Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, No. 37 Guoxue Alley, Chengdu, Sichuan, 610041, China.
Respir Res. 2024 Jun 18;25(1):246. doi: 10.1186/s12931-024-02874-3.
There is no individualized prediction model for intensive care unit (ICU) admission on patients with community-acquired pneumonia (CAP) and connective tissue disease (CTD) so far. In this study, we aimed to establish a machine learning-based model for predicting the need for ICU admission among those patients.
This was a retrospective study on patients admitted into a University Hospital in China between November 2008 and November 2021. Patients were included if they were diagnosed with CAP and CTD during admission and hospitalization. Data related to demographics, CTD types, comorbidities, vital signs and laboratory results during the first 24 h of hospitalization were collected. The baseline variables were screened to identify potential predictors via three methods, including univariate analysis, least absolute shrinkage and selection operator (Lasso) regression and Boruta algorithm. Nine supervised machine learning algorithms were used to build prediction models. We evaluated the performances of differentiation, calibration, and clinical utility of all models to determine the optimal model. The Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) techniques were performed to interpret the optimal model.
The included patients were randomly divided into the training set (1070 patients) and the testing set (459 patients) at a ratio of 70:30. The intersection results of three feature selection approaches yielded 16 predictors. The eXtreme gradient boosting (XGBoost) model achieved the highest area under the receiver operating characteristic curve (AUC) (0.941) and accuracy (0.913) among various models. The calibration curve and decision curve analysis (DCA) both suggested that the XGBoost model outperformed other models. The SHAP summary plots illustrated the top 6 features with the greatest importance, including higher N-terminal pro-B-type natriuretic peptide (NT-proBNP) and C-reactive protein (CRP), lower level of CD4 + T cell, lymphocyte and serum sodium, and positive serum (1,3)-β-D-glucan test (G test).
We successfully developed, evaluated and explained a machine learning-based model for predicting ICU admission in patients with CAP and CTD. The XGBoost model could be clinical referenced after external validation and improvement.
目前尚无针对社区获得性肺炎（CAP）和结缔组织病（CTD）患者入住重症监护病房（ICU）的个体化预测模型。本研究旨在建立一种基于机器学习的模型，以预测这些患者入住 ICU 的需求。
这是一项回顾性研究，纳入了 2008 年 11 月至 2021 年 11 月期间在中国一家大学医院住院的患者。纳入标准为入院和住院期间诊断为 CAP 和 CTD 的患者。收集了患者入院后 24 小时内的人口统计学资料、CTD 类型、合并症、生命体征和实验室检查结果。通过单因素分析、最小绝对收缩和选择算子（Lasso）回归和 Boruta 算法筛选基线变量，以确定潜在的预测因素。使用 9 种有监督机器学习算法构建预测模型。我们评估了所有模型的区分度、校准度和临床实用性，以确定最优模型。使用 Shapley 加性解释（SHAP）和局部可解释模型不可知解释（LIME）技术对最优模型进行解释。
纳入的患者按 70:30 的比例随机分为训练集（1070 例）和测试集（459 例）。三种特征选择方法的交集结果得到 16 个预测因子。极端梯度提升（XGBoost）模型在各种模型中获得了最高的受试者工作特征曲线下面积（AUC）（0.941）和准确性（0.913）。校准曲线和决策曲线分析（DCA）均表明 XGBoost 模型优于其他模型。SHAP 总结图说明了最重要的前 6 个特征，包括较高的 N 末端前 B 型利钠肽（NT-proBNP）和 C 反应蛋白（CRP）、较低的 CD4+T 细胞、淋巴细胞和血清钠水平以及阳性血清（1,3）-β-D-葡聚糖检测（G 试验）。
我们成功开发、评估和解释了一种基于机器学习的模型，用于预测 CAP 和 CTD 患者入住 ICU。XGBoost 模型在经过外部验证和改进后可以作为临床参考。
