# A serum metabolite-based machine learning model predicts response to neoadjuvant immunotherapy in mismatch repair-deficient colorectal cancer

## TL;DR

A blood test using machine learning can predict which mismatch repair-deficient colorectal cancer patients will respond to immunotherapy.

## Contribution

Development of a non-invasive serum metabolite-based machine learning model to predict immunotherapy response in dMMR colorectal cancer.

## Key findings

- A 5-metabolite predictive model (5-MPM) achieved AUC values of 0.85 in training and 0.88 in external validation.
- The model includes PGE2, tryptophan, arginine, citrulline, and histidine as key metabolites.
- SHAP analysis revealed individual metabolite contributions to model predictions.

## Abstract

Colorectal cancer (CRC) with microsatellite instability-high (MSI-H) or mismatch repair-deficient (dMMR) shows significant sensitivity to immune checkpoint inhibitors (ICIs). However, a considerable proportion of patients still exhibit primary or acquired resistance to ICIs. Until now, efficient and non-invasive biomarkers for accurately predicting immunotherapy efficacy remain unavailable.

In this multicenter study, we employed liquid chromatography–mass spectrometry (LC–MS) and enzyme-linked immunosorbent assay (ELISA) to identify and validate serum metabolites associated with response to immunotherapy. Using machine learning algorithms, we constructed a random forest predictive model based on a panel of five metabolites. This model, termed the 5-Metabolite Predictive Model (5-MPM), incorporates prostaglandin E2 (PGE2), tryptophan, arginine, citrulline, and histidine.

The 5-MPM model demonstrated robust predictive performance in both training cohort and external validation cohort, with AUC values of 0.85 and 0.88, respectively. The SHAP analysis elucidated the contribution of each metabolite to model predictions. Integrating above five metabolites with metastasis stage did not further improve the predictive performance of this model.

This study provides the first systematic characterization of metabolic reprogramming in dMMR colorectal cancer with different response to immunotherapy, and establishes a non-invasive, high-precision predictive tool that offers a new basis for individualized therapeutic decision-making.