JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Constructing a Prognostic Model for Subtypes of Colorectal Cancer Based on Machine Learning and Immune Infiltration-Related Genes

  • 0Department of Gastrointestinal Surgery, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, China.
Journal of Cellular and Molecular Medicine +

|

February 26, 2025

|

February 26, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a machine learning model using immune genes to predict colorectal cancer (CRC) patient survival. The model accurately stratifies patients into high- and low-risk groups, aiding personalized treatment strategies.

Area Of Science

  • Computational biology
  • Oncology
  • Immunogenomics

Background

  • Colorectal cancer (CRC) exhibits diverse molecular subtypes.
  • Accurate prognostic models are crucial for personalized treatment strategies in CRC.
  • Identifying immune infiltration-related genes can improve prognostic predictions.

Purpose Of The Study

  • To construct a prognostic model integrating machine learning and immune infiltration-related genes for CRC subtypes.
  • To identify key genes predicting patient prognosis using bioinformatics and machine learning.
  • To develop a robust approach for predicting molecular subtype patient survival in CRC.

Main Methods

  • Utilized publicly accessible gene expression and clinical data for colorectal cancer patients.
  • Employed integrated bioinformatics analysis for immune-wise gene identification.
  • Applied machine learning algorithms (LASSO, random forest) and Cox regression to build a prognostic risk scoring model.
  • Performed functional enrichment, immune infiltration, and genomic variation analyses, validated at the single-cell level.

Main Results

  • Developed a machine learning-based prognostic model with strong predictive power (AUC-ROC, C-index).
  • Successfully stratified CRC patients into high- and low-risk groups with significant differences in overall survival (OS).
  • The model demonstrated good calibration and discrimination abilities.

Conclusions

  • The developed prognostic model offers a robust approach for predicting CRC molecular subtype patient survival.
  • This model has the potential to guide personalized treatment strategies and improve patient outcomes.
  • Further validation in diverse cohorts and clinical settings is warranted.

Keywords: