背景:根治性膀胱切除术(RC)的术前风险评估是一个持续的挑战,尤其是在老年患者中。
目的:评估机器学习模型中合并症指数及其与临床参数的组合预测RC后死亡率和发病率的能力。
方法:在392例接受开放式RC的患者中,报告了并发症和死亡率.年龄调整后的Charlson合并症指数(aCCI)的预测值,Elixhauser指数(EI),采用回归分析评估了体质状态分类系统(ASA)和Gagne合并合并症指数(GCI).各种机器学习模型(高斯天真贝叶斯,逻辑回归,神经网络,决策树,随机森林)进行了额外调查。
结果:在RC后,aCCI,ASA和GCI对并发症的预测(χ2=8.8,p<0.01,χ2=15.7,p<0.01和χ2=4.6,p=0.03)和死亡率(χ2=21.1,p<0.01,χ2=25.8,p<0.01和χ2=2.4,p=0.04)均无明显预测结果。然而,受试者特征曲线下面积(AUROC)显示,aCCI和ASA仅在死亡率预测方面表现良好(0.81和0.78,CGI0.63),而并发症预测较差(aCCI0.6,ASA0.63,CGI0.58).ASA的组合,年龄,体重指数和性别在机器学习模型中表现出更好的预测效果。高斯朴素贝叶斯(0.79)和逻辑回归(0.76)显示了使用保持测试集的最佳性能。
结论:ASA和aCCI对RC后的死亡率有很好的预测效果,但未能准确预测并发症。这里,机器学习模型中合并症指数和临床参数的组合似乎很有希望.
BACKGROUND: Pre-operative risk assessment in radical cystectomy (RC) is an ongoing challenge especially in elderly patients.
OBJECTIVE: To evaluate the ability of comorbidity indices and their combination with clinical parameters in machine learning models to predict mortality and morbidity after RC.
METHODS: In 392 patients who underwent open RC, complication and mortality rates were reported. The predictive values of the age-adjusted Charlson Comorbidity index (aCCI), the Elixhauser Index (EI), the Physical Status Classification System (ASA) and Gagne\'s combined comorbidity Index (GCI) were evaluated using regression analyses. Various machine learning models (Gaussian naïve bayes, logistic regression, neural net, decision tree, random forest) were additionally investigated.
RESULTS: The aCCI, ASA and GCI showed significant results for the prediction of complications (χ2 = 8.8, p < 0.01, χ2 = 15.7, p < 0.01 and χ2 = 4.6, p = 0.03) and mortality (χ2 = 21.1, p < 0.01, χ2 = 25.8, p < 0.01 and χ2 = 2.4, p = 0.04) after RC while the EI showed no significant prediction. However, areas under receiver characteristic curves (AUROCs) revealed good performance only for the prediction of mortality by the aCCI and ASA (0.81 and 0.78, CGI 0.63) while the prediction of complications was poor (aCCI 0.6, ASA 0.63, CGI 0.58). The combination of ASA, age, body mass index and sex in machine learning models showed a better prediction. Gaussian naïve bayes (0.79) and logistic regression (0.76) showed the best performance using a hold-out test set.
CONCLUSIONS: The ASA and aCCI show good prediction of mortality after RC but fail predicting complications accurately. Here, the combination of comorbidity indices and clinical parameters in machine learning models seems promising.