Regularized Machine Learning Models for Prediction of Metabolic Syndrome Using GCKR, APOA5, and BUD13 Gene Variants: Tehran Cardiometabolic Genetic Study.

OBJECTIVE: Metabolic syndrome (MetS) is a complex multifactorial disorder that considerably burdens healthcare systems. We aim to classify MetS using regularized machine learning models in the presence of the risk variants of GCKR, BUD13 and APOA5, and environmental risk factors. MATERIALS AND METHODS: A cohort study was conducted on 2,346 cases and 2,203 controls from eligible Tehran Cardiometabolic Genetic Study (TCGS) participants whose data were collected from 1999 to 2017. We used different regularization approaches [least absolute shrinkage and selection operator (LASSO), ridge regression (RR), elasticnet (ENET), adaptive LASSO (aLASSO), and adaptive ENET (aENET)] and a classical logistic regression (LR) model to classify MetS and select influential variables that predict MetS. Demographics, clinical features, and common polymorphisms in the GCKR, BUD13 and APOA5 genes of eligible participants were assessed to classify TCGS participant status in MetS development. The models' performance was evaluated by 10-repeated 10-fold crossvalidation. Various assessment measures of sensitivity, specificity, classification accuracy, and area under the receiver operating characteristic curve (AUC-ROC) and AUC-precision-recall (AUC-PR) curves were used to compare the models. RESULTS: During the follow-up period, 50.38% of participants developed MetS. The groups were not similar in terms of baseline characteristics and risk variants. MetS was significantly associated with age, gender, schooling years, body mass index (BMI), and alternate alleles in all the risk variants, as indicated by LR. A comparison of accuracy, AUCROC, and AUC-PR metrics indicated that the regularization models outperformed LR. Regularized machine learning models provided comparable classification performances, whereas the aLASSO model was more parsimonious and selected fewer predictors. CONCLUSION: Regularized machine learning models provided more accurate and parsimonious MetS classifying models. These high-performing diagnostic models can lay the foundation for clinical decision support tools that use genetic and demographical variables to locate individuals at high risk for MetS.

The AGT epistasis pattern proposed a novel role for ZBED9 in regulating blood pressure: Tehran Cardiometabolic genetic study (TCGS).

INTRODUCTION: High blood pressure is widely regarded as the most important risk factor for cardiovascular diseases. Epistasis analysis may provide additional insight into the genetic basis of hypertension. METHODS: A nested case-control design was used on 4214 unrelated Tehran Cardiometabolic Genetic Study (TCGS) adults to evaluate 65 SNPs of previously associated genes, including ZBED9, AGT, and TNXB. The integrated effect of each gene was determined using the Sequence-based Kernel Association Test (SKAT). We used model-based multifactor dimension reduction (Mb-MDR) and entropy-based gene-gene interaction (IGENT) methods to determine interaction and epistasis patterns. RESULTS: The integrated effect of each gene has a statistically significant association with blood pressure traits (P-value < 0.05). The single-locus analysis identified two missense variants in ZBED9 (rs450630) and AGT (rs4762) associated with hypertension. In the ZBED9 gene, significant local interactions were discovered. The G allele in rs450630 showed an antagonistic effect on hypertension, but interestingly, IGENT analysis revealed significant epistasis effects for different combinations of ZBED9, AGT, and TNXB loci. CONCLUSION: We discovered a novel interaction effect between a significant variant in an essential gene for hypertension (AGT) and a missense variant in ZBED9, which has shifted our focus to ZBED9's role in blood pressure regulation.

Evaluating machine learning-powered classification algorithms which utilize variants in the GCKR gene to predict metabolic syndrome: Tehran Cardio-metabolic Genetics Study.

BACKGROUND: Metabolic syndrome (MetS) is a prevalent multifactorial disorder that can increase the risk of developing diabetes, cardiovascular diseases, and cancer. We aimed to compare different machine learning classification methods in predicting metabolic syndrome status as well as identifying influential genetic or environmental risk factors. METHODS: This candidate gene study was conducted on 4756 eligible participants from the Tehran Cardio-metabolic Genetic study (TCGS). We compared predictive models using logistic regression (LR), Random Forest (RF), decision tree (DT), support vector machines (SVM), and discriminant analyses. Demographic and clinical features, as well as variables regarding common GCKR gene polymorphisms, were included in the models. We used a 10-repeated tenfold cross-validation to evaluate model performance. RESULTS: 50.6% of participants had MetS. MetS was significantly associated with age, gender, schooling years, BMI, physical activity, rs780094, and rs780093 (P < 0.05) as indicated by LR. RF showed the best performance overall (AUC-ROC = 0.804, AUC-PR = 0.776, and Accuracy = 0.743) and indicated BMI, physical activity, and age to be the most influential model features. According to the DT, a person with BMI < 24 and physical activity < 8.8 possesses a 4% chance for MetS. In contrast, a person with BMI ≥ 25, physical activity < 2.7, and age ≥ 33, has 77% probability of suffering from MetS. CONCLUSION: Our findings indicated that, on average, machine learning models outperformed conventional statistical approaches for patient classification. These well-performing models may be used to develop future support systems that use a variety of data sources to identify persons at high risk of getting MetS.

