A fine-tuned machine learning model to predict survivals of breast cancer patients based on gamma-delta T cell markers

Abstract

Background: Gamma-delta (γδ) T cells influence cancer immunotherapy and prognosis by enhancing clinical responses to checkpoint inhibitors. However, identifying prognostic markers for γδ T cells remains a crucial challenge. Methods: Initially, we identified γδ T cell markers specific to breast cancer (BC) through single-cell analysis of GSE195861 dataset from the GEO database. Subsequently, we utilized LASSO regression to select prognostic genes for use as variables in artificial intelligence (AI) models. We performed survival analysis, assessed cancer microenvironment scores, and conducted biological functional analysis on these selected genes. Following this, we trained five commonly used machine learning models, and the best-performing model in the training set underwent careful tuning to optimize its performance. Tissues from five GEO datasets and our hospital were used for model validation. Results: Cells of BC were classified into 12 subclasses, and the γδT cells accounted for the majority. Totally, 310 markers of γδT cells were identified, among which 12 were proved to have the prognostic ability by the external validation of GSE20685 (Hazard Ratio (HR) = 1.634, p = 0.031), GSE3143 (HR = 2.887, p = 0.001), GSE19536 (HR = 2.713, p = 0.001), GSE202203 (HR = 2.088, p < 0.001) and GSE35629 (HR = 6.476, p = 0.001). The random forest (RF) model with the 10-fold cross-validation achieved the best accuracy of 0.824 among the trained models. Then performance of the RF model increased to the accuracy of 0.835 after fine-tuned. In the validation, the AUC /accuracy of the fine-tuned RF model is 0.81/0.849 in GSE20685, 0.75/ 0.812 in GSE3143, 0.75/ 0.807 in GSE19536, 0.80/ 0.841 in GSE202203, 0.78/ 0.821 in GSE35629 and 0.77/0.801 in the real-world cohort. Conclusions: We developed an efficient machine learning model based on γδT cell markers, which had a potent capability to predict the prognosis of BC patients.