Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Akbarzadeh M

PROVIDER: S-EPMC8994379 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Akbarzadeh Mahdi M Alipour Nadia N Moheimani Hamed H Zahedi Asieh Sadat AS Hosseini-Esfahani Firoozeh F Lanjanian Hossein H Azizi Fereidoun F Daneshpour Maryam S MS

Journal of translational medicine 20220409 1

<h4>Background</h4>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.<h4>Methods</h4>This candidate gene study was conducted on 4756 eligible participants from the Tehran Cardio-metabolic Genetic study (TCGS). We c ...[more]

PMID: 35397593

Similar Datasets

Project description:BackgroundNon-participation in cohort studies, if associated with both the exposure and occurrence of the event, can introduce bias in the estimates of interest. This study aims to identify factors associated with follow-up participation in Tehran Lipid and Glucose Study, a large-scale community-based prospective study in West Asia.MethodsA sample of 10,368 adults from TLGS was included in the analysis. All analyses were split according to sex and age groups (20-39, 40-59, and 60 years). The associations between socio-demographic, health, and lifestyle factors with response rate were identified using the Generalized Estimating Equations model.ResultsOver the median of 15.7 years of follow up the response rate was 64.5%. The highest response rate was observed in those aged 40-59 years for both sexes. Current smokers had lower odds of response in both sexes for all age groups, ranging from 0.51 to 0.74, p < 0.01. In young adults, being single (OR = 0.79, OR = 0.57, p ≤ 0.01, respectively for men and women) and unemployed (OR = 0.73, OR = 0.76, p ≤ 0.01, respectively for men and women) in both sexes, high physical activity in men (OR = 0.77, p < 0.01), high education (OR = 0.75, p = 0.02) and obesity (OR = 0.85, p = 0.05) in women were associated with lower response rate. For the middle-aged group, diabetes in men (OR = 0.77, p = 0.05) and hypertension (OR = 0.84, p = 0.05), and having a history of cancer (OR = 0.43, p = 0.03) in women were factors associated with lower response rates. Finally, interventions for both sexes (OR = 0.75, OR = 0.77, p ≤ 0.05, respectively for men and women) and being divorced/widow in women (OR = 0.77, p = 0.05) were the factors associated with the lower response rate in the elderly.ConclusionsLong-term participation was influenced by socio-demographic, health, and lifestyle factors in different sex- and age-specific patterns in TLGS. Recruitment strategies targeting these factors may improve participant follow-up in longitudinal studies.

Project description:ObjectiveMetabolic 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 methodsA 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.ResultsDuring 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.ConclusionRegularized 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.

Project description:ObjectivesThe aim of the present study was to evaluate the prevalence of polycystic ovary syndrome (PCOS), its phenotypical and cardio-metabolic features in a community sample of the Iranian population in comparison to healthy eumenorrheic, non-hirsute women without polycystic ovaries. The second aim was to assess the cardio-metabolic characteristics of women who suffered from one criteria of PCOS compared to those healthy eumenorrheic, non-hirsute women.MethodsIn this cross-sectional population-based study, a total of 1,960 eligible women, aged (18-45 years) were recruited from the Tehran-Lipid and Glucose-Study participants and were classified as the three groups of (i) women with PCOS by the Rotterdam criteria, (ii) non-PCOS women with one criteria of PCOS and (iii) healthy eumenorrheic, non-hirsute women without polycystic ovaries morphology (PCOM) as the control group. Further PCOS women were extended to four phenotypes of hyperandrogenism, oligo-anovulation, polycystic ovaries (phenotype A), hyperandrogenism, oligo/anovulation (phenotype B), hyperandrogenism, polycystic ovaries (phenotype C) and oligo-anovulation, polycystic ovaries (phenotype D). Cardio-metabolic profiles and the prevalence of comorbidities of metabolic syndrome (MetS) and lipid abnormalities were compared among these groups linear, and the median regression models adjusted for age and body mass index.ResultsThe prevalence of PCOS according to the diagnostic criteria of the NIH, Rotterdam and AE-PCOS Society were 13.6, 19.4, and 17.8, respectively. Among those who met the Rotterdam criteria, 23.9, 46.3, 21.6, and 8.2% had phenotypes A, B, C, and D, respectively. Among the remaining 1,580 women who did not fulfil the PCOS criteria, 108 (6.8%) suffered from only oligo/anovulation, 332 (21%) only hyperandrogenism/hyperandrogenemia, 159 (16.2%) only PCOM in ultrasound and 981 (62%) were healthy eumenorrheic, non-hirsute women without PCOM. The study revealed that some adiposity indices and lipid abnormalities in PCOS phenotypes with hyperandrogenism (A, B, and C) were worse than in healthy women. By contrast, women with phenotype D did not differ from the healthy ones in terms of adiposity and lipid abnormalities. However, the respective values for other cardio-metabolic profiles and MetS rates in different phenotypes of PCOS were similar to the healthy women. Only the prevalence of MetS in phenotype A was significantly higher than in the healthy women. There were no statistically significant differences between participants with one criteria of PCOS and healthy counterparts in terms of most adiposity indexes, cardio-metabolic factors, and comorbidity of MetS and its components. However, women with hyperandrogenism had a significantly higher level of the waist to height ratio (WHtR) and hypertriglyceridemia than their healthy counterparts.ConclusionPCOS, mainly classical phenotypes A and B, are common among Iranian women of reproductive age. Women with PCOS who had androgen excess exhibited the worst lipid profile, and those who had full three criteria of the syndrome exhibited the higher rate of MetS. However, women with only ovulatory dysfunction and only PCOM had similar cardio-metabolic characteristics, compared to healthy subjects. These data suggest that routine screening for metabolic disturbances may be needed in the prevention of cardio-metabolic disorders in patients with more serious phenotypes of PCOS.