Total delay and associated factors in pulmonary tuberculosis patients in Golestan province.

BACKGROUND: Delay in diagnosis and treatment of TB is a critical component in TB control program which thereby spreading illness in the community. Sicnce Golestan province has the high risk with high rates of tuberculosis in the country, therefore, the analysis of the factors associated with treatment delay in this province for effective interventions and proper planning is considered necessary. METHODS: 689 patients documents of TB cases in the health department of Golestan University of Medical Sciences in 2016 were enrolled in this survey. The response variable in this study was having the delay or not (via determining the 34 day as cut-off point in the interval between the date of onset of the symptoms and the date of treatment start-up). The data were analyzed using SPSS 24 software and final significant level for multivariate logistic regression model was considered 0.05. RESULTS: Median (mean) treatment delay was calculated 49(77.75) days. In the current study 60.4% of patients had total delay greater than 34 days. In final model variables such as type of PTB (OR=0.645), contact history (patients who had no contact with TB patients (OR=1.441)) and patients who their contact history were unknown (OR=1.654)) had significant relationship with delay in starting treatment after 34 days of onset of symptoms of PTB patients in Golestan (p<0.05). CONCLUSION: It should beam emphasis on increasing the community's awareness of the symptoms of tuberculosis and effective collaboration should be made between the Infectious Disease Control Center and the private and public sectors.

Survival prediction of gastric cancer patients by Artificial Neural Network model.

AIM: This study aims to predict survival rate of gastric cancer patients and identify the effective factors related to it, using artificial neural network model. BACKGROUND: Gastric cancer is the most deadly disease in north and northeast provinces of Iran. A total of 430 patients with gastric cancer who referred to Baghban clinic in Sari, from early November 2006 to late October 2013 were followed. METHODS: A historical cohort of patients who referred to Baghban Clinic, the cancer research center of Mazandaran University of Medical Sciences in Sari, from early November 2006 to late October 2013 was studied. Three groups of variables (demographic, biological and socio-economic) were studied. Survival rate and effective factors on survival time were calculated using Kaplan-Meier methods and artificial neural networks and the best network structure were chosen using the mean square error and ROC curve. All analyses were performed using SPSS v.18.0 and the level of significance was selected α=0.05. RESULTS: In this research, the median survival time was 19±2.04 months. The 1 to 5-year survival rates for patients were 0.64, 0.44, 0.34, 0.24 and 0.19, respectively. The percentage of right predictions of the selected network and the area under the ROC curve were 92% and 94%, respectively. According to the results, the type of treatment, metastasis, stage of disease, histology grade, histology type and the age of diagnosis were effective factors on survival period. CONCLUSION: the 5 years survival rate of gastric cancer patients in Mazandaran is lower than other provinces which could be due to the delay in diagnosis or patient's referral. Therefore, the use of screening methods and early diagnosis could be influential for improving survival rate of these patients.

Treatment Delay and Total Delay among Pulmonary Tuberculosis Patients in the North of Iran: Application Survival Data Analysis.

BACKGROUND: Tuberculosis (TB) remains the leading cause of death among infectious diseases worldwide. Identifying the factors associated with the treatment delay and total delay would be helpful in the prevention of tuberculosis and in reducing the burden on the health care system. The objective of this study was to assess the treatment delay and total delay in TB patients and investigate the factors causing these delays. MATERIALS AND METHODS: This was a longitudinal study conducted in 2009-2015. Our study consisted of 1694 TB patients registered in the TB center of Mazandaran province. Data regarding the patients' demographic characteristics and clinical factors associated with treatment delay and total delay were analyzed. Kaplan Meier plots and log rank tests were used to assess the survival pattern. Cox proportional hazards model for multivariable analysis was discussed. We used mean values and median (Q2) [first quartile (Q1)-third quartile (Q3)] to describe delays. RESULTS: The median treatment delay and total delay were 35 (ranged 23-80) and 36 (ranged 24-82) days, respectively. The mean age of TB patients was 47.40±20.3. No significant association was found between the location of residence, nationality, gender, and type of pulmonary TB patients with treatment delay and total delay. Additionally, age, prison status of patients, HIV test, and contact history had a significant relationship with the treatment delay and total delay (p-value <0.05). It was shown that the median total delay in men patients in the ≤14 year-old age group, imprisoner patients, rural patients, patients who have not received an HIV test, smear negative patients, those who are Iranian, and TB patients whose contact history was unknown was lower than that of others. The highest median treatment delay and total delay was in the >60 age groups, and were 41 and 44 days, respectively. Treatment delay was the same as the total delay except in the place of residence variable; median treatment delay among urban patients was less than that of rural patients. CONCLUSION: According to this study age, prison status of patients, HIV test and contact history had a significant relationship with the treatment delay and total delay (P-value<0.05). Understanding the factors that are closely associated with these delays is essential to effectively control TB and could be helpful in reducing these delays.