Li Jun, Sun Yiwu, Ren Jie, Wu Yifan, He Zhaoyi
Department of Anesthesiology, Dazhou Central Hospital, Dazhou, Sichuan, China.
Department of Anesthesiology, Guizhou Provincial People's Hospital, Guiyang, Guizhou, China.
J Cardiothorac Vasc Anesth. 2025 Mar;39(3):666-674. doi: 10.1053/j.jvca.2024.12.016. Epub 2024 Dec 16.
The incidence, mortality, and readmission rates for acute heart failure (AHF) are high, and the in-hospital mortality for AHF patients in the intensive care unit (ICU) is higher. However, there is currently no method to accurately predict the mortality of AHF patients.
The Medical Information Mart for Intensive Care Ⅳ (MIMIC-Ⅳ) database was used to perform a retrospective study. Patients meeting the inclusion criteria were identified from the MIMIC-Ⅳ database and randomly divided into a training set (n = 3,580, 70%) and a validation set (n = 1,534, 30%). The variates collected include demographic data, vital signs, comorbidities, laboratory test results, and treatment information within 24 hours of ICU admission. By using the least absolute shrinkage and selection operator (LASSO) regression model in the training set, variates that affect the in-hospital mortality of AHF patients were screened. Subsequently, in the training set, five common machine learning (ML) algorithms were applied to construct models using variates selected by LASSO to predict the in-hospital mortality of AHF patients. The predictive ability of the models was evaluated for sensitivity, specificity, accuracy, the area under the curve of receiver operating characteristics, and clinical net benefit in the validation set. To obtain a model with the best predictive ability, the predictive ability of common scoring systems was compared with the best ML model.
Among the 5,114 patients, in-hospital mortality was 12.5%. Comparing the area under the curve, the XGBoost model had the best predictive ability among all ML models, and the XGBoost model was chosen as the final model for its higher net benefit. Its predictive ability was superior to common scoring systems.
The XGBoost model can effectively predict the in-hospital mortality of AHF patients admitted to the ICU, which may assist clinicians in precise management and early intervention for patients with AHF to reduce mortality.
急性心力衰竭（AHF）的发病率、死亡率和再入院率都很高，重症监护病房（ICU）中AHF患者的院内死亡率更高。然而，目前尚无准确预测AHF患者死亡率的方法。
使用重症监护医学信息集市Ⅳ（MIMIC-Ⅳ）数据库进行回顾性研究。从MIMIC-Ⅳ数据库中识别出符合纳入标准的患者，并随机分为训练集（n = 3580，70%）和验证集（n = 1534，30%）。收集的变量包括人口统计学数据、生命体征、合并症、实验室检查结果以及ICU入院后24小时内的治疗信息。通过在训练集中使用最小绝对收缩和选择算子（LASSO）回归模型，筛选出影响AHF患者院内死亡率的变量。随后，在训练集中，应用五种常见的机器学习（ML）算法，使用LASSO选择的变量构建模型，以预测AHF患者的院内死亡率。在验证集中评估模型的预测能力，包括敏感性、特异性、准确性、受试者操作特征曲线下面积和临床净效益。为了获得具有最佳预测能力的模型，将常见评分系统的预测能力与最佳ML模型进行比较。
在5114例患者中，院内死亡率为12.5%。比较曲线下面积，XGBoost模型在所有ML模型中具有最佳预测能力，因其净效益较高而被选为最终模型。其预测能力优于常见评分系统。
XGBoost模型可以有效预测入住ICU的AHF患者的院内死亡率，这可能有助于临床医生对AHF患者进行精准管理和早期干预，以降低死亡率。
