Machine Learning Predicts Cardiovascular Events in Patients With Diabetes: The Silesia Diabetes-Heart Project.

We aimed to develop a machine learning (ML) model for predicting cardiovascular (CV) events in patients with diabetes (DM). This was a prospective, observational study where clinical data of patients with diabetes hospitalized in the diabetology center in Poland (years 2015-2020) were analyzed using ML. The occurrence of new CV events following discharge was collected in the follow-up time for up to 5 years and 9 months. An end-to-end ML technique which exploits the neighborhood component analysis for elaborating discriminative predictors, followed by a hybrid sampling/boosting classification algorithm, multiple logistic regression (MLR), or unsupervised hierarchical clustering was proposed. In 1735 patients with diabetes (53% female), there were 150 (8.65%) ones with a new CV event in the follow-up. Twelve most discriminative patients' parameters included coronary artery disease, heart failure, peripheral artery disease, stroke, diabetic foot disease, chronic kidney disease, eosinophil count, serum potassium level, and being treated with clopidogrel, heparin, proton pump inhibitor, and loop diuretic. Utilizing those variables resulted in the area under the receiver operating characteristic curve (AUC) ranging from 0.62 (95% Confidence Interval [CI] 0.56-0.68, P < 0.01) to 0.72 (95% CI 0.66-0.77, P < 0.01) across 5 nonoverlapping test folds, whereas MLR correctly determined 111/150 (74.00%) high-risk patients, and 989/1585 (62.40%) low-risk patients, resulting in 1100/1735 (63.40%) correctly classified patients (AUC: 0.72, 95% CI 0.66-0.77). ML algorithms can identify patients with diabetes at a high risk of new CV events based on a small number of interpretable and easy-to-obtain patients' parameters.

Association of chemotactic cytokine receptor 5 (CCR5) gene polymorphism (59029 A/G, rs1799987) with diabetic kidney disease in patients with type 2 diabetes from Poland.

INTRODUCTION: Diabetic kidney disease (DKD) pathogenesis is multifactorial and is a combination of metabolic, genetic, and environmental factors. Due to a long period of asymptomatic course, it is often diagnosed late when advanced stages of the disease are present. Among patients with diabetes, the presence of chemotactic cytokine receptor 5 (CCR5) gene polymorphism is suspected to be associated with the risk of DKD occurrence; however, the results of the research conducted so far are inconclusive. The aim of this study was to evaluate the CCR5 gene polymorphism (rs1799987, 59029 A/G) association with DKD among patients with type 2 diabetes mellitus (T2DM), who are residents of the Upper Silesia region of Poland. MATERIAL AND METHODS: CCR5 gene polymorphism (rs1799987, 59029 A/G) was assessed among consecutive patients with type 2 diabetes mellitus (T2DM) treated in a single outpatient diabetology clinic in Upper Silesia, Poland. Its association with DKD was examined. Additionally, selected clinical and demographic data were included in the analysis. RESULTS: Among 467 eligible study patients, there was no association between examined CCR5 gene polymorphism and the presence of DKD in relation both to the American Diabetes Association definition (p = 0.6) and to the National Kidney Foundation definition (p = 0.3) of this complication. CONCLUSION: The presented study did not confirm the association between the examined gene polymorphism and the risk of DKD; further studies in this area are needed in order to establish or explicitly exclude this association.

Influence of SGLT2 Inhibitor Treatment on Urine Antioxidant Status in Type 2 Diabetic Patients: A Pilot Study.

Sodium-glucose cotransporter 2 inhibitors (SGLT2i) have been recognized as potent antioxidant agents. Since SGLT2i are nephroprotective drugs, we aimed to examine the urine antioxidant status in patients with type 2 diabetes mellitus (T2DM). One hundred and one subjects participated in this study, including 37 T2DM patients treated with SGLT2i, 31 T2DM patients not using SGLT2i, and 33 healthy individuals serving as a control group. Total antioxidant capacity (TAC), superoxide dismutase (SOD), manganese superoxide dismutase (MnSOD), free thiol groups (R-SH, sulfhydryl groups), and catalase (CAT) activity, as well as glucose concentration, were assessed in the urine of all participants. Urine SOD and MnSOD activity were significantly higher among T2DM patients treated with SGLT2i than T2DM patients without SGLT2i treatment (p = 0.009 and p = 0.003, respectively) and to the healthy controls (p = 0.002 and p = 0.001, respectively). TAC was significantly lower in patients with T2DM treated with SGLT2i when compared to those not treated and healthy subjects (p = 0.036 and p = 0.019, respectively). It could be hypothesized that the mechanism by which SGLT2i provides nephroprotective effects involves improvement of the SOD antioxidant activity. However, lower TAC might impose higher OS (oxidative stress), and elevation of SOD activity might be a compensatory mechanism.

