Neural network hepatofibrosis diagnosis method and system
暂无分享,去创建一个
The invention discloses a neural network hepatofibrosis diagnosis method and a system thereof, and aims to solve the problems of low accuracy and the like in the prior art. The neural network hepatofibrosis diagnosis system comprises three application modules of data management, neural network, and clinical diagnosis. The data management module provides data entry, editing and modification, deleting, and other operating functions, and at the same time further provides data importing and exporting functions which are convenient for data management. The neural network module comprises an input layer and a hidden layer, optimizes the internal link relations of the neural network through network training, and tests the diagnosis accuracy of the trained neural network through network testing. The clinical diagnosis module uses the trained neural network to carry out diagnosis through inputting patient detection data. According to the invention, a neural network technology is used to establish a diagnosis model, appropriate indexes are screened out as the diagnosis bases through a multifactor regression analysis, the operation is simple, the data management is convenient, both the sensitivity and the singularity of the diagnosis can better satisfy clinical demands, and a reference is provided for the clinical diagnosis of hepatofibrosis.