Artificial intelligence-based dynamic prediction model construction method and system for cerebrovascular disease

Abstract

The invention discloses a method and system for constructing a dynamic prediction model of cerebrovascular disease based on artificial intelligence. The method includes: extracting features from item values ​​of test results of target patients, obtaining the feature extraction results, and performing feature extraction on the feature extraction results. Perform feature transformation on multiple first features, obtain multiple second features after transformation, construct a risk factor model according to multiple preset features of cerebrovascular disease and the weight value of each preset feature, and convert the multiple second features. The features are substituted into the risk factor model for fitting, a preset Adam optimization algorithm is constructed according to the fitting results, a cerebrovascular disease prediction model is pre-built, and the preset Adam optimization algorithm is used to train the cerebrovascular disease prediction model, Obtain the trained cerebrovascular disease prediction model. Accurate cerebrovascular disease assessment can be performed according to the commonly used examination items of patients, which ensures the accuracy and objectivity of the assessment results. Reduce costs and improve user experience.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and big data medical prediction models, in particular to a method and system for constructing a dynamic prediction model of cerebrovascular disease based on artificial intelligence. Background technique [0002] Cerebrovascular disease is a chronic disease that endangers national health. The results of the latest China National Cerebrovascular Disease Screening Survey (CNSSS) show that from 2002 to 2013, the number of people aged 40 to 74 in China ranked first The proportion of symptoms of cerebrovascular disease increased significantly from 189 / 100,000 people to 379 / 100,000 people, and the overall annual growth rate was as high as 8.3% (higher than China's GDP growth rate in the same period). According to the analysis results of the China Cerebrovascular Epidemiological Survey (NESS-China) published in 2017: cerebrovascular disease is one of the leading causes of death in my count...

AI Technical Summary

Problems solved by technology

[0003] In view of the problems shown above, the present invention provides a method and system for constructing a dynamic prediction model of cerebrovascular disease based on artificial intelligence to solve the problem that the artificial prediction results mentioned in the background technology are relatively subjective, and the prediction accuracy rate will vary with time. The level of doctors fluctuates up and down, which leads to the occurrence of prediction errors. At the same time, the cost of examinations related to cerebrovascular diseases is not low, so that most people cannot predict the probability of their own cerebrovascular diseases, which reduces the user experience.

Images