Predictive value of circulating lymphocyte subsets and inflammatory indexes for neoadjuvant chemoradiotherapy response in rectal mucinous adenocarcinoma patients: A machine learning approach.

ABSTRACT

INTRODUCTION: In this study, we aimed to evaluate the predictive value of circulating lymphocyte subsets and inflammatory indexes in response to neoadjuvant chemoradiotherapy (NCRT) in patients with rectal mucinous adenocarcinomas (MACs). METHODS: Rectal MAC patients who underwent NCRT and curative resection at Fujian Medical University Union Hospital's Department of Colorectal Surgery between 2016 and 2020 were included in the study. Patients were categorized into good and poor response groups based on their pathological response to NCRT. An independent risk factor-based nomogram model was constructed by utilizing multivariate logistic regression analysis. Additionally, the extreme gradient boosting (XGB) algorithm was applied to build a machine learning (ML)-based predictive model. Feature importance was quantified using the Shapley additive explanations method. RESULTS: Out of the 283 participants involved in this research, 190 (67.1%) experienced an unfavorable outcome. To identify the independent risk factors, logistic regression analysis was performed, considering variables such as tumor length, pretreatment clinical T stage, PNI, and Th/Tc ratio. Subsequently, a nomogram model was constructed, achieving a C-index of 0.756. The ML model exhibited higher prediction accuracy than the nomogram model, achieving an AUROC of 0.824 in the training set and 0.762 in the tuning set. The top five important parameters of the ML model were identified as the Th/Tc ratio, neutrophil to lymphocyte, Th lymphocytes, Gross type, and T lymphocytes. CONCLUSION: Radiochemotherapy sensitivity is markedly influenced by systemic inflammation and lymphocyte-mediated immune responses in rectal MAC patients. Our ML model integrating clinical characteristics, circulating lymphocyte subsets, and inflammatory indexes is a potential assessment tool that can provide a reference for individualized treatment for rectal MAC patients.