Personalized Medicine Breakthrough: Gastric Cancer Prognostic Model Developed Using Machine Learning

Strategic Insights -

A team of researchers from the Renmin Hospital of Wuhan University, in collaboration with international partners, has made a groundbreaking discovery in the field of personalized medicine. By leveraging machine learning algorithms, the team has developed a highly accurate prognostic model for gastric cancer, a highly heterogeneous disease that requires precise treatment approaches. The study's findings, published in the Journal of Molecular Histology, suggest that the model can accurately evaluate the prognosis of gastric cancer patients and contribute to the development of personalized treatment plans.

Key Takeaways:

  • The study utilized machine learning algorithms to identify 7 hub genes (CGB5, FEM1A, MATN3, ZNF101, MARCKS, BRI3BP, and APOD) closely related to gastric cancer prognosis.
  • A high-precision risk model was constructed using these 7 hub genes, and the risk score was calculated using random survival forest (RSF) and generalized boosted regression modeling (GBM).
  • The risk model showed good predictive ability for gastric cancer patients' prognosis, with the risk score serving as an independent prognostic factor.
  • Immunohistochemical staining revealed that the protein expression levels of CGB5, MATN3, MARCKS, and APOD in gastric cancer tissues were significantly higher than those in normal tissues, correlating with pathological characteristics of gastric cancer patients.

Statistics:

  • The study analyzed transcriptome data and clinical information of gastric cancer patients obtained from the Cancer Genome Atlas (TCGA) database.
  • Microarray data (GSE84437 and GSE26253) were obtained from the Gene Expression Omnibus (GEO) database.
  • Univariate Cox regression analysis was used to screen prognostic genes, with 7 hub genes identified.
  • The risk model had a good predictive ability, with approximately 90% accuracy in evaluating gastric cancer patients' prognosis.

Sources:

  • A prognostic model for gastric cancer constructed by multiple machine learning algorithms. Journal of Molecular Histology, 2025;56(6):340.
  • NewsRx. Recent Findings from Renmin Hospital of Wuhan University Advance Knowledge in Personalized Medicine (A prognostic model for gastric cancer constructed by multiple machine learning algorithms). Cancer Weekly. October 28, 2025; p 2656.