The effect of data balancing approaches on the prediction of metabolic syndrome using non-invasive parameters based on random forest.

BACKGROUND: Metabolic syndrome (MetS) is a cluster of metabolic abnormalities (including obesity, insulin resistance, hypertension, and dyslipidemia), which can be used to identify at-risk populations for diabetes and cardiovascular diseases, the main causes of morbidity and mortality worldwide. The achievement of a simple approach for diagnosing MetS without needing biochemical tests is so valuable. The present study aimed to predict MetS using non-invasive features based on a successful random forest learning algorithm. Also, to deal with the problem of data imbalance that naturally exists in this type of data, the effect of two different data balancing approaches, including the Synthetic Minority Over-sampling Technique (SMOTE) and Random Splitting data balancing (SplitBal), on model performance is investigated. RESULTS: The most important determinant for MetS prediction was waist circumference. Applying a random forest learning algorithm to imbalanced data, the trained models reach 86.9% and 79.4% accuracies and 37.1% and 38.2% sensitivities in men and women, respectively. However, by applying the SplitBal data balancing technique, the best results were obtained, and despite that the accuracy of the trained models decreased by 7.8% and 11.3%, but their sensitivity improved significantly to 82.3% and 73.7% in men and women, respectively. CONCLUSIONS: The random forest learning method, along with data balancing techniques, especially SplitBal, could create MetS prediction models with promising results that can be applied as a useful prognostic tool in health screening programs.

Metabolic syndrome prediction using non-invasive and dietary parameters based on a support vector machine.

BACKGROUND AND AIMS: Metabolic syndrome (MetS) is a widely used index for finding people at risk for chronic diseases, including cardiovascular disease and diabetes. Early detection of MetS is especially important in prevention programs. Relying on previous studies that suggest machine learning methods as a valuable approach for diagnosing MetS, this study aimed to develop MetS prediction models based on support vector machine (SVM) algorithms, applying non-invasive and low-cost (NI&LC), and also dietary parameters. METHODS AND RESULTS: This population-based research was conducted on a large dataset of 4596 participants within the framework of the Shahedieh cohort study. An Extremely Randomized Trees Classifier was used to select the most effective features among NI&LC and dietary data. The prediction models were developed based on SVM algorithms, and their performance was assessed by accuracy, sensitivity, specificity, positive prediction value, negative prediction value, f1-score, and receiver operating characteristic curve. MetS was diagnosed in 14% of men and 22% of women. Among NI&LC features, waist circumference, body mass index, waist-to-height ratio, waist-to-hip ratio, systolic blood pressure, and diastolic blood pressure were the most predictive variables. By using NI&LC features, models with 78.4% and 63.5% accuracy and 81.2% and 75.3% sensitivity were yielded for men and women, respectively. By incorporating NI&LC and dietary features, the accuracy of the model in women improved by 3.7%. CONCLUSIONS: SVM algorithms had promising potential for early detection of MetS relying on NI&LC parameters. These models can be used in prevention programs, clinical practice, and personal applications.

Evaluating Neck Circumference as an Independent Predictor of Metabolic Syndrome and Its Components Among Adults: A Population-Based Study.

