文献速递流行病学与生物统计医学人工智能与信息学

逻辑回归在主要慢性病预测中与机器学习表现相当

Logistic regression was as good as machine learning for predicting major chronic diseases.
PubMed 文献 · J Clin Epidemiol · 2020-03-10

该研究在亚洲成人前瞻性队列(n=6,762)中比较五种机器学习模型与逻辑回归对心血管病、慢性肾病、糖尿病和高血压的预测性能。结果显示逻辑回归在慢性肾病和糖尿病预测中AUC最高,其他疾病最佳模型与逻辑回归差异小于1%且无统计学意义。结论认为在低发病率与简单临床预测变量下,逻辑回归与机器学习表现相当。

要点

  • 逻辑回归预测慢性肾病AUC为0.905,糖尿病AUC为0.768,均为最优。
  • 心血管病与高血压最佳模型与逻辑回归AUC差异小于1%且无统计学意义。
  • 在简单临床预测变量下,逻辑回归可作为主要慢性病风险预测的可靠选择。

核心结论

  • 在低发病率与简单临床预测变量条件下,逻辑回归预测主要慢性病风险的表现与机器学习模型相当。

研究设计与样本

  • 基于人群的亚洲成人前瞻性队列研究,样本量n=6,762。
  • 比较五种机器学习模型(单隐层神经网络、支持向量机、随机森林、梯度提升机、k近邻)与标准逻辑回归。

主要发现

  • 6年随访中,心血管病、慢性肾病、糖尿病和高血压的发病率分别为4.0%、7.0%、9.2%和34.6%。
  • 最佳模型与逻辑回归的AUC差异均小于1%且无统计学意义。

临床怎么用

  • 在采用简单临床预测变量构建主要慢性病风险模型时,可优先考虑逻辑回归,因其性能与机器学习相当且更易解释。

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

OBJECTIVE: To evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for the prediction of risk of cardiovascular diseases (CVDs), chronic kidney disease (CKD), diabetes (DM), and hypertension (HTN) and in a prospective cohort study using simple clinical predictors. STUDY DESIGN AND SETTING: We conducted analyses in a population-based cohort study in Asian adults (n = 6,762). Five different ML models were considered-single-hidden-layer neural network, support vector machine, random forest, gradient boosting machine, and k-nearest neighbor-and were compared with standard logistic regression. RESULTS: The incidences at 6 years of CVD, CKD, DM, and HTN cases were 4.0%, 7.0%, 9.2%, and 34.6%, respectively. Logistic regression reached the highest area under the receiver operating characteristic curve for CKD (0.905 [0.88, 0.93]) and DM (0.768 [0.73, 0.81]) predictions. For CVD and HTN, the best models were neural network (0.753 [0.70, 0.81]) and support vector machine (0.780 [0.747, 0.812]), respectively. However, the differences with logistic regression were small (less than 1%) and nonsignificant. Logistic regression, gradient boosting machine, and neural network were systematically ranked among the best models. CONCLUSION: Logistic regression yields as good performance as ML models to predict the risk of major chronic diseases with low incidence and simple clinical predictors.

来源:J Clin Epidemiol,查看原文。版权归原作者所有。

引用

  1. Nusinovici S, Tham YC, Chak Yan MY, et al. Logistic regression was as good as machine learning for predicting major chronic diseases. J Clin Epidemiol. 2020. PMID: 32169597. doi:10.1016/j.jclinepi.2020.03.002

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。