Lung cancer prognosis comprehensive prediction model, construction method and device

Abstract

The invention discloses a lung cancer prognosis comprehensive prediction model and a construction method and device. The method comprises the following steps: collecting original gene expression data and corresponding clinical survival data of a lung cancer sample and conducting data preprocessing and standardization, thereby acquiring a gene expression matrix; obtaining the types of immune cells in the tumor and calculating the relative ratio of the various types of immune cells; screening out parameters for constructing a prognosis prediction model from the obtained immune cell types and obtaining corresponding regression coefficients, wherein the parameters are multiple immune cell types; based on the screened parameters, calculating an immune score according to the relative ratio and the corresponding regression coefficient; identifying a gene co-expression module, searching for a gene module cooperatively expressed in the lung cancer sample, and determining a gene module related to prognosis; and constructing a prognosis comprehensive prediction model. According to the invention, immune scores, clinical information and gene co-expression module characteristics are integrated to construct a comprehensive prediction model to predict prognosis of lung cancer patients.

Description

technical field [0001] The invention belongs to the field of biomedicine, and in particular relates to a lung cancer prognosis comprehensive prediction model, a construction method and a device. Background technique [0002] The morbidity and mortality of lung cancer rank among the top among malignant tumors in my country. According to reports, there are more than 600,000 new lung cancer patients in my country each year, and more than 500,000 dead patients, and the mortality rate is increasing year by year. Lung cancer includes non-small cell lung cancer and small cell lung cancer. Non-small cell lung cancer mainly includes lung adenocarcinoma and lung squamous cell carcinoma. Among them, lung adenocarcinoma is the most common type of lung cancer, which is prone to distant metastasis and Poor prognosis features. [0003] Clinically, the operability of lung cancer depends on the TNM stage, and the prognosis of patients with resectable lung cancer depends on the histopatholo...

AI Technical Summary

Problems solved by technology

So far, traditional clinical indicators and staging can only roughly distinguish different stages of lung cancer, which cannot meet the increasing requirements of individualized treatment in clinical practice.

At present, in lung cancer, there is no prognostic model that simultaneously integrates gene expression, infiltrating immune cell content in the tumor, and traditional clinical prognostic indicators for clinical prediction of lung cancer prognosis

Images