Lv Jing, Chen Juan, Liu Meijun, Dai Xue, Deng Wang
Department of Pulmonary and Critical Care Medicine, The First Batch of Key Disciplines on Public Health in Chongqing, Second Affiliated Hospital of Chongqing Medical University, Chongqing, China.
Front Med (Lausanne). 2025 Jul 3;12:1582426. doi: 10.3389/fmed.2025.1582426. eCollection 2025.
This study aimed to construct a machine learning predictive model for prognostic analysis of patients with p- ARDS.
In this single-center retrospective study, 230 patients with p- ARDS admitted to the RICU of the second affiliated hospital of Chongqing Medical University from January 2020 to November 2024 were included. Patients were divided into survival group and death group according to the 28-day prognosis results. All patients' clinical data were first results within 24 h of admission. 20% of the total samples were randomly selected as the test set, and the remaining samples were used as the training set for crossvalidation, and six different models were constructed, including Logistic Regression, Random Forest, NaiveBayes, SVM, XGBoost and Adaboost. The AUC value, AP value, accuracy, sensitivity, specificity, Brier score, and F 1 score were used to evaluate the performance of the models and pick the optimal model. Finally, the SHAP feature importance map was drawn to explain the optimal model.
10 key variables, namely LAR, Lac, pH, age, PO2/FiO2, ALB, BMI, TP, PT, DBIL were screened using the filtration method. The importance ranking of the variables showed that age was the most important variable. Among the six algorithms, the performance of the SVM algorithm is significantly better than that of other algorithms. The AUC, AP, Accuracy, Sensitivity, Specificity, Brier Score, and F1 Scores in the test set were 0.77, 0.67, 0.74, 0.60, 0.81, 0.19, and 0.60, respectively. This indicates the potential value of machine learning models in predicting the prognosis of patients with p- ARDS.
This study developed and visualized a machine learning model constructed based on 10 common clinical features for predicting 28-day mortality in patients with p- ARDS. The model shows good predictive performance and achieves explanatory analysis in combination with SHAP and LIME methods, providing a reliable mortality risk assessment tool for p- ARDS.
本研究旨在构建用于成人急性呼吸窘迫综合征（p-ARDS）患者预后分析的机器学习预测模型。
在这项单中心回顾性研究中，纳入了2020年1月至2024年11月期间在重庆医科大学附属第二医院RICU住院的230例p-ARDS患者。根据28天预后结果将患者分为生存组和死亡组。所有患者的临床资料均为入院后24小时内的首次结果。随机抽取20%的总样本作为测试集，其余样本作为训练集进行交叉验证，并构建了六种不同的模型，包括逻辑回归、随机森林、朴素贝叶斯、支持向量机、XGBoost和Adaboost。使用AUC值、AP值、准确率、敏感性、特异性、布里尔评分和F1评分来评估模型的性能并挑选最优模型。最后，绘制SHAP特征重要性图来解释最优模型。
使用过滤法筛选出10个关键变量，即乳酸清除率（LAR）、乳酸（Lac）、pH值、年龄、氧合指数（PO2/FiO2）、白蛋白（ALB）、体重指数（BMI）、总蛋白（TP）、凝血酶原时间（PT）、直接胆红素（DBIL）。变量的重要性排名显示年龄是最重要的变量。在六种算法中，支持向量机算法的性能明显优于其他算法。测试集中的AUC、AP、准确率、敏感性、特异性、布里尔评分和F1评分分别为0.77、0.67、0.74、0.60、0.81、0.19和0.60。这表明机器学习模型在预测p-ARDS患者预后方面的潜在价值。
本研究开发并可视化了一种基于10个常见临床特征构建的机器学习模型，用于预测p-ARDS患者的28天死亡率。该模型显示出良好的预测性能，并结合SHAP和LIME方法实现了解释性分析，为p-ARDS提供了可靠的死亡风险评估工具。
