Loading
Life sciences · Journal article
Communications Medicine · October 5, 2026
No summary has been generated for this record yet. What follows is drawn from its source metadata only.
Journal article.
No findings were extractable from the material analysed.
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
This record has not been graded across any dimension yet. Treat the label above as provisional and read the source.
What is missing. This record has no bottom line, key findings, reported figures, evidence dimensions. That is a gap in the analysis, not a judgement about the study.
Hypertensive adults are at high risk of metabolic syndrome (MetS), yet accurate risk prediction tools for this group are scarce. We prospectively followed 130,489 Chinese hypertensive adults from the Guangzhou Hypertensive Population Community Cohort (GHPCC) for 6–36 months to document incident MetS. Cox regression and stratified analyses identified key risk factors. Five machine-learning algorithms were used to build an optimal MetS risk prediction model, which was externally validated in the China Health and Retirement Longitudinal Study (CHARLS). Predictor importance was assessed, partial dependence plots examined key effects, and a reference level for the top predictor was derived. Body fat percentage (BFP), Chinese visceral adiposity index (CVAI), basal metabolic rate (BMR), and triglyceride-glucose-related indices (TyG-WC, TyG-WHtR, TyG-BMI) are more strongly associated with incident MetS than traditional indicators such as waist circumference and fasting glucose. These associations vary markedly in magnitude across subgroups defined by sex, age, alcohol use, smoking, education, and physical activity, but same in directions. Among five algorithms, the XGBoost-based model performs best, with TyG-BMI as the strongest predictor. When the distributions of other features were held constant, the predicted probability of MetS reached 50% at a TyG‑BMI level of approximately 222.97 kg/m², suggesting a strong association with MetS risk. Notably, this value represents a descriptive reference point from the partial dependence plot rather than a clinically validated independent threshold. Biological age also shows superior predictive value over chronological age. BFP, CVAI, BMR, and TyG-related indices are robust and modifiable predictors of MetS in hypertensive patients. Our findings may help stratify high-risk hypertensive adults for targeted prevention. High blood pressure is common, and people with this condition are more likely to develop metabolic syndrome — a cluster of conditions including obesity, high blood sugar, and abnormal cholesterol that raise the risk of severe diseases such as heart disease and stroke. However, doctors lack simple tools to identify hypertensive patients at higher risk of metabolic syndrome. In this study, we followed more than 130,000 Chinese adults with high blood pressure for up to three years. We used machine learning to build a computer model that predicts who will develop metabolic syndrome. The model uses easy-to-measure indicators, such as body fat percentage, waist-related obesity indices, and a combined score of blood sugar and triglycerides.