Li Shuhe, Dou Ruoxu, Song Xiaodong, Lui Ka Yin, Xu Jinghong, Guo Zilu, Hu Xiaoguang, Guan Xiangdong, Cai Changjie
Department of Critical Care, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou 510080, China.
Department of Anesthesiology, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou 510080, China.
J Clin Med. 2023 Jan 24;12(3):915. doi: 10.3390/jcm12030915.
Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis.
Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: "Basic + Lab", "Basic + Intervention", and "Whole" feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019.
The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost "Basic + Lab" model (0.83), the LR "Whole" model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored.
We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h.
风险分层在脓毒症管理决策中起着至关重要的作用，因为现有方法难以满足评估这一异质性群体的需求。我们旨在开发并验证一种机器学习模型，以预测重症脓毒症患者的院内死亡率。
在一家大型三级医疗中心纳入符合Sepsis-3定义的成年患者。在重症监护病房（ICU）的最初24小时内提取相关临床特征，重新分类为不同类别，并在三种策略下用于模型开发：“基础+实验室”、“基础+干预”和“全部”特征集。将极端梯度提升（XGBoost）与逻辑回归（LR）及既定的严重程度评分进行比较。使用2017年至2019年的入院病例进行时间验证。
最终队列包括24272例患者，其中4013例患者构成用于时间验证的测试队列。经过训练和微调的具有全部特征集的XGBoost模型在测试队列中显示出最佳的辨别能力，曲线下面积（AUROC）为0.85，显著高于XGBoost“基础+实验室”模型（0.83）、LR“全部特征”模型（0.82）、序贯器官衰竭评估（SOFA）（0.63）、简化急性生理学评分（SAPS-II）（0.73）和逻辑器官功能障碍评分（LODS）（0.74）。在不同亚组中的表现保持稳健，并且在探索可解释性时，诸如尿量增加和补充氧气治疗等预测因素与生存率改善密切相关。
我们开发并验证了一种基于XGBoost的新型模型，并证明在使用最初24小时内的特征预测脓毒症患者的院内死亡风险方面，其性能显著优于LR和其他评分系统。
