Constructing a Risk Prediction Model for Lung Cancer Recurrence by Using Gene Function Clustering and Machine Learning

Abstract

Objective: A significant proportion of patients with early non-small cell lung cancer (NSCLC) can be cured by surgery. The distant metastasis of tumors is the most common cause of treatment failure. Precisely predicting the likelihood that a patient develops distant metastatic risk will help identify patients who can further intervene, such as conventional adjuvant chemotherapy or experimental drugs.

Methods: Current molecular biology techniques enable the whole genome screening of differentially expressed genes, and rapid development of a large number of bioinformatics methods to improve prognosis.

Results: The genes associated with metastasis do not necessarily play a role in the pathogenesis of the disease, but rather reflect the activation of specific signal transduction pathways associated with enhanced migration and invasiveness.

Conclusion: In this study, we discovered several genes related to lung cancer resistance and established a risk model to predict high-risk patients.

Keywords: Functional cluster; gene expression; lung cancer; machine learning; predictive model; recurrent..