Esophageal squamous carcinoma risk prediction system

Abstract

The invention discloses an esophageal squamous carcinoma risk prediction system, which comprises an input module, a calculation module and an output module, esophageal squamous carcinoma three-year risk prediction models Model1 and Model2 are built in the calculation module, and the two prediction models are obtained based on cancer screening data of Chinese population. Through internal and external verification, the model disclosed by the invention has better discrimination capability, is higher than the c-statuses (area under an ROC curve) of the previous model, and has good discrimination capability and clinical significance. According to the risk prediction system disclosed by the invention, the esophageal squamous cell carcinoma prediction models Model1 and Model2 are built in, so that the risk of esophageal squamous cell carcinoma can be effectively predicted, and the application prospect is good.

Description

technical field [0001] The invention relates to a risk prediction system for esophageal squamous cell carcinoma, in particular to a prediction system for predicting the risk of esophageal squamous cell carcinoma in healthy people. Background technique [0002] Among noncommunicable diseases, cancer has emerged as a particularly important health problem. Cancer is the first or second leading cause of premature death (ie death between 30-69 years) in more than 90 countries around the world. [0003] In addition, esophageal squamous cell carcinoma remains the main type of esophageal cancer in Asia, Africa and South America, and African Americans in North America. [0004] In 2005, the state issued guidelines for cancer screening, early diagnosis and early treatment in China, including guidelines for early detection and treatment of esophageal cancer. The guidelines pointed out that it is suitable for high-incidence areas of esophageal cancer in rural areas of China and high-ri...

AI Technical Summary

Problems solved by technology

[0006] The current prediction model for esophageal squamous cell carcinoma has the following defects: (1) The prediction model established based on case-control studies has a low level of evidence quality in evidence-based medicine and is a discriminative model

(2) The predictive model based on the cohort uses unconditional univariate logistic regression, and logistic regression cannot effectively use survival data

(3) The prediction models are all based on questionnaire data and do not consider endoscopy-related information

For the population participating in endoscopy, only using questionnaire-based data to predict the risk of esophageal squamous cell carcinoma will reduce the accuracy of risk calculation

Images