Obesity science & practice · 2026
Identification and Optimization of Risk for Stroke With Abdominal Obesity Patients: Insights From NHANES 2005-2018.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Zhou Lei, He Mengyang, Xiao Feng, Liu Qixing, Li Xuezhen, He Binghua, Tan Xiangang
Аннотация
OBJECTIVE: Stroke is the leading cause of disability worldwide, and it is now estimated that one in four individuals may experience a stroke during their lifetime. Early detection and rapid access to treatment can save lives and improve recovery. This study aimed to identify and characterize the potential influencing factors in patients with obesity who have had strokes.
METHODS: The research screened the 2005-2018 NHANES database and analyzed potential risk factors in eligible stroke patients with abdominal obesity using 10 machine model learning. Multivariable-adjusted least absolute shrinkage and selection operator (LASSO) regression, restricted cubic spline (RCS) analysis, and Shapley Additive Explanations (SHAP) plots were used to identify important risk factors for obese individuals who have experienced strokes.
RESULTS: The 8764 eligible individuals were divided into training set (6,134) and validation set (2,630) for predictive model development. In addition, the random forest model achieved the highest performance in predicting stroke incidence (area under the curve: 0.823) and all-cause mortality (area under the curve: 0.741). The SHAP values showed that age was the highest predictor followed by hypertension, diabetes, heart failure, smoking history, alcohol use, total cholesterol (TC), TyG-BMI, and cardiovascular artery disease (CDAI).
CONCLUSIONS: TyG-BMI, CDAI, and TC are innovative and clinically viable predictive biomarkers for stroke in patients with abdominal obesity, exhibiting age- and gender-specific effects that are particularly pronounced in elderly females. These findings provide an evidence-based basis for personalized stroke risk assessment and targeted prevention strategies in the growing abdominally obese population.
METHODS: The research screened the 2005-2018 NHANES database and analyzed potential risk factors in eligible stroke patients with abdominal obesity using 10 machine model learning. Multivariable-adjusted least absolute shrinkage and selection operator (LASSO) regression, restricted cubic spline (RCS) analysis, and Shapley Additive Explanations (SHAP) plots were used to identify important risk factors for obese individuals who have experienced strokes.
RESULTS: The 8764 eligible individuals were divided into training set (6,134) and validation set (2,630) for predictive model development. In addition, the random forest model achieved the highest performance in predicting stroke incidence (area under the curve: 0.823) and all-cause mortality (area under the curve: 0.741). The SHAP values showed that age was the highest predictor followed by hypertension, diabetes, heart failure, smoking history, alcohol use, total cholesterol (TC), TyG-BMI, and cardiovascular artery disease (CDAI).
CONCLUSIONS: TyG-BMI, CDAI, and TC are innovative and clinically viable predictive biomarkers for stroke in patients with abdominal obesity, exhibiting age- and gender-specific effects that are particularly pronounced in elderly females. These findings provide an evidence-based basis for personalized stroke risk assessment and targeted prevention strategies in the growing abdominally obese population.