Diabetes research and clinical practice · 2025
Sex-specific adipose-muscle patterns from CT reveal metabolic syndrome risk in the elderly with machine learning.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
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.
Hou Bowen, Zhang Yingjing, Ran Zheng, Li Yitong, Gharaibeh Nadeer M, Li Xiaoming
Аннотация
AIMS: While muscle atrophy and ectopic fat deposition characterize metabolic syndrome (MS), their sex-specific patterns in elderly populations remain unclear.
METHODS: With the approval of the IRB, this cross-sectional study analyzed 316 participants (180 MS patients) using CT-based quantification of subcutaneous adipose tissue (SAT), skeletal muscle (SM), and intramuscular adipose tissue (IMAT). Normalized and adjusted data were evaluated via XGBoost machine learning with SHAP interpretation.
RESULTS: MS group demonstrated greater waist circumference (P < 0.001) and higher body mass index (P = 0.003, 0.038). Significant sex-specific differences in adipose-muscle distribution were observed: Female MS patients demonstrated significantly more IMAT compared to controls (P = 0.043, 0.030, 0.029). Male MS subjects exhibited different metabolic adaptations with higher SMI in different parts of lower extremities (P = 0.045, 0.043, 0.005). Predictive models demonstrated excellent performance, with area under curves of 0.875 (95 %CI:0.854-0.897) in females and 0.902 (95 %CI:0.885-0.918) in males. SHAP dependence analysis revealed a U-shaped SMI-MS risk relationship in males, whereas females showed greater risk at low skeletal mass index.
CONCLUSIONS: Theses findings identified distinct sex-specific adipose-muscle patterns in MS, providing new insights for personalized prevention and treatment strategies. The robust predictive performance of our models supported the clinical utility of these biomarkers for MS risk assessment.
METHODS: With the approval of the IRB, this cross-sectional study analyzed 316 participants (180 MS patients) using CT-based quantification of subcutaneous adipose tissue (SAT), skeletal muscle (SM), and intramuscular adipose tissue (IMAT). Normalized and adjusted data were evaluated via XGBoost machine learning with SHAP interpretation.
RESULTS: MS group demonstrated greater waist circumference (P < 0.001) and higher body mass index (P = 0.003, 0.038). Significant sex-specific differences in adipose-muscle distribution were observed: Female MS patients demonstrated significantly more IMAT compared to controls (P = 0.043, 0.030, 0.029). Male MS subjects exhibited different metabolic adaptations with higher SMI in different parts of lower extremities (P = 0.045, 0.043, 0.005). Predictive models demonstrated excellent performance, with area under curves of 0.875 (95 %CI:0.854-0.897) in females and 0.902 (95 %CI:0.885-0.918) in males. SHAP dependence analysis revealed a U-shaped SMI-MS risk relationship in males, whereas females showed greater risk at low skeletal mass index.
CONCLUSIONS: Theses findings identified distinct sex-specific adipose-muscle patterns in MS, providing new insights for personalized prevention and treatment strategies. The robust predictive performance of our models supported the clinical utility of these biomarkers for MS risk assessment.