利用机器学习预测术后肝癌死亡结局。
Predicting postoperative liver cancer death outcomes with machine learning.
机构信息
Department of Anesthesiology, Pain and Perioperative Medicine, The first Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
Department of Rehabilitation Medicine, The first Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
出版信息
Curr Med Res Opin. 2021 Apr;37(4):629-634. doi: 10.1080/03007995.2021.1885361. Epub 2021 Feb 18.
OBJECTIVE
To investigate the effect of 5 machine learning algorithms in predicting total hepatocellular carcinoma (HCC) postoperative death outcomes.
METHODS
This study was a secondary analysis. A prognosis model was established using machine learning with python.
RESULTS
The results from the machine learning gbm algorithm showed that the most important factors, ranked from first to fifth, were: preoperative aspartate aminotransferase (GOT), preoperative AFP, preoperative cereal third transaminase (GPT), preoperative total bilirubin, and LC3. Postoperative death model results for liver cancer patients in the test group: of the 5 algorithm models, the highest accuracy rate was that of forest (0.739), followed by the gbm algorithm (0.714); of the 5 algorithms, the AUC values, from high to low, were forest (0.803), GradientBoosting (0.746), gbm (0.724), Logistic (0.660) and DecisionTree (0.578).
CONCLUSION
Machine learning can predict total hepatocellular carcinoma postoperative death outcomes.
目的
研究 5 种机器学习算法在预测肝细胞癌（HCC）全切除术后死亡结局中的作用。
方法
本研究为二次分析。使用 python 进行机器学习建立预后模型。
结果
机器学习 gbm 算法结果显示，最重要的因素按降序排列依次为：术前天门冬氨酸转氨酶（GOT）、术前甲胎蛋白（AFP）、术前谷丙转氨酶（GPT）、术前总胆红素和 LC3。肝癌患者术后死亡模型结果：在实验组的 5 个算法模型中，准确率最高的是森林（0.739），其次是 gbm 算法（0.714）；5 个算法的 AUC 值从高到低依次为森林（0.803）、梯度提升（0.746）、gbm（0.724）、逻辑回归（0.660）和决策树（0.578）。
结论
机器学习可以预测全肝切除术后肝细胞癌死亡结局。
Zotero 插件