Construction Of A Prognostic Prediction Model For Lung Cancer Based On A Weighted Co-expression Networ

Lung cancer is the malignant tumor with the highest incidence rate and mortality in China.The poor prognosis is one of the reasons for the high mortality rate of lung cancer.Most lung cancer patients will experience recurrence after treatment.The five-year average survival rate of lung cancer patients in China is still below 20%,and it is urgent to improve the diagnosis and treatment effectiveness of lung cancer patients.Prognostic analysis of lung cancer is of great significance in improving survival rates.It is necessary to further study the prognostic factors of lung cancer patients,establish prognostic prediction models,predict patient prognostic risks and survival conditions,which can help clinical doctors better judge the patient’s prognosis,propose targeted diagnosis and treatment plans,and increase the patient’s prognostic survival time.This article uses machine learning methods to construct a predictive model for predicting the prognosis of lung cancer patients.Firstly,three omics data,namely gene expression,exon gene expression,and copy number variation,were obtained from the TCGA genomics database.The weighted co expression network was used to analyze and screen characteristic genes closely related to lung cancer occurrence.Based on the selected features,four machine learning methods(logical regression,support vector machine,K nearest neighbor and random forest)were used to build prediction models,and the results showed that logical regression and K nearest neighbor algorithms had good prediction effects(AUC values were 0.841 and 0.831,respectively).This study also utilized a stacked model to integrate the results of the above four methods for prediction,and the prediction results were significantly improved.The AUC values of logistic regression,support vector machine,and K-nearest neighbor reached 0.940,0.952,and 0.982,respectively.The method constructed in this study has a good predictive effect on the prognosis of lung cancer patients,and can assist clinical doctors in making more accurate judgments on the prognosis of lung cancer.