Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning

Objective: We aimed to develop an interpretable model to predict the mortality risk for patients with severe pneumonia. Methods: The study retrospectively employed data from severe pneumonia patients hospitalized at the First Affiliated Hospital of Henan University of Chinese Medicine and Henan Provincial Hospital of Chinese Medicine between January 2008 and November 2021 as the training set for the model development. Patients with severe pneumonia admitted from the same two hospitals between December 2021 and January 2024 were prospectively included as the test set for the model evaluation. The demographic characteristics, clinical manifestations upon admission, risk factors upon admission, comorbidities, complications, laboratory results, treatment during hospitalization, other features, and fatal outcomes were collected. In the training set, all data were analyzed in comparison to survivors and non-survivors. The least absolute shrinkage and selection operator (LASSO) regression was applied to select features for the establishment of five models: logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost). The performance of the models was assessed from discrimination, calibration and clinical practicability. The optimal model was screened out, and SHapley Additive exPlanation (SHAP) method was used to explain. Results: A total of 323 eligible patients with severe pneumonia were enrolled, including 226 patients in the training set and 97 in the test set. In comparison to the other four models, the XGBoost model demonstrated the third highest AUROC (0.853), along with optimal calibration and clinical practicability. The SHAP value of the XGBoost model indicated that the retention catheterization applicationhad the strongest predictive value for all prediction horizons, closely followed by the variables of oral Chinese herbal decoction, BUN level, age, tracheotomy application, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome). Conclusions: Older age, increased BNU level, complication of septic shock, tracheotomy application, retention catheterization application, oral Chinese herbal decoction, and TCM syndrome (pathogenic qi falling into and prostration syndrome) may be potential risk factors that affect mortality in severe pneumonia, among which tracheotomy application and oral Chinese herbal decoction are protective factors. The XGBoost model exhibits superior overall performance in predicting hospital mortality risk for severe pneumonia, greater than traditional scoring systems such as PSI, SOFA, and APACHE II, which assists clinicians in prognostic assessment, resulting in improved therapeutic strategies and optimal resource allocation for patients.