Background Metabolic syndrome (MetS), a public health problem worldwide, represents a high-risk condition for cardiovascular disease and diabetes. The reserve of subcutaneous fat in the upper torso is an important factor in the development of MetS and its risk factors. As neck circumference (NC) is a simple and reliable index that indicates upper-body subcutaneous fat accumulation, this study was conducted to investigate the association between NC with MetS and its components in a large population-based sample of Iranian adults. Methods The present cross-sectional study was conducted among 2094 individuals aged 20-70 years from Yazd Health Study (YaHS). MetS was defined based on the National Cholesterol Education Program Adult Treatment Panel III (ATP III) criteria. NC more than 40.25 cm for men and more than 35.75 cm for women was considered a high-risk NC. Logistic regression analysis was applied to obtain the associations of NC with MetS and its component. Results After adjusting for age, BMI, energy intake, physical activity, and smoking in those whose NC was higher than normal, the risk of the MetS (odds ratio {OR}: 2.32; 95%CI: 1.55-3.46, P<0.001 in men and OR: 2.56; 95%CI: 1.76-3.74, P<0.001 in women), abdominal obesity (OR: 4.39; 95%CI: 2.67-7.23, P<0.001 in men and OR: 1.92; 95%CI: 1.27-2.90, P=0.002 in women), high blood pressure (OR: 1.54; 95%CI: 1.07-2.21, P=0.02 in men and OR: 1.51; 95%CI: 1.06-2.14, P=0.02 in women), low high-density lipoprotein cholesterol (HDL-C) (OR: 1.47; 95%CI: 1.01-2.15, P=0.04 in men and OR: 1.69; 95%CI: 1.23-2.32, P=0.001 in women), and hypertriglyceridemia (OR: 1.41; 95%CI: 1.03-1.99, P=0.04 in men and OR: 1.68; 95%CI: 1.17-2.41, P=0.005 in women) were higher. There was no significant difference in the risk of hyperglycemia between the two NC groups in both sexes. The Pearson's correlation coefficients of NC with waist circumference, hip circumference, body mass index, and waist-to-height ratio were 0.52, 0.43, 0.41, and 0.31, respectively (P<0.001). Moreover, NC had a considerable correlation with serum triglyceride, high-density lipoprotein, systolic blood pressure, and diastolic blood pressure (0.27, -0.30, 0.29, 0.25, P<0.001), respectively. Conclusion Increased NC was significantly associated with higher odds of MetS and its components. Since NC measurement is simple, inexpensive, reliable, and less invasive, it can be used as a complementary tool in the screening and diagnosis of MetS and its risk factors in clinical and community programs especially in developing countries.

The addition of exercise to a weight loss diet on inflammatory markers: a systematic review and Meta-analysis of controlled clinical trials.

This systematic review and meta-analysis of controlled clinical trials was performed to evaluate the effects of weight-loss diets plus exercise compared with weight-loss diets alone on inflammatory biomarkers in adults. PubMed, Scopus, EMBASE, Web of Science (ISI), and Google Scholar were searched up to April 2021. Overall effects were derived using a random effects model. The overall quality of evidence was assessed using Grading of Recommendations Assessment, Development, and Evaluation (GRADE). Twenty-nine trials were included in this systematic review and meta-analysis. The meta-analysis showed no significant difference in serum high sensitivity C-reactive protein (hs-CRP) [weighted mean difference (WMD) = -0.004 mg/l, 95% CI: -0.140, 0.132, P = 0.954], interleukin-6 (IL-6) (WMD = -0.039 pg/ml, 95% CI: -0.233 to 0.156, P = 0.696), and tumor necrosis factor-α (TNF-α) (WMD = 0.405 ng/ml, 95% CI: -1.036 to 0.226, P = 0.209) after adding exercise to a weight-loss diet compared with a weight-loss diet alone. Subgroup analysis revealed that exercise plus a weight-loss diet significantly reduced TNF-α in studies greater than 16 weeks in duration (WMD = -0.742 ng/ml, 95% CI: -1.384 to -0.1, P = 0.024). This systematic review and meta-analysis indicate that exercise in addition to a weight-loss diet does not have a significant effect on further reducing inflammatory markers compared to a weight loss diet alone.

Effect of exercise as adjuvant to energy-restricted diets on quality of life and depression outcomes: a meta-analysis of randomized controlled trials.

BACKGROUND AND AIM: Obesity and related co-morbidities lead to a decrease in health-related quality of life (HRQOL) and mood. Lifestyle strategies may improve these outcomes. However, the efficacy of exercise in conjunction with a weight-loss diet on HRQOL and mood is unclear. The aim of this systematic review and meta-analysis of randomized controlled trials (RCTs) was to examine whether the addition of exercise to energy-restricted dietary programs improves HRQOL and mood status when compared with energy-restricted diets alone in overweight and obese adults. METHODS: Eligible RCTs were identified by searching PubMed/MEDLINE, EMBASE, ISI (Web of sciences), Scopus, and Google Scholar up to April 2021. Summary effects were derived using a random-effects model. The quality of evidence was assessed using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) methodology. RESULTS: The meta-analysis revealed that an energy-restricted diet plus exercise compared with an energy-restricted diet alone had no significant effects on depression (n = 6, hedges'g = - 0.04, 95% CI: - 0.28,0.20), MOS 36-Item Short-Form Health Survey (SF-36)-physical component summary scores (n = 8, weighted mean difference (WMD) = 1.51, 95% CI: - 0.16, 3.18), SF36-mental component summary scores (n = 7, WMD = 0.64, 95% CI: - 1.00, 2.28), and HRQOL disease-specific questionnaire scores (n = 5, hedges'g = 0.16, 95% CI: - 0.09, 0.40). The GRADE revealed that the quality of evidence was low for disease-specific HRQOL scores, and depression status; and high for physical and mental health assessed by SF-36. CONCLUSION: In our sample of overweight and obese adults, no beneficial effect of adding exercise to an energy-restricted diet was found in terms of HRQOL and Depression.

Does exercise beneficially affect sex hormones when added to hypo-caloric diets in adults with overweight or obesity? A systematic review and meta-analysis of controlled clinical trials.

OBJECTIVE: There is no consensus of opinion if exercise beneficially affects sex hormones if added to weight-loss diets. The purpose of this study was to perform a systematic review and meta-analysis of controlled clinical trials to evaluate the effect of adding exercise to a hypo-caloric diet during a weight-loss program, on serum testosterone, estradiol, and sex hormone-binding globulin (SHBG) in adults with overweight/obesity. DESIGN: Systematic review and meta-analysis of the literature. METHODS: Online databases including PubMed/MEDLINE, EMBASE, Scopus, ISI Web of Science, and Google Scholar were searched up to April 2021. A random-effects model was applied to compare mean changes in sex hormones and SHBG between participants undergoing a hypo-caloric diet with or without exercise. RESULTS: In total, 9 eligible clinical trials with 462 participants were included. Out of these, seven, three, and four studies illustrated changes in testosterone, estradiol, and SHBG, respectively. The meta-analysis revealed that exercise had no significant effect on circulating testosterone (WMD = -0.03 nmol/L, 95% CI: -0.11, 0.06, P = 0.51), estradiol (WMD = -0.46 pg/mL, 95% CI: -1.57, 0.65, P = 0.42), and SHBG (WMD = 0.54 nmol/L, 95% CI: -2.63, 3.71, P = 0.74) when added to low-calorie diets. CONCLUSION: The addition of exercise to a hypo-caloric diet provided no additional improvement in sex hormone profiles. Further, well-designed randomized controlled trials with longer follow-up periods in both sexes are recommended to confirm and expand the current results.

Does exercise affect bone mineral density and content when added to a calorie-restricted diet? A systematic review and meta-analysis of controlled clinical trials.

The effects of exercise in conjunction with weight-loss diets on bone health are mixed. Our objective was to systematically review and meta-analyze controlled clinical trials in adults investigating the addition of exercise to a weight-loss diet compared with a calorie-matched weight-loss diet without exercise on bone measures. Online databases including PubMed/MEDLINE, EMBASE, ISI (Web of Science), Scopus, and Google Scholar were searched up to April 2021 with no restriction. A random effects model was used to calculate the overall estimates. Quality of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology. Fourteen eligible controlled clinical trials were included in the systematic review. The meta-analysis revealed that, compared to weight-loss diets alone, the addition of exercise did not improve total body bone mineral density (BMD) [weighted mean difference (WMD) = 0.002 g/cm2, P = 0.62, n = 8], lumbar BMD (WMD = 0.007 g/cm2, P = 0.44, n = 9), total hip BMD (WMD = 0.015 g/cm2, P = 0.14, n = 4) and total bone mineral content (BMC) (WMD = - 11.97 g, P = 0.29, n = 7). Subgroup analysis revealed that resistance exercise in conjunction with hypocaloric diets positively affects total BMD compared to an energy restrictive diet alone (WMD = 0.01 g/cm2, P = 0.003, n = 3). Overall, it appears that only resistance exercise beneficially affects total BMD during a calorie-restricted diet in adults. Further well-controlled and long-term clinical trials are still needed to confirm these results. PROSPERO registration number: CRD42020173434.

The effects of exercise and low-calorie diets compared with low-calorie diets alone on health: a protocol for systematic reviews and meta-analyses of controlled clinical trials.

