Development and performance assessment of novel machine learning models to predict pneumonia after liver transplantation.
Development and performance assessment of novel machine learning models to predict pneumonia after liver transplantation.
复制标题
DOI：
10.1186/s12931-021-01690-3
复制
发表时间：
2021-03-31
影响因子：
5.8
通讯作者：
Zhou S
中科院分区：
文献类型：
--
作者：
Chen C;Yang D;Gao S;Zhang Y;Chen L;Wang B;Mo Z;Yang Y;Hei Z;Zhou S
肺炎是原位肝移植术后最常见的肺部并发症，其发病率和死亡率都很高。我们的目的是使用机器学习（ML）方法开发一个预测奥尔特患者术后肺炎的模型。方法回顾性抽取2015年1月至2019年9月在中山大学附属第三医院行奥尔特的786例成人患者的电子病历数据，随机分为训练集和测试集。使用训练集，开发了六种ML模型，包括逻辑回归（LR），支持向量机（SVM），随机森林（RF），自适应增强（AdaBoost），极端梯度增强（XGBoost）和梯度增强机（GBM）。通过测试集上受试者操作特征的曲线下面积（AUC）评估这些模型。根据所选模型探讨了肺炎的相关危险因素和转归。最终纳入591例奥尔特患者，253例（42.81%）被诊断为术后肺炎，这与术后住院和死亡率增加有关（P < 0.05）。在六种ML模型中，XGBoost模型表现最好。XGBoost模型在测试集上的AUC为0.734（灵敏度：52.6%;特异性：77.5%）。肺炎与INR、HCT、PLT、ALB、ALT、FIB、WBC、PT、Na+、TBIL、麻醉时间、术前住院时间、总补液量、手术时间等14项指标显著相关。我们的研究首次证明，XGBoost模型的14个共同的变量可以预测奥尔特患者术后肺炎。在线版本包含补充材料，可通过10.1186/s12931-021-01690-3获得。
Pneumonia is the most frequently encountered postoperative pulmonary complications (PPC) after orthotopic liver transplantation (OLT), which cause high morbidity and mortality rates. We aimed to develop a model to predict postoperative pneumonia in OLT patients using machine learning (ML) methods. Data of 786 adult patients underwent OLT at the Third Affiliated Hospital of Sun Yat-sen University from January 2015 to September 2019 was retrospectively extracted from electronic medical records and randomly subdivided into a training set and a testing set. With the training set, six ML models including logistic regression (LR), support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost) and gradient boosting machine (GBM) were developed. These models were assessed by the area under curve (AUC) of receiver operating characteristic on the testing set. The related risk factors and outcomes of pneumonia were also probed based on the chosen model. 591 OLT patients were eventually included and 253 (42.81%) were diagnosed with postoperative pneumonia, which was associated with increased postoperative hospitalization and mortality (P < 0.05). Among the six ML models, XGBoost model performed best. The AUC of XGBoost model on the testing set was 0.734 (sensitivity: 52.6%; specificity: 77.5%). Pneumonia was notably associated with 14 items features: INR, HCT, PLT, ALB, ALT, FIB, WBC, PT, serum Na+, TBIL, anesthesia time, preoperative length of stay, total fluid transfusion and operation time. Our study firstly demonstrated that the XGBoost model with 14 common variables might predict postoperative pneumonia in OLT patients. The online version contains supplementary material available at 10.1186/s12931-021-01690-3.
登录
查看更多内容
影响因子：
5.8
作者：
Chen, Chung-Yu;Lin, Wei-Chi;Yang, Hsiao-Yu
通讯作者：
Yang, Hsiao-Yu
影响因子：
3.7
作者：
de Araujo Magalhaes, Clarissa Bentes;Nogueira, Ingrid Correia;Barros Pereira, Eanes Delgado
通讯作者：
Barros Pereira, Eanes Delgado
影响因子：
5.1
作者：
Li, X.;Wu, M.;Zou, J.
通讯作者：
Zou, J.
影响因子：
2.6
作者：
Quesada, Jose A.;Lopez-Pineda, Adriana;Carratala-Munuera, Concepcion
通讯作者：
Carratala-Munuera, Concepcion
影响因子：
6.2
作者：
Levesque, Eric;Hoti, Emir;Samuel, Didier
通讯作者：
Samuel, Didier