Development of a prediction model based on Hemoglobin, Albumin, Lymphocyte count, and Platelet-score for lymph node metastasis in rectal cancer.

This study aimed to evaluate the ability of the preoperative Hemoglobin, Albumin, Lymphocyte count, and Platelet (HALP) score to predict lymph node metastasis (LNM) in patients with rectal cancer (RC) and improve prediction accuracy by incorporating clinical parameters. Data from 263 patients with RC were analyzed. The receiver operating characteristic (ROC) curve was used to determine the optimal cutoff value (OCV) for the HALP score in predicting LNM. Based on this cutoff value, patients were divided into two groups. A baseline analysis was conducted to identify independent factors linked to LNM. A support vector machine (SVM) prediction model was developed, and its performance was evaluated using ROC, calibration curves, decision curve analysis, and Kolmogorov-Smirnov curve. The OCV for HALP score was 45.979. Patients were then classified into a low HALP group (n = 182) and a high HALP group (n = 81). The analysis found 21 clinical factors significantly associated with LNM. Among them, the key risk factors included high inflammatory status, poor nutritional condition, and a low HALP score. The SVM model incorporated these factors and showed robust predictive performance, with area under the curve values of 0.897, 0.813, and 0.750 for the training, validation, and testing datasets, respectively. The HALP score was significantly associated with LNM in RC patients. A machine learning model integrating the HALP score and inflammatory markers may be an effective tool for predicting LNM in RC.