Background Metabolic syndrome (MetS) is a complex condition that appears as a cluster of metabolic abnormalities, and is closely associated with the prevalence of various diseases. Early prediction of the risk of MetS in the middle-aged population provides greater benefits for cardiovascular disease-related health outcomes. This study aimed to apply the latest machine learning techniques to find the optimal MetS prediction model for the middle-aged Korean population. Methods We retrieved 20 data types from the Korean Medicine Daejeon Citizen Cohort, a cohort study on a community-based population of adults aged 30–55 years. The data included sex, age, anthropometric data, lifestyle-related data, and blood indicators of 1991 individuals. Participants satisfying two (pre-MetS) or ≥ 3 (MetS) of the five NECP-ATP III criteria were included in the MetS group. MetS prediction used nine machine learning models based on the following algorithms: Decision tree, Gaussian Naïve Bayes, K-nearest neighbor, eXtreme gradient boosting (XGBoost), random forest, logistic regression, support vector machine, multi-layer perceptron, and 1D convolutional neural network. All analyses were performed by sequentially inputting the features in three steps according to their characteristics. The models’ performances were compared after applying the synthetic minority oversampling technique (SMOTE) to resolve data imbalance. Results MetS was detected in 33.85% of the subjects. Among the MetS prediction models, the tree-based random forest and XGBoost models showed the best performance, which improved with the number of features used. As a measure of the models’ performance, the area under the receiver operating characteristic curve (AUC) increased by up to 0.091 when the SMOTE was applied, with XGBoost showing the highest AUC of 0.851. Body mass index and waist-to-hip ratio were identified as the most important features in the MetS prediction models for this population. Conclusions Tree-based machine learning models were useful in identifying MetS with high accuracy in middle-aged Koreans. Early diagnosis of MetS is important and requires a multidimensional approach that includes self-administered questionnaire, anthropometric, and biochemical measurements.
An anti-inflammatory diet has many beneficial effects on cardiometabolic diseases. Constitution type of traditional Korean medicine can predict cardiometabolic risk factors. We examined the relationship between vegetable consumption and the high-sensitive C-reactive protein (hs-CRP) level on cardiometabolic risk factors in Korean adults by constitution types. Data from 1,983 eligible participants (mean age, 44.3 years) were included in the present cross-sectional study. The inflammatory status of the participants was categorized into low- (<3.0 mg/L) or high-risk (≥3.0 mg/L) groups based on their constitution types. Cardiometabolic risk factors (abdominal obesity, elevated triglycerides, reduced high-density lipoprotein-cholesterol, elevated blood pressure, elevated fasting plasma glucose, and ≥2 concurrent cardiovascular diseases (CVDs) risk factors) and dietary assessment of the participants were assessed. A total of 11.1% of Tae-eumin (TE) and 4.9% of non-TE groups had a higher hs-CRP level (TE: 6.6 ± 0.2, non-TE: 8.4 ± 0.3) than a low hs-CRP level TE and non-TE (TE: 0.9 ± 0.1, non-TE: 0.6 ± 0.1). Vegetable consumption of <91.5 g/day was highly associated with a high-risk hs-CRP level (adjusted odds ratio (ORs): second tertile (T2): 2.290, (95% confidence interval (CI): 1.285–4.082); first tertile (T1): 2.474 (95% CI: 1.368–4.475), P = 0.003 ) compared with that of the highest (T3) in TE. Low (T1 and T2) vegetable consumption was associated with a 54–63% increased prevalence of more than two concurrent CVDs risk factors compared with that of the highest in the TE group P = 0.012 . Higher vegetable consumption greatly decreased the prevalence of CVDs risk factors by 63–86% in the low-risk and high-risk hs-CRP TE groups. Our results highlight the cardioprotective effects of higher consumption of vegetables in Korean adults with TE. Evidence-based clinical risk factor management and multifaceted approaches at the community and population levels targeting prevention in high-burden groups are recommended to reduce the premature mortality attributed to CVD.
Diet plays a crucial role as a modifiable risk factor related to the development of metabolic syndrome (MetS) and its cluster. Constitution type of traditional Korean medicine has shown accuracy to predict the risk for MetS. We attempted to examine the association between nutritional status, pre-MetS, and its cluster in Korean adults by their constitution type. Participants aged 30 to 55 years who had no cancer or cardiovascular diseases (CVDs) were assigned to join in the present study. Pre-MetS was defined as ≥2 of the following factors: abdominal obesity; elevated triglycerides (TG); reduced high-density lipoprotein cholesterol (HDL-C); elevated blood pressure (BP); and elevated fasting plasma glucose (FPG). Constitution type was categorized into Tae-Eumin (TE) or non-TE. Dietary assessment of the subjects were surveyed using a short-form of the food frequency questionnaire (FFQ) and the nutrition quotient (NQ), which uses 4 factors, namely, balance, diversity, moderation, and dietary behavior. A total of 986 subjects were evaluated by constitution type with MetS status. Of these subjects, 48.6% had pre-MetS, 89.5% were obese and had the highest waist circumference (WC) in Pre-MetS TE. BP, FPG, TG were higher, while HDL-C was lower, than normal TE or non-TE both in Pre-MetS TE and non-TE. The prevalence of pre-MetS was positively associated with lower status of dietary behavior (odds ratio [ORs]: 2.153, 95% confidence interval [CI]: 1.179–3.931) while negatively related to higher vegetables and fruits intakes (ORs: 0.594, 95% CI: 0.359–0.983) in TE. Lower status of NQ had about 2 times higher risk of Pre-MetS (ORs: 1.855, 95% CI: 1.018–3.380) and abdominal obesity (ORs: 2.035, 95% CI: 1.097–3.775) in TE compared with higher status of NQ after controlling for covariates. Poor diet was a key contributor to the development of Pre-MetS and abdominal obesity in Korean adults with TE. Customized nutrition care and integrated medicinal approaches are strongly suggested to conduct optimal preventive care for people who are vulnerable to health risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.