BACKGROUND: Exercise and weight loss diets are two independent non-pharmaceutical strategies used to improve several aspects of body composition and health. We plan to systematically review controlled clinical trials investigating weight loss diets alone compared to weight loss diets in conjunction with exercise on energy intake, body weight, body composition, cardiometabolic risk factors, sex hormones, and mental health. METHODS AND ANALYSIS: PubMed/MEDLINE, EMBASE, ISI (Web of Science), Scopus, and Google Scholar will be searched to retrieve potential controlled clinical trials investigating the effects of exercise in conjunction with weight loss diets compared with weight loss diets alone on energy intake, body weight and composition (fat mass, fat-free mass), anthropometrics (waist circumference), cardiometabolic markers, sex hormones [testosterone, estradiol, and sex hormone binding globulin (SHBG)], liver and kidney enzymes (alanine aminotransferase (ALT), aspartate aminotransferase (AST), gamma-glutamyl transferase (GGT), uric acid, blood urea nitrogen (BUN), glomerular filtration rate (GFR), quality of life, and depression in adults. The weighted mean difference (WMD) and its corresponding 95% confidence intervals (CIs) will be derived using random effects model. Several subgroup analyses based on follow-up duration, the health status of the participants, the diet used for weight loss, the exercise protocol, participants' sex, and other possible variables will be conducted to explore possible sources of heterogeneity. Publication bias will be explored by inspecting funnel plots and by conducting asymmetry tests. Overall quality of the evidence will be assessed by using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) tool. DISCUSSION: We envisage that this systematic review and meta-analysis will provide valuable information regarding the effectiveness of adding exercise to weight loss diets. No primary data is going to be collected; therefore, ethical approval is not required. The resulting manuscripts will be disseminated in peer-reviewed journals and at international and national conferences. SYSTEMATIC REVIEW REGISTRATION: The study protocol is registered in the International Prospective Register of Systematic Reviews (PROSPERO, Registration ID: CRD42020173434 ).

Assessment of the dietary pattern of dormitory students in Kerman, Iran.

OBJECTIVE: Nowadays it is known that dietary imbalances are associated with non-communicable diseases which would be a major cause of worldwide deaths in 2020. This study was conducted to assess the dietary pattern of students who live in a dormitory in Kerman, Iran, based on Healthy Eating Index-2005 (HEI-2005). METHODS: This cross-sectional study was conducted on 229 students who lived in the dormitory of Kerman University of Medical Science. The participants were recruited by multistage sampling. Their usual dietary intake was collected by using a valid food frequency questionnaire. The diet quality was calculated via HEI-2005. The HEI-2005 score was categorized into three groups: less than 50 (poor diet), between 50-70 (needs improvement) and more than 70 (good diet). RESULTS: The mean score of HEI-2005 in the present study was 64.22±8.98. 8.1% of the participants had poor diet, 63.4% had to improve their diet, and 28.5% enjoyed a good diet. The percent of energy intake from total fat, saturated fatty acid, solid fat and added sugar, and also sodium were significantly lower in the highest category of HEI-2005 than the lowest category. There was no significant difference in the intake of cholesterol, total vegetable and dairy products between the highest and lowest quartile categories. CONCLUSIONS: Majority of the participants need to improve their diet.Policy revisions and dietary interventions would require to promote diet quality and prevent non-communicable diseases in the future.

Associations of Pre-Defined Dietary Patterns with Obesity Associated Phenotypes in Tehranian Adolescents.

Obesity has become a public health problem in adolescents and could be a risk factor for both short-term and long-term health consequences. This study aimed to evaluate the relationship of Dietary Guidelines for Americans Adherence Index (DGAI), Healthy Eating Index-2005 (HEI-2005) and Healthy Eating Index-2010 (HEI-2010) with risk of obesity associated phenotypes in Tehranian adolescents. This cross-sectional study was conducted within the framework of the Tehran Lipid and Glucose Study, on 722 adolescents, aged 10-19 years. Usual dietary intakes were assessed by a food frequency questionnaire, and diet quality scores were obtained based on DGAI, HEI-2005 and HEI-2010. General obesity and cardio metabolic risk factors were defined according to the Centers of Disease Control and Prevention and de'Ferranti cut-offs, respectively. After adjusting for age, sex, energy intake and physical activity, compared to those in the lowest quartile, participants in the highest quartile of HEI-2010 had lower risk of general obesity (OR: 0.62; 95% CI: 0.38-0.93; Ptrend = 0.03) and central obesity (OR: 0.63; 95% CI: 0.44-0.95; Ptrend = 0.04). No association was observed between different types of obesity and scores of other diet quality indices. In conclusions, considering the role of HEI-2010 in decreasing the risk of obesity, these findings suggest that HEI-2010 may be useful for assessing diet-related progress in obesity prevention efforts.