No Correlation between Positive Fructose Hydrogen Breath Test and Clinical Symptoms in Children with Functional Gastrointestinal Disorders: A Retrospective Single-Centre Study.

Fructose malabsorption is regarded as one of the most common types of sugar intolerance. However, the correlation between gastrointestinal symptoms and positive results in fructose hydrogen breath tests (HBTs) remains unclear. The aim of this study was to assess the clinical importance of positive fructose HBT by correlating the HBT results with clinical features in children with various gastrointestinal symptoms. Clinical features and fructose HBT results were obtained from 323 consecutive children (2-18 years old, mean 10.7 ± 4.3 years) that were referred to the Tertiary Paediatric Gastroenterology Centre and diagnosed as having functional gastrointestinal disorders. A total of 114 out of 323 children (35.3%) had positive HBT results, of which 61 patients were females (53.5%) and 53 were males (46.5%). Children with positive HBT were significantly younger than children with negative HBT (9.0 vs. 11.6 years old; p < 0.001). The most frequent symptom among children with fructose malabsorption was recurrent abdominal pain (89.5%). Other important symptoms were diarrhoea, nausea, vomiting, and flatulence. However, no correlation between positive fructose HBT results and any of the reported symptoms or general clinical features was found. In conclusion, positive fructose HBT in children with functional gastrointestinal disorders can be attributed to their younger age but not to some peculiar clinical feature of the disease.

Fat, Sugar or Gut Microbiota in Reducing Cardiometabolic Risk: Does Diet Type Really Matter?

The incidence of cardiometabolic diseases, such as obesity, diabetes, and cardiovascular diseases, is constantly rising. Successful lifestyle changes may limit their incidence, which is why researchers focus on the role of nutrition in this context. The outcomes of studies carried out in past decades have influenced dietary guidelines, which primarily recommend reducing saturated fat as a therapeutic approach for cardiovascular disease prevention, while limiting the role of sugar due to its harmful effects. On the other hand, a low-carbohydrate diet (LCD) as a method of treatment remains controversial. A number of studies on the effect of LCDs on patients with type 2 diabetes mellitus proved that it is a safe and effective method of dietary management. As for the risk of cardiovascular diseases, the source of carbohydrates and fats corresponds with the mortality rate and protective effect of plant-derived components. Additionally, some recent studies have focused on the gut microbiota in relation to cardiometabolic diseases and diet as one of the leading factors affecting microbiota composition. Unfortunately, there is still no precise answer to the question of which a single nutrient plays the most important role in reducing cardiometabolic risk, and this review article presents the current state of the knowledge in this field.

Metabolic-Associated Fatty Liver Disease (MAFLD), Diabetes, and Cardiovascular Disease: Associations with Fructose Metabolism and Gut Microbiota.

Non-alcoholic fatty liver disease (NAFLD) is an increasingly common condition associated with type 2 diabetes (T2DM) and cardiovascular disease (CVD). Since systemic metabolic dysfunction underlies NAFLD, the current nomenclature has been revised, and the term metabolic-associated fatty liver disease (MAFLD) has been proposed. The new definition emphasizes the bidirectional relationships and increases awareness in looking for fatty liver disease among patients with T2DM and CVD or its risk factors, as well as looking for these diseases among patients with NAFLD. The most recommended treatment method of NAFLD is lifestyle changes, including dietary fructose limitation, although other treatment methods of NAFLD have recently emerged and are being studied. Given the focus on the liver-gut axis targeting, bacteria may also be a future aim of NAFLD treatment given the microbiome signatures discriminating healthy individuals from those with NAFLD. In this review article, we will provide an overview of the associations of fructose consumption, gut microbiota, diabetes, and CVD in patients with NAFLD.