Project description:Pearson's correlation coefficient (ρ) is the most commonly reported metric of the success of prediction in genomic selection (GS). However, in real breeding ρ may not be very useful for assessing the quality of the regression in the tails of the distribution, where individuals are chosen for selection. This research used 14 maize and 16 wheat data sets with different trait-environment combinations. Six different models were evaluated by means of a cross-validation scheme (50 random partitions each, with 90% of the individuals in the training set and 10% in the testing set). The predictive accuracy of these algorithms for selecting individuals belonging to the best α=10, 15, 20, 25, 30, 35, 40% of the distribution was estimated using Cohen's kappa coefficient (κ) and an ad hoc measure, which we call relative efficiency (RE), which indicates the expected genetic gain due to selection when individuals are selected based on GS exclusively. We put special emphasis on the analysis for α=15%, because it is a percentile commonly used in plant breeding programmes (for example, at CIMMYT). We also used ρ as a criterion for overall success. The algorithms used were: Bayesian LASSO (BL), Ridge Regression (RR), Reproducing Kernel Hilbert Spaces (RHKS), Random Forest Regression (RFR), and Support Vector Regression (SVR) with linear (lin) and Gaussian kernels (rbf). The performance of regression methods for selecting the best individuals was compared with that of three supervised classification algorithms: Random Forest Classification (RFC) and Support Vector Classification (SVC) with linear (lin) and Gaussian (rbf) kernels. Classification methods were evaluated using the same cross-validation scheme but with the response vector of the original training sets dichotomised using a given threshold. For α=15%, SVC-lin presented the highest κ coefficients in 13 of the 14 maize data sets, with best values ranging from 0.131 to 0.722 (statistically significant in 9 data sets) and the best RE in the same 13 data sets, with values ranging from 0.393 to 0.948 (statistically significant in 12 data sets). RR produced the best mean for both κ and RE in one data set (0.148 and 0.381, respectively). Regarding the wheat data sets, SVC-lin presented the best κ in 12 of the 16 data sets, with outcomes ranging from 0.280 to 0.580 (statistically significant in 4 data sets) and the best RE in 9 data sets ranging from 0.484 to 0.821 (statistically significant in 5 data sets). SVC-rbf (0.235), RR (0.265) and RHKS (0.422) gave the best κ in one data set each, while RHKS and BL tied for the last one (0.234). Finally, BL presented the best RE in two data sets (0.738 and 0.750), RFR (0.636) and SVC-rbf (0.617) in one and RHKS in the remaining three (0.502, 0.458 and 0.586). The difference between the performance of SVC-lin and that of the rest of the models was not so pronounced at higher percentiles of the distribution. The behaviour of regression and classification algorithms varied markedly when selection was done at different thresholds, that is, κ and RE for each algorithm depended strongly on the selection percentile. Based on the results, we propose classification method as a promising alternative for GS in plant breeding.

Dataset Information

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

Background

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets