南方医科大学学报

南方医科大学学报 ›› 2023, Vol. 43 ›› Issue (6): 952-963.doi: 10.12122/j.issn.1673-4254.2023.06.10

• • 上一篇    下一篇

机器学习模型和Cox回归模型预测食管胃结合部腺癌预后的效能

高凯绩，王一豪，曹海坤，贾建光   

  1. 蚌埠医学院第一附属医院肿瘤外科，安徽 蚌埠 233000
  • 出版日期:2023-06-20 发布日期:2023-07-06

Efficacy of machine learning models versus Cox regression model for predicting prognosis of esophagogastric junction adenocarcinoma

GAO Kaiji, WANG Yihao, CAO Haikun, JIA Jianguang   

  1. Department of Surgical Oncology, First Affiliated Hospital of Bengbu Medical College, Bengbu 233000, China
  • Online:2023-06-20 Published:2023-07-06

RichHTML

10

PDF

353

摘要： 目的 探讨机器学习和传统Cox回归模型在预测食管胃结合部腺癌（AEG）患者术后生存能力中的应用价值。方法 选取2015年9月~2020年10月本院收治的287例AEG患者，排除失访及临床资料缺失者，共筛选出203例患者的临床病理资料，经过对数据的赋值等处理，转换成满足R语言分析数据的要求的数据。将203例患者数据使用随机数表法按照3∶1的比例划分为训练集和验证集，对两组数据分别进行Cox比例风险模型构建和4种机器学习模型的构建，绘制出ROC曲线、校准曲线和临床决策曲线（DCA）。为评估4种机器学习模型之间的预测效能，进行机器学习模型的内部验证。通过曲线下面积(AUC)评价模型预测的性能，校准曲线反映模型的拟合情况，并通过DAC判断其临床意义。结果 Cox等比例风险回归、极端梯度提升、随机森林、支持向量机、多层感知机验证集中3年生存率的AUC值分别为0.870、0.901、0.791、0.832、0.725，验证集中5年生存率的AUC值分别为0.915、0.916、0.758、0.905、0.737。4种机器学习模型内部验证分别是：极端梯度提升（AUC=0.818）、随机森林（AUC=0.772）、支持向量机（AUC=0.804）、多层感知机（AUC=0.745）。结论 机器学习模型对于AEG患者生存率预测的表现优于Cox等比例风险回归模型，尤其在不满足等比例假设或线性回归模型下，并能够包含较多的影响变量。在内部验证中，XGBoost模型的预测效能最好，支持向量机次之，随机森林出现过拟合，多层感知机受数据量影响可能拟合效果较差。

关键词: 食管胃结合腺癌；人工智能；机器学习；Cox比例风险回归模型

Abstract: Objective To compare the performance of machine learning models and traditional Cox regression model in predicting postoperative outcomes of patients with esophagogastric junction adenocarcinoma (AEG). Methods This study was conducted among 203 AEG patients with complete clinical and follow-up data, who were treated in our hospital between September, 2015 and October, 2020. The clinicopathological data of the patients were processed for analysis using R language package and divided into training and validation datasets at the ratio of 3∶1. The Cox proportional hazards regression model and 4 machine learning models were constructed for analyzing the datasets. ROC curves, calibration curves and clinical decision curves (DCA) were plotted. Internal validation of the machine learning models was performed to assess their predictive efficacy. The predictive performance of each model was evaluated by calculating the area under the curve (AUC), and the model fitting was assessed using the calibration curve. Results For predicting 3-year survival based on the validation dataset, the AUC was 0.870 for Cox proportional hazard regression model, 0.901 for eXtreme Gradient Boosting (XGBoost), 0.791 for random forest, 0.832 for support vector machine, and 0.725 for multilayer perceptron; For predicting 5-year survival, the AUCs of these models were 0.915, 0.916, 0.758, 0.905, and 0.737, respectively. For internal validation, the AUCs of the 4 machine learning models decreased in the order of XGBoost (0.818), random forest (0.758), support vector machine (0.0.804), and multilayer perceptron (0.745). Conclusion The machine learning models show better predictive efficacy for survival outcomes of patients with AEG than Cox proportional hazard regression model, especially when proportional odds assumption or linear regression models are not applicable. XGBoost models have better performance than the other machine learning models, and the multi-layer perception model may have poor fitting results for a limited data volume.

Key words: esophagogastric junction adenocarcinoma; artificial intelligence; machine learning; Cox proportional hazard regression model