Predicting Neoadjuvant Treatment Response in Rectal Cancer Using Machine Learning: Evaluation of MRI-Based Radiomic and Clinical Models

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

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.

Radiomics Approaches for the Prediction of Pathological Complete Response after Neoadjuvant Treatment in Locally Advanced Rectal Cancer: Ready for Prime Time?

In recent years, neoadjuvant therapy of locally advanced rectal cancer has seen tremendous modifications. Adding neoadjuvant chemotherapy before or after chemoradiotherapy significantly increases loco-regional disease-free survival, negative surgical margin rates, and complete response rates. The higher complete rate is particularly clinically meaningful given the possibility of organ preservation in this specific sub-population, without compromising overall survival. However, all locally advanced rectal cancer most likely does not benefit from total neoadjuvant therapy (TNT), but experiences higher toxicity rates. Diagnosis of complete response after neoadjuvant therapy is a real challenge, with a risk of false negatives and possible under-treatment. These new therapeutic approaches thus raise the need for better selection tools, enabling a personalized therapeutic approach for each patient. These tools mostly focus on the prediction of the pathological complete response given the clinical impact. In this article, we review the place of different biomarkers (clinical, biological, genomics, transcriptomics, proteomics, and radiomics) as well as their clinical implementation and discuss the most recent trends for future steps in prediction modeling in patients with locally advanced rectal cancer.