机器学习模型预测社区中老年人未来衰弱:ELSA队列研究
本研究基于英国老龄化纵向研究(ELSA)中基线(2008-2009年)非衰弱且4年后(2012-2013年)重新评估衰弱表型的50岁及以上社区居住者,采用回顾性队列设计,比较逻辑回归、随机森林(RF)等机器学习模型预测随访时衰弱的表现。结合过采样与欠采样的不平衡数据处理方法提升了模型性能,RF表现最佳,平衡数据下ROC曲线下面积和精确率-召回率曲线下面积分别为0.92和0.97,特异性0.83,敏感性0.88,平衡准确率85.5%。年龄、椅子站立测试、家庭财富、平衡问题和自评健康是多数平衡数据训练模型中最重要的衰弱预测因素。
要点
- RF模型在平衡数据下预测4年衰弱:AUC 0.92,特异性0.83,敏感性0.88,平衡准确率85.5%。
- 年龄、椅子站立测试、家庭财富、平衡问题、自评健康为多数模型最重要预测因素。
核心结论
- 机器学习有助于识别随时间推移变为衰弱的个体,该结果通过平衡数据集得以实现。
- 本研究突出了可能有助于早期发现衰弱的因素。
研究设计与样本
- 回顾性队列研究,参与者为英国老龄化纵向研究(ELSA)中基线(2008-2009年)非衰弱且4年随访(2012-2013年)重新评估衰弱表型的50岁及以上社区居住者。
- 基线社会、临床和心理社会预测因素用于预测随访时衰弱,比较逻辑回归、随机森林(RF)、支持向量机、神经网络、K近邻和朴素贝叶斯分类器。
主要发现
- 所提出的结合过采样与欠采样方法调整不平衡数据后改善了模型性能。
- RF表现最佳,平衡数据下ROC曲线下面积和精确率-召回率曲线下面积分别为0.92和0.97,特异性0.83,敏感性0.88,平衡准确率85.5%。
- 年龄、椅子站立测试、家庭财富、平衡问题和自评健康是多数平衡数据训练模型中最重要的衰弱预测因素。
关键数值与推荐
- RF模型平衡数据下ROC曲线下面积0.92,精确率-召回率曲线下面积0.97,特异性0.83,敏感性0.88,平衡准确率85.5%。
临床怎么用
- 机器学习模型可用于识别未来可能变为衰弱的社区中老年人。
- 年龄、椅子站立测试、家庭财富、平衡问题和自评健康可作为早期发现衰弱的候选预测因素。
局限性
- 原文未述局限性
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
BACKGROUND: Machine learning (ML) models can be used to predict future frailty in the community setting. However, outcome variables for epidemiologic data sets such as frailty usually have an imbalance between categories, that is, there are far fewer individuals classified as frail than as nonfrail, adversely affecting the performance of ML models when predicting the syndrome. METHODS: A retrospective cohort study with participants (50 years or older) from the English Longitudinal Study of Ageing who were nonfrail at baseline (2008-2009) and reassessed for the frailty phenotype at 4-year follow-up (2012-2013). Social, clinical, and psychosocial baseline predictors were selected to predict frailty at follow-up in ML models (Logistic Regression, Random Forest [RF], Support Vector Machine, Neural Network, K-nearest neighbor, and Naive Bayes classifier). RESULTS: Of all the 4 378 nonfrail participants at baseline, 347 became frail at follow-up. The proposed combined oversampling and undersampling method to adjust imbalanced data improved the performance of the models, and RF had the best performance, with areas under the receiver-operating characteristic curve and the precision-recall curve of 0.92 and 0.97, respectively, specificity of 0.83, sensitivity of 0.88, and balanced accuracy of 85.5% for balanced data. Age, chair-rise test, household wealth, balance problems, and self-rated health were the most important frailty predictors in most of the models trained with balanced data. CONCLUSIONS: ML proved useful in identifying individuals who became frail over time, and this result was made possible by balancing the data set. This study highlighted factors that may be useful in the early detection of frailty.
引用
- Leme DEDC, de Oliveira C. Machine Learning Models to Predict Future Frailty in Community-Dwelling Middle-Aged and Older Adults: The ELSA Cohort Study. J Gerontol A Biol Sci Med Sci. 2023. PMID: 37209408. doi:10.1093/gerona/glad127
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。