A comprehensive prediction model, construction method and device for lung cancer prognosis

Abstract

The invention discloses a lung cancer prognosis comprehensive prediction model, a construction method and a device. The method comprises the following steps: collecting original gene expression data and corresponding clinical survival data of lung cancer samples, performing data preprocessing and standardization, and obtaining a gene expression matrix; obtaining tumor Types of internal immune cells and calculate the relative ratio of each type of immune cells; Screen out the parameters for constructing the prognosis prediction model from the acquired immune cell types and obtain the corresponding regression coefficients, the parameters are a variety of immune cell types; Based on the screened out According to the relative ratio and the corresponding regression coefficient, calculate the immune score; identify the gene co-expression module, find the gene module co-expressed in the lung cancer sample, and determine the gene module related to the prognosis; construct the comprehensive prediction model of the prognosis; the present invention Integrate immune score, clinical information and gene co-expression module features to build a comprehensive prediction model to predict the prognosis of lung cancer patients.

Description

technical field [0001] The invention belongs to the field of biomedicine, and in particular relates to a comprehensive prediction model of lung cancer prognosis, 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 and more than 500,000 deaths in my country every year, 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 two pathological types, lung adenocarcinoma and lung squamous cell carcinoma. Lung adenocarcinoma is the most common type of lung cancer. features of poor prognosis. [0003] Clinically, whether lung cancer can be operated or not depends on TNM staging, and the prognosis of patients with resectable lung cancer depends on the histopathological criteria of tu...

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