JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Establishment of multiple machine learning prognostic model for gene differences between primary tumors and lymph nodes in luminal breast cancer

  • 0Department of Pathology, The Fourth Hospital of Hebei Medical University, No. 12 Jiankang Road, Shijiazhuang, 050011, Hebei, China.
Breast Cancer Research and Treatment +

|

December 10, 2024

|

December 10, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a new prognostic model (LMRS) using 26 genes to predict breast cancer patient outcomes. The model accurately forecasts prognosis by analyzing gene expression in primary tumors and lymph nodes.

Area Of Science

  • Oncology
  • Genomics
  • Bioinformatics

Background

  • Understanding gene expression differences between primary tumors (PT) and metastatic lymph nodes (LN) is crucial for breast cancer prognosis.
  • Existing models may not fully capture the complexity of tumor-lymph node interactions.

Purpose Of The Study

  • To explore the correlation between primary tumors and paired metastatic lymph nodes.
  • To develop and validate a predictive model for forecasting patient prognoses in breast cancer.

Main Methods

  • Acquired single-cell, bulk transcriptome, survival, clinical, and mutation data from GEO and TCGA.
  • Developed and validated a prognostic model using a machine learning integration framework with ten algorithms.
  • Constructed the Lymph Node Metastasis-Related Scores (LMRS) model using 26 differentially expressed genes.

Main Results

  • The LMRS model demonstrated high stability and effectiveness, outperforming 64 other models.
  • High LMRS scores correlated with downregulated cytolytic activity, T cell co-stimulation, and immune cells (B cells, CD8+ T cells, iDCs, TILs).
  • Hub biomarkers PGK1 and HSP90 showed higher expression in PT and LN, with higher levels in LN than PT.

Conclusions

  • A multiple-gene prognostic model (LMRS) with high clinical accuracy was developed for breast cancer prognosis.
  • The study highlights significant gene expression differences between PT and LN.
  • The LMRS model offers valuable evidence for forecasting patient prognoses.

Keywords: