Wang Xingchen, Zhu Tianqi, Xia Minghong, Liu Yu, Wang Yao, Wang Xizhi, Zhuang Lenan, Zhong Danfeng, Zhu Jun, He Hong, Weng Shaoxiang, Zhu Junhui, Lai Dongwu
Key Laboratory of Cardiovascular Intervention and Regenerative Medicine of Zhejiang Province, Department of Cardiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China.
Front Cardiovasc Med. 2022 May 12;9:764629. doi: 10.3389/fcvm.2022.764629. eCollection 2022.
Early prediction and classification of prognosis is essential for patients in the coronary care unit (CCU). We applied a machine learning (ML) model using the eXtreme Gradient Boosting (XGBoost) algorithm to prognosticate CCU patients and compared XGBoost with traditional classification models.
CCU patients' data were extracted from the MIMIC-III v1.4 clinical database, and divided into four groups based on the time to death: <30 days, 30 days-1 year, 1-5 years, and ≥5 years. Four classification models, including XGBoost, naïve Bayes (NB), logistic regression (LR), and support vector machine (SVM) were constructed using the Python software. These four models were tested and compared for accuracy, F1 score, Matthews correlation coefficient (MCC), and area under the curve (AUC) of the receiver operating characteristic curves. Subsequently, Local Interpretable Model-Agnostic Explanations method was performed to improve XGBoost model interpretability. We also constructed sub-models of each model based on the different categories of death time and compared the differences by decision curve analysis. The optimal model was further analyzed using a clinical impact curve. At last, feature ablation curves of the XGBoost model were conducted to obtain the simplified model.
Overall, 5360 CCU patients were included. Compared to NB, LR, and SVM, the XGBoost model showed better accuracy (0.663, 0.605, 0.632, and 0.622), micro-AUCs (0.873, 0.811, 0.841, and 0.818), and MCC (0.337, 0.317, 0.250, and 0.182). In subgroup analysis, the XGBoost model had a better predictive performance in acute myocardial infarction subgroup. The decision curve and clinical impact curve analyses verified the clinical utility of the XGBoost model for different categories of patients. Finally, we obtained a simplified model with thirty features.
For CCU physicians, the ML technique by XGBoost is a potential predictive tool in patients with different conditions, and it may contribute to improvements in prognosis.
对冠心病监护病房（CCU）患者进行早期预后预测和分类至关重要。我们应用了一种使用极端梯度提升（XGBoost）算法的机器学习（ML）模型来预测CCU患者的预后，并将XGBoost与传统分类模型进行比较。
从MIMIC-III v1.4临床数据库中提取CCU患者的数据，并根据死亡时间分为四组：<30天、30天至1年、1至5年和≥5年。使用Python软件构建了四个分类模型，包括XGBoost、朴素贝叶斯（NB）、逻辑回归（LR）和支持向量机（SVM）。对这四个模型进行测试，并比较其准确性、F1分数、马修斯相关系数（MCC）以及接收器操作特征曲线的曲线下面积（AUC）。随后，采用局部可解释模型无关解释方法来提高XGBoost模型的可解释性。我们还基于不同的死亡时间类别构建了每个模型的子模型，并通过决策曲线分析比较差异。使用临床影响曲线对最佳模型进行进一步分析。最后，绘制XGBoost模型的特征消融曲线以获得简化模型。
总共纳入了5360例CCU患者。与NB、LR和SVM相比，XGBoost模型显示出更好的准确性（分别为0.663、0.605、0.632和0.622）、微AUC（分别为0.873、0.811、0.841和0.818）以及MCC（分别为0.337、0.317、0.250和0.182）。在亚组分析中，XGBoost模型在急性心肌梗死亚组中具有更好的预测性能。决策曲线和临床影响曲线分析验证了XGBoost模型对不同类别患者的临床实用性。最后，我们获得了一个具有30个特征的简化模型。
对于CCU医生而言，XGBoost的ML技术是一种针对不同病情患者的潜在预测工具，可能有助于改善预后。
