Hormones (Athens, Greece) · 2025
Combining body roundness index and triglyceride-glucose index to enhance MASLD prediction: insights from NHANES and machine learning.
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.
Li Xiaomin, Liu Shanpeng, Zhao Qingrui, An Mengqing, Hou Chenyu, Hu Songliu, Niu Yucun
Аннотация
BACKGROUND: Non-alcoholic fatty liver disease (MASLD), associated with obesity and metabolic syndrome, necessitates effective biomarkers for diagnosis and management.
AIMS: This study examines the combined utility of the body roundness index (BRI) and the triglyceride-glucose (TyG) index in predicting MASLD.
METHODS: We analyzed NHANES 2017-2018 cross-sectional data from 1,211 individuals without hepatitis or significant alcohol use. Logistic regression models assessed relationships between BRI, body mass index (BMI), TyG, and MASLD. Predictive performance was enhanced using machine learning techniques and a nomogram. Validation methods included the Net Reclassification Index, the integrated discriminant improvement index, receiver operating characteristic analysis, decision curve analysis, and calibration curve analysis.
RESULTS: A significant nonlinear relationship was observed between BRI, BMI, and TyG with MASLD incidence, along with notable additive interactions (all p < 0.05). TyG emerged as a key mediator of BRI or BMI effects on MASLD. The combined indices (BRI and TyG) achieved a predictive area under the curve (AUC) of 0.797, exceeding individual metrics and BMI + TyG. Among 105 machine learning models, random forest excelled with a mean AUC of 0.918. A nomogram demonstrated strong accuracy (AUC = 0.83).
CONCLUSION: The combined BRI and TyG indices serve as effective surrogate biomarkers for managing MASLD, facilitating personalized interventions, and enhancing clinical outcome predictions.
AIMS: This study examines the combined utility of the body roundness index (BRI) and the triglyceride-glucose (TyG) index in predicting MASLD.
METHODS: We analyzed NHANES 2017-2018 cross-sectional data from 1,211 individuals without hepatitis or significant alcohol use. Logistic regression models assessed relationships between BRI, body mass index (BMI), TyG, and MASLD. Predictive performance was enhanced using machine learning techniques and a nomogram. Validation methods included the Net Reclassification Index, the integrated discriminant improvement index, receiver operating characteristic analysis, decision curve analysis, and calibration curve analysis.
RESULTS: A significant nonlinear relationship was observed between BRI, BMI, and TyG with MASLD incidence, along with notable additive interactions (all p < 0.05). TyG emerged as a key mediator of BRI or BMI effects on MASLD. The combined indices (BRI and TyG) achieved a predictive area under the curve (AUC) of 0.797, exceeding individual metrics and BMI + TyG. Among 105 machine learning models, random forest excelled with a mean AUC of 0.918. A nomogram demonstrated strong accuracy (AUC = 0.83).
CONCLUSION: The combined BRI and TyG indices serve as effective surrogate biomarkers for managing MASLD, facilitating personalized interventions, and enhancing clinical outcome predictions.