Prognostic Value of Preoperative ICPI in Rectal Cancer: A Nomogram Based Approach

Objective This study examines the prognostic significance of preoperative inflammatory combined prognostic index (ICPI) in patients having laparoscopic rectal cancer surgery and constructs a machine learning-derived nomogram to predict patient prognosis. Methods This study retrospectively collected patients who underwent laparoscopic rectal cancer surgery from January 2016 to January 2021. Patients receiving neoadjuvant therapy were excluded due to its alteration of inflammatory markers and pathology. The optimal cut-off values for neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), and ICPI were 3.0, 171.82, 0.32, and 4.3, respectively. Prognostic features were identified from the training cohort using three ML methods (Lasso Regression, XGBoost, Random Forest), with consensus features selected through intersection analysis. Cox regression was performed to establish a nomogram for predicting 1-year, 3-year, and 5-year overall survival (OS) in rectal cancer patients. The enhancement in predictive capability and clinical benefit were evaluated through the Concordance Index (C-index), Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA). Results A total of 357 patients were enrolled and randomly divided into a training cohort (70%, n = 249) and a validation cohort (30%, n = 108).Additionally, patients with high NLR, PLR, MLR, and ICPI had poorer OS (P < 0.001). After machine learning and multivariable Cox regression, pN stage, carcinoembryonic antigen (CEA), surgical time, ICPI, and age were identified as independent prognostic factors affecting OS. A nomogram was constructed, and the area under the curve (AUC) values in both the training and validation cohorts exceeded 0.80, with C-indices of 0.80 and 0.79, respectively. The calibration curves demonstrated good agreement between the predicted and actual outcomes, indicating high prediction accuracy. DCA revealed that the nomogram exhibited a higher net benefit. Conclusion ICPI integrates multiple inflammatory parameters to predict rectal cancer survival. We also developed a machine learning-based nomogram for predicting OS in laparoscopic rectal cancer surgery patients.