Development and internal validation of a predictive model for clinical deterioration in newly diagnosed lung cancer patients based on interpretable machine learning

ObjectiveTo develop and validate an interpretable machine learning–based model for the early identification of the risk of clinical deterioration during hospitalization in newly diagnosed lung cancer patients.MethodsClinical data of patients with newly diagnosed lung cancer admitted between July 2023 and December 2025 were retrospectively collected in this single-center study. A hybrid feature selection strategy integrating least absolute shrinkage and selection operator (LASSO) regression and the Boruta algorithm was employed to identify key predictors. Logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) models were constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC), calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) values were further applied to interpret the model's decision-making process.ResultsA total of 1,001 newly diagnosed lung cancer patients were included, comprising 121 patients (12.1%) in the deterioration group and 880 patients (87.9%) in the non-deterioration group. Through the hybrid feature selection approach, five core predictive variables were identified, including Activities of Daily Living (ADL) score, lymphocyte count, C-reactive protein (CRP), respiratory rate, and neutrophil count. Among the models, the SVM model achieved the highest observed AUC of 0.822 (95% CI: 0.737–0.899) in the internal validation set, with a sensitivity of 0.750 (95% CI: 0.594–0.893) and a specificity of 0.792 (95% CI: 0.740–0.838). After Platt scaling calibration, the model achieved a Brier score of 0.083 (Hosmer-Lemeshow p = 0.649), with a calibration intercept of 0.141 and a slope of 1.126, indicating satisfactory agreement between predicted and observed risks. DCA suggested a potential net clinical benefit. SHAP analysis, in conjunction with multivariable regression results, consistently demonstrated that ADL score and lymphocyte count were associated with reduced risk of clinical deterioration, whereas CRP and neutrophil count were associated with increased risk.ConclusionThe SVM model developed in this study may help identify patients at risk of clinical deterioration among hospitalized lung cancer patients and may assist healthcare professionals in achieving early risk identification and potential clinical decision support.