# Immune Predictors of Radiotherapy Outcomes in Cervical Cancer

## TL;DR

This study identifies immune markers and a machine learning model that predict radiotherapy outcomes in cervical cancer patients.

## Contribution

The study introduces CCRTIM, an 8-feature machine learning model for predicting radiotherapy prognosis in cervical cancer.

## Key findings

- RT increases macrophage accumulation, particularly an M1-like HSPA1B+ subset with antigen-presenting capacity.
- C3/C3AR1 axis mediates epithelial-myeloid crosstalk, and its inhibition reduces radiotherapy efficacy in mice.
- CCRTIM model predicts prognosis with an AUC of 0.76 and enables risk stratification.

## Abstract

The immune microenvironment influences the sensitivity of patients to radiotherapy (RT), yet determinants of therapeutic resistance remain elusive. This study integrates single‐cell transcriptomics and machine learning to delineate immune predictors of RT outcomes. Comprehensive analysis reveals reduced epithelial cell numbers, accompanied by enhanced apoptosis, complement activation, and inflammatory responses. RT triggers macrophage accumulation, particularly an RT‐responsive M1‐like HSPA1B+ subset with elevated antigen‐presenting capacity. While T and NK cell cytotoxicity increases, their exhaustion markers (e.g., PDCD1, TIGIT) are exacerbated. CellChat analysis identifies robust epithelial‐myeloid crosstalk mediated by the C3/C3AR1 axis. In murine models, C3AR1 antagonism diminishes RT efficacy, impairing macrophage infiltration and M1 polarization. Leveraging 25 single‐cell‐derived immune features, an 8‐feature multilayer perceptron model: Cervical Cancer Radiotherapy Immune‐Response Model (CCRTIM) is developed. CCRTIM robustly predicts prognosis (AUC = 0.76) and exhibits risk stratification. These findings unveil dynamic immune remodeling post‐RT and establish actionable biomarkers for precision radiotherapy strategies.

This study reveals dynamic immune remodeling in cervical cancer following radiotherapy. Single‐cell analysis identifies the C3/C3AR1 axis as a central mediator of epithelial–myeloid crosstalk, whose inhibition reduces treatment efficacy in mice. Guided by these insights, the eight‐feature machine‐learning model: Cervical Cancer Radiotherapy Immune‐Response Model (CCRTIM) is developed to robustly predict patient prognosis and inform precision immuno‐radiotherapy strategies.