机器学习方法估计60-70岁女性四肢骨骼肌质量
本研究基于LASSO回归开发并验证用于预测60-70岁社区居住女性四肢骨骼肌质量(ASM)的人体测量方程,以生物电阻抗分析(BIA)测得的ASM为参考。共纳入1296名女性随机分为开发组和验证组(1:1),最终方程纳入体重、腰臀比、小腿围和坐高,调整R²为0.848,Bland-Altman分析显示预测值与BIA测量值高度一致,平均差异-0.041 kg。
要点
- LASSO回归筛选出体重、腰臀比、小腿围和坐高作为ASM的独立预测因子。
- Bland-Altman分析平均差异-0.041 kg,95%一致性界限-1.441至1.359 kg。
核心结论
- 该方程可为无法配备BIA的社区提供60-70岁女性ASM的可用测量方法,促进社区层面肌少症的早期筛查。
- 坐高可有效预测ASM,提示其或可用于进一步肌肉质量研究。
研究设计与样本
- 横断面研究,纳入1296名60-70岁社区居住女性,按1:1随机分为开发组和验证组。
- 以BIA测得的ASM为参考,候选预测变量包括体重、身高、BMI、坐高、腰臀比、小腿围及5项肢体长度汇总指标。
- 采用LASSO回归(10折交叉验证)筛选预测因子,多元线性回归建立预测方程,配对t检验和Bland-Altman分析验证一致性。
主要发现
- LASSO回归选择体重、腰臀比、小腿围和坐高作为独立变量。
- Bland-Altman分析显示BIA测得ASM与预测ASM高度一致,平均差异-0.041 kg,95%一致性界限-1.441至1.359 kg。
关键数值与推荐
- 预测方程:ASM = 0.2308 × 体重(kg) - 27.5652 × 腰臀比 + 8.0179 × 小腿围(m) + 2.3772 × 坐高(m) + 22.2405。
- Bland-Altman平均差异-0.041 kg,95%一致性界限-1.441至1.359 kg。
临床怎么用
- 在无法配备BIA的社区,可使用该方程基于体重、腰臀比、小腿围和坐高估算60-70岁女性ASM,辅助肌少症早期筛查。
- 坐高可作为预测ASM的有效指标,或可纳入后续肌肉质量研究。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: This article aimed to develop and validate an anthropometric equation based on the least absolute shrinkage and selection operator (LASSO) regression, a machine learning approach, to predict appendicular skeletal muscle mass (ASM) in 60-70-year-old women. DESIGN: A cross-sectional study. SETTING AND PARTICIPANTS: Community-dwelling women aged 60-70 years. METHODS: A total of 1296 community-dwelling women aged 60-70 years were randomly divided into the development or the validation group (1:1 ratio). ASM was evaluated by bioelectrical impedance analysis (BIA) as the reference. Variables including weight, height, body mass index (BMI), sitting height, waist-to-hip ratio (WHR), calf circumference (CC), and 5 summary measures of limb length were incorporated as candidate predictors. LASSO regression was used to select predictors with 10-fold cross-validation, and multiple linear regression was applied to develop the BIA-measured ASM prediction equation. Paired t test and Bland-Altman analysis were used to validate agreement. RESULTS: Weight, WHR, CC, and sitting height were selected by LASSO regression as independent variables and the equation is ASM = 0.2308 × weight (kg) - 27.5652 × WHR + 8.0179 × CC (m) + 2.3772 × Sitting height (m) + 22.2405 (adjusted R2 = 0.848, standard error of the estimate = 0.661 kg, P < .001). Bland-Altman analysis showed a high agreement between BIA-measured ASM and predicted ASM that the mean difference between the 2 methods was -0.041 kg, with the 95% limits of agreement of -1.441 to 1.359 kg. CONCLUSIONS AND IMPLICATIONS: The equation for 60-70-year-old women could provide an available measurement of ASM for communities that cannot equip with BIA, which promotes the early screening of sarcopenia at the community level. Additionally, sitting height could predict ASM effectively, suggesting that maybe it can be used in further studies of muscle mass.
引用
- Shi J, He Q, Pan Y, et al. Estimation of Appendicular Skeletal Muscle Mass for Women Aged 60-70 Years Using a Machine Learning Approach. J Am Med Dir Assoc. 2022. PMID: 36216159. doi:10.1016/j.jamda.2022.09.002
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。