Key result
Machine learning models predict metabolic syndrome with ~87% balanced accuracy using lifestyle and social factors.
Why the study?
Predicting metabolic syndrome is challenging due to its multifactorial nature, population heterogeneity, and variations in risk factors across groups.
Do machine learning models utilizing sleep quality, nutrient intake, and social development index accurately predict Metabolic Syndrome in the Tlalpan 2020 cohort?
Cohort (n=3,156)
No
Do machine learning models utilizing sleep quality, nutrient intake, and social development index accurately predict Metabolic Syndrome in the Tlalpan 2020 cohort?
Machine learning models combined with synthetic data balancing (SMOTE and ADASYN) can predict metabolic syndrome with approximately 87% balanced accuracy while identifying sex-specific risk profiles involving sleep, nutrition, and socioeconomic status.
Answers are grounded in this paper and cite their sources.
Should not yet change metabolic syndrome screening; leaves open prospective validation of ML models in cohorts.
Metabolic Syndrome (MetS) is a serious condition that significantly increases the risk of cardiovascular diseases and the severity of type 2 diabetes, also impacting on the development and evolution of other chronic diseases. Predicting metabolic syndrome is a complex task due to the multifactorial nature of this condition, which involves a combination of various risk factors such as abdominal obesity, insulin resistance, dyslipidemia, and hypertension. The complex interplay of these factors makes it challenging to predict the syndrome. Both genetic predisposition and environmental factors also contribute to the development of metabolic syndrome. Metabolic syndrome affects diverse populations with different ethnicities, lifestyles, and socioeconomic backgrounds. Prediction models, in addition, need to account for population heterogeneity and consider variations in risk factors across different groups. The present study analyzed data from participants in a cohort from Mexico City to identify key risk factors in men and women, addressing the presence of unbalanced data. In order to tackle the issues posed by data imbalance data, SMOTE and ADASYN were applied to assess significant differences in the selection of risk factors for MetS prediction. Random Forest and RPART models using ADASYN and SMOTE demonstrated better performance, achieving a balanced accuracy of approximately 87%. In women, they highlighted sleep quality, anxiety factors, tobacco consumption, and nutritional components. In the case of men, stronger associations were identified with the social development index and factors related to gout in parents.
No takes yet. Share an insight, caveat, or question.
Gutiérrez-Esparza et al. (2024) conducted a cohort in Metabolic Syndrome (n=3,156). Sleep quality, nutrients intake, and social development index was evaluated on Prediction of Metabolic Syndrome (MetS) using machine learning models (Random Forest and RPART) with data balancing (SMOTE and ADASYN). Random Forest and RPART models using ADASYN and SMOTE predicted metabolic syndrome with a balanced accuracy of approximately 87% based on sleep, nutritional, and social factors.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: