional temporal trends in the burden of cancer attributable to high BMI, and the contributions of various cancer types using the framework of the Global Burden of Disease Study. RESULTS: From 2010 to 2019, there was a 35 % increase in deaths and a 34 % increase in disability-adjusted life-years from cancers attributable to high BMI. The age-standardized death rates for cancer attributable to high BMI increased over the study period (annual percentage change [APC] +0.48 %, 95 % CI 0.22 to 0.74 %). The greatest number of deaths from cancer attributable to high BMI occurred in Europe, but the fastest-growing age-standardized death rates and disability-adjusted life-years occurred in Southeast Asia. Liver cancer was the fastest-growing cause of cancer mortality (APC: 1.37 %, 95 % CI 1.25 to 1.49 %) attributable to high BMI. CONCLUSION: The global burden of cancer-related deaths attributable to high BMI has increased substantially from 2010 to 2019. The greatest increase in age-standardized death rates occurred in Southeast Asia, and liver cancer is the fastest-growing cause of cancer mortality attributable to high BMI. Urgent and sustained measures are required at a global and regional level to reverse these trends and slow the growing burden of cancer attributed to high BMI.

Association of Adipokines with Development and Progression of Nonalcoholic Fatty Liver Disease.

Nonalcoholic fatty liver disease (NAFLD) is a chronic liver disease affecting 30% of the general population and 40% to 70% of obese individuals. Adipose tissue plays a crucial role in its pathogenesis, as it produces and secretes pro- and anti-inflammatory cytokines called adipokines. Adiponectin and leptin have well-determined actions in terms of NAFLD pathophysiology. Adiponectin deficiency is associated with a pro-inflammatory condition, as it is observed in obesity and other metabolic disorders. On the other hand, increased leptin levels, above the normal levels, act as a pro-inflammatory stimulus. Regarding other adipokines (resistin, visfatin, chemerin, retinol-binding protein 4, irisin), data about their contribution to NAFLD pathogenesis and progression are inconclusive. In addition, pharmacological agents like thiazolidinediones (pioglitazone and rosiglitazone), that are used in the management of NAFLD exert favourable effects on adipokine levels, which in turn may contribute to the improvement of liver function. This review summarizes the current knowledge and developments in the association between adipokines and NAFLD and discusses possible therapeutic implications targeting the modulation of adipokine levels as a potential tool for the treatment of NAFLD.