前列腺癌预测模型对比研究

Comparing Prediction Models for Prostate Cancer

【目的】对比基于集成学习算法与非集成学习算法构建的前列腺癌预测模型性能,选出最优算法和重要风险因素。【方法】基于KNN、决策树、支持向量机、BP神经网络4种非集成算法和AdaBoost、GradientBoost、XGBoost三种集成算法构建前列腺癌预测模型并验证模型效能,识别前列腺癌风险因素。【结果】非集成算法中决策树模型性能最优,准确率为0.9333,F1分数为0.9301,AUC为0.9145;集成算法中XGBoost模型性能最优,准确率为0.9573,F1分数为0.9624,AUC为0.9513。识别出总PSA、游离PSA等9个前列腺癌重要风险因素。【局限】实验数据集有待扩充,构建模型的算法有待增加。【结论】在前列腺癌预测模型性能和风险因素识别方面,集成学习算法整体上优于非集成学习算法。

[Objective]This paper compares the performance of prostate cancer prediction models based on ensemble learning and non-ensemble learning algorithms,aiming to identify the optimal algorithm and key risk factors for the cancer.[Methods]First,we constructed the prediction models with K-Nearest Neighbor,Decision Tree,Support Vector Machine,and BP neural network.Then,we built prediction models based on AdaBoost,GradientBoost and XGBoost.Finally,we identified risk factors of prostate cancer with the two groups of models.[Results]Among models based on the non-ensemble algorithms,the Decision Tree model had the best performance with the accuracy of 0.9333,the F1 score of 0.9301,and the AUC of 0.9145.For the ensemble algorithm based models,the performance of XGBoost model was the best,with the accuracy of 0.9573,F1 score of 0.9624,and the AUC of 0.9513.We found nine important risk factors for prostate cancer,including total PSA and free PSA.[Limitations]The experimental data set and the model building algorithm need to be expanded.[Conclusions]Ensemble learning algorithm is better than the non-ensemble ones to predict prostate cancer and identify risk factors.