Visualization obesity risk prediction system based on machine learning

Obesity is closely associated with various chronic diseases.Therefore, accurate, reliable and cost-effective methods for preventing its occurrence and progression are required. In this study, we developed a visualized obesity risk prediction system based on machine learning techniques, aiming to achieve personalized comprehensive health management for obesity. The system utilized a dataset consisting of 1678 anonymized health examination records, including individual lifestyle factors, body composition, blood routine, and biochemical tests. Ten multi-classification machine learning models, including Random Forest and XGBoost, were constructed to identify non-obese individuals (BMI < 25), class 1 obese individuals (25 ≤ BMI < 30), and class 2 obese individuals (30 ≤ BMI). By evaluating the performance of each model on the test set, we selected XGBoost as the best model and built the visualized obesity risk prediction system based on it. The system exhibited good predictive performance and interpretability, directly providing users with their obesity risk levels and determining corresponding intervention priorities. In conclusion, the developed obesity risk prediction system possesses high accuracy and interactivity, aiding physicians in formulating personalized health management plans and achieving comprehensive and accurate obesity management.

Pro-Inflammatory Profile of Adipokines in Obesity Contributes to Pathogenesis, Nutritional Disorders, and Cardiovascular Risk in Chronic Kidney Disease

Obesity is a disease which leads to the development of many other disorders. Excessive accumulation of lipids in adipose tissue (AT) leads to metabolic changes, including hypertrophy of adipocytes, macrophage migration, changes in the composition of immune cells, and impaired secretion of adipokines. Adipokines are cytokines produced by AT and greatly influence human health. Obesity and the pro-inflammatory profile of adipokines lead to the development of chronic kidney disease (CKD) through different mechanisms. In obesity and adipokine profile, there are gender differences that characterize the male gender as more susceptible to metabolic disorders accompanying obesity, including impaired renal function. The relationship between impaired adipokine secretion and renal disease is two-sided. In the developed CKD, the concentration of adipokines in the serum is additionally disturbed due to their insufficient excretion by the excretory system caused by renal pathology. Increased levels of adipokines affect the nutritional status and cardiovascular risk (CVR) of patients with CKD. This article aims to systematize the current knowledge on the influence of obesity, AT, and adipokine secretion disorders on the pathogenesis of CKD and their influence on nutritional status and CVR in patients with CKD.

The relationship between serum adipokines and glucose homeostasis in normal-weight and obese patients on hemodialysis: a preliminary study

PURPOSE

Insulin resistance (IR) is a prevalent disorder in advanced renal failure irrespective of diabetes. Adipokines might play a role in IR, which has not been well-documented in uremic conditions. This study investigated the relationship of Zinc-α₂-glycoprotein (ZAG), adipose triglyceride lipase (ATGL), and adipolin with glucose-insulin homeostasis in normal weight (NW) and obese (OB) patients with hemodialysis.

METHODS

In this cross-sectional study, 59 patients (29 NW; 18.5 ≤ BMI < 25 kg/m², and 30 OB; BMI ≥ 30 kg/m²) were studied. Anthropometries, circulating ZAG, adipolin, ATGL, free fatty acids (FFAs), fasting blood glucose (FBG), insulin, and homeostasis model assessment of IR (HOMA)-IR were assessed.

RESULTS

There were no significant differences in age, gender, hemodialysis duration, dialysis adequacy and diabetes between the two groups. ZAG (100.9 ± 37.1 vs. 107.5 ± 30.5 ng/mL, P = 0.03) and adipolin (12.4 ± 1.6 vs. 13.2 ± 2.8 ng/mL, P = 0.002) concentrations were significantly lower, and FFAs (228.1 ± 112.6 vs. 185 ± 119 ng/mL, P = 0.014) were significantly higher in the OB than NW group. No significant differences were observed in ATGL, FBG, insulin and HOMA-IR between the two groups. Patients with lower IR had higher ZAG (112.9 ± 31.7 vs. 94.9 ± 34.5 ng/mL; P = 0.046), lower FFAs (167.8 ± 98.4 vs. 249.9 ± 120.8 ng/mL; P = 0.004), and marginally lower ATGL (9.1 ± 5.2 vs. 12.3 ± 9.6 mIU/mL; P = 0.079) concentrations than those with higher IR. ZAG was negatively (r =  - 0.323, P = 0.018 and r =  - 0.266, P = 0.054) and FFAs were positively (r = 0.321, P = 0.019 and r = 0.353, P = 0.009) correlated with insulin and HOMA-IR, respectively. ATGL was directly correlated with FFAs (r = 0.314, P = 0.018).

CONCLUSIONS

Novel adipokines, ZAG and ATGL, might contribute to glucose-insulin homeostasis in hemodialysis. Understanding potential causative, diagnostic or therapeutic roles of adipokines in IR require further studies.

Comparative Assessment of Serum Adipokines Zinc-α2-glycoprotein and Adipose Triglyceride Lipase, and Cardiovascular Risk Factors Between Normal Weight and Obese Patients with Hemodialysis

BACKGROUND

Little is known about the potential relationship of obesity, adipose tissue and novel adipokines with cardiometabolic risk factors in end-stage renal disease. Zinc-α2-glycoprotein (ZAG) and adipose triglyceride lipase (ATGL) are novel adipokines with proposed desirable effects on inflammation, and lipid and glucose metabolism. The aim of this study was to investigate serum concentrations of ZAG and ATGL, and the relationship of these adipokines with cardiovascular risk factors in normal weight (NW) and obese (OB) patients undergoing hemodialysis.

METHODS

Patients with regular hemodialysis including 44 normal weight (18.5<BMI<25 kg/m²) and 44 obese (BMI≥30 kg/m²) were enrolled. Serum lipid profile, high-sensitivity C-reactive protein (hsCRP) and nitric oxide metabolites along with ZAG and ATGL concentrations were assessed.

RESULTS

ZAG concentrations were significantly lower in OB compared to NW group (100 ± 34 vs. 106 ± 31 ng/ml; p = 0.007). No significant difference was observed in ATGL between the two groups. A significant inverse correlation between ZAG and HDL (r = ‒0.236, p = 0.048) and a marginal inverse correlation between ATGL and HDL (r = ‒0.211, p = 0.078) were observed in all patients. ZAG had positive correlations with triglyceride/HDL (r = 0.279, p = 0.019), cholesterol/HDL (r = 0.319, p = 0.007), and LDL/HDL (r = 0.26, p = 0.029) ratios. Among cardiovascular risk factors, only LDL/HDL ratio and hsCRP were significantly higher in OB patients (p = 0.009 and p = 0.038, respectively).

CONCLUSIONS

Serum concentrations of ZAG, but not ATGL, were significantly lower in the OB group. It appears that obesity overrides the role of hemodialysis in determining ZAG concentration. In contrast, uremic condition might overshadow the role of obesity in determining levels of traditional cardiovascular risk factors.

Update on epigenetics in allergic disease

Chronic inflammatory diseases, including allergies and asthma, are the result of complex gene-environment interactions. One of the most challenging questions in this regard relates to the biochemical mechanism of how exogenous environmental trigger factors modulate and modify gene expression, subsequently leading to the development of chronic inflammatory conditions. Epigenetics comprises the umbrella of biochemical reactions and mechanisms, such as DNA methylation and chromatin modifications on histones and other structures. Recently, several lifestyle and environmental factors have been investigated in terms of such biochemical interactions with the gene expression-regulating machinery: allergens; microbes and microbial compounds; dietary factors, including vitamin B12, folic acid, and fish oil; obesity; and stress. This article aims to update recent developments in this context with an emphasis on allergy and asthma research.