文献速递白内障与屈光手术

机器学习基于问卷数据预测10年白内障手术风险

Predicting the 10-year risk of cataract surgery using machine learning techniques on questionnaire data: findings from the 45 and Up Study.
PubMed 文献 · Br J Ophthalmol · 2021-05-26

该研究基于45 and Up研究中207 573名45岁及以上无白内障手术史参与者,利用人口学、社会经济、病史、生活方式、饮食及自评健康等问卷数据,比较三种机器学习算法与逻辑回归预测10年白内障手术风险的准确性。梯度提升机、随机森林和深度学习的AUC均优于逻辑回归,年龄、自评视力和健康保险为一致重要预测因素。

要点

  • 梯度提升机AUC 0.790,优于随机森林0.785、深度学习0.781和逻辑回归0.767。
  • 年龄、自评视力和健康保险在所有模型中均为重要预测因素。
  • 仅用问卷数据即可较准确预测10年白内障手术风险。

核心结论

  • 机器学习模型仅基于问卷数据即可较准确预测10年白内障手术风险,且略优于传统逻辑回归模型。

研究设计与样本

  • 研究纳入45 and Up研究中207 573名45岁及以上、基线无白内障手术史的参与者,收集问卷风险因素,并通过Medicare Benefits Schedule Claims数据集确认白内障手术事件。
  • 比较随机森林、梯度提升机、深度学习和逻辑回归四种算法,采用10折交叉验证评估预测性能,主要指标为受试者工作特征曲线下面积(AUC)。

主要发现

  • 梯度提升机AUC为0.790(95%CI 0.785至0.795),随机森林AUC为0.785(95%CI 0.780至0.790),深度学习AUC为0.781(95%CI 0.775至0.786),均优于逻辑回归AUC 0.767(95%CI 0.762至0.773),所有p<0.05。
  • 年龄、自评视力和健康保险在所有模型中均被一致识别为重要预测因素。

临床怎么用

  • 可利用常规问卷数据构建机器学习模型,辅助识别白内障手术高风险人群,为筛查和预防性干预提供参考。

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/AIMS: To investigate the feasibility and accuracy of using machine learning (ML) techniques on self-reported questionnaire data to predict the 10-year risk of cataract surgery, and to identify meaningful predictors of cataract surgery in middle-aged and older Australians. METHODS: Baseline information regarding demographic, socioeconomic, medical history and family history, lifestyle, dietary and self-rated health status were collected as risk factors. Cataract surgery events were confirmed by the Medicare Benefits Schedule Claims dataset. Three ML algorithms (random forests [RF], gradient boosting machine and deep learning) and one traditional regression algorithm (logistic model) were compared on the accuracy of their predictions for the risk of cataract surgery. The performance was assessed using 10-fold cross-validation. The main outcome measures were areas under the receiver operating characteristic curves (AUCs). RESULTS: In total, 207 573 participants, aged 45 years and above without a history of cataract surgery at baseline, were recruited from the 45 and Up Study. The performance of gradient boosting machine (AUC 0.790, 95% CI 0.785 to 0.795), RF (AUC 0.785, 95% CI 0.780 to 0.790) and deep learning (AUC 0.781, 95% CI 0.775 to 61 0.786) were robust and outperformed the traditional logistic regression method (AUC 0.767, 95% CI 0.762 to 0.773, all p<0.05). Age, self-rated eye vision and health insurance were consistently identified as important predictors in all models. CONCLUSIONS: The study demonstrated that ML modelling was able to reasonably accurately predict the 10-year risk of cataract surgery based on questionnaire data alone and was marginally superior to the conventional logistic model.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Wang W, Han X, Zhang J, et al. Predicting the 10-year risk of cataract surgery using machine learning techniques on questionnaire data: findings from the 45 and Up Study. Br J Ophthalmol. 2021. PMID: 34039562. doi:10.1136/bjophthalmol-2020-318609

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。