A Machine Learning Model to Predict Post-Operative Intensive Care Unit Admission in Patients with Cancer Based on Clinical Characteristics and Hematologic Parameters Data

Background and Objectives: The prioritization of intensive care unit (ICU) admission following surgery for cancer is controversial. There is an urgent need to develop an appropriate clinical predictive model to aid in making ICU admission decisions after surgery. Materials and Methods: Four model strategies were used to build post−operative ICU admission predictive models: SVM, Catboost, ANN, and KNN. Internal verification was used for model evaluation at a ratio of 7:3. The area under the curve (AUC) value, calibration plots, and decision curve analysis were employed to assess the performance and clinical usefulness of the model. Results: The ICU group of patients with cancer who underwent surgery showed better prognosis for disease−free survival (DFS, p = 0.0008) and overall survival (OS, p < 0.0001). Cox multivariate analyses validated that lower baseline RBC, LDH, and CRP; higher baseline ALB, LCR, and lower post−operative LDH; higher post−operative HCT and ApoA−I; and higher fluctuating MCH independently predicted better DFS and OS (all p < 0.05). The AUC of the Catboost model was superior to that of the other models in the training cohort and internal validation cohort. Calibration plot and decision curve analysis indicated that the Catboost model possessed the best performance, with higher clinical utility, compared with other models. Conclusions: ICU admission after surgery was associated with superior survival in patients with cancer. The cost−effective Catboost model has promising clinical application but requires further clinical evaluation. Unravelling the cellular and molecular foundation of ICU admission might enable the development of more practical life−support strategies.