Unlock instant, AI-driven research and patent intelligence for your innovation.

Diabetic retinopathy early warning method based on bp neural network

A BP neural network and diabetic retina technology, applied in the field of biomedicine, can solve the problems of no prediction method, complex detection, inaccurate data, etc., and achieve the effect of low experimental error and excellent training effect.

Active Publication Date: 2022-06-21
HENAN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still few studies on early warning of the risk of diabetic retinopathy. Due to the complexity of detection and inaccurate data, there is no good prediction method to achieve early warning of diabetic retinopathy.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Diabetic retinopathy early warning method based on bp neural network
  • Diabetic retinopathy early warning method based on bp neural network
  • Diabetic retinopathy early warning method based on bp neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Based on the BP neural network theory, the invention establishes a new early warning model of diabetes onset, which can early warning the onset of diabetes by identifying the index values ​​of key markers of the disease. This method is superior to other methods. It can detect the key markers that affect the prevalence of diabetic retinopathy. In the clinic, we only need to detect the key markers, and use the algorithm to calculate the risk warning value of the key markers, and further Improve the identification of key early warning factors in diabetes complications, and provide more reference and basis for scientific diagnosis and treatment of the disease. During the research, real patient data from the "National Population Health Science Data Center Data Warehouse PHDA" was used, and the model was trained and verified based on the MATLAB language.

[0042] This method is mainly composed of two parts: firstly, the data samples are trained by the improved BP neural netwo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Diabetic retinopathy early warning method based on BP neural network, based on BP neural network theory, establishes a new early warning model of diabetes onset, which can warn the onset of diabetes by identifying the index values ​​of key markers of the disease. In this study, by adjusting the functions and neuron parameters of the BP neural network several times, a network model with the best training effect and the lowest experimental error was obtained, and the weight matrix in the network state was obtained, and the weight data of each medical index in the transmission process were obtained. Do hierarchical clustering analysis, select molecular modules with higher weight and the closest clustering distance as the key markers for disease early warning, not only to study the independent importance of individual sign indicators in disease early warning, but also to pay attention to the induction of disease between them It has unique advantages in the study of diabetic complications.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a method for early warning of diabetic retinopathy based on BP neural network. Background technique [0002] Up to now, diabetes has developed into the third largest chronic disease after cardiovascular disease and malignant tumor disease. Among them, diabetes is a clinically heterogeneous glucose intolerance syndrome, mainly due to autoimmune-mediated Metabolic disease characterized by insulin deficiency and disturbance of glucose metabolism caused by selective pancreatic β-cell damage. Chronically high blood sugar levels in the body can pose serious health risks, and some people with diabetes develop a form of retinopathy, a complication known as diabetic retinopathy. Compared with type 1 diabetes and type 2 diabetes, the current research on the pathogenesis and early warning of diabetes complications at home and abroad is relatively rare. Previous studies on the risk early warning...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/20G16H50/30G16H50/70G06N3/08
CPCG16H50/20G16H50/30G16H50/70G06N3/084
Inventor 李培峦李沛谕闫金铃仝利红陈曦
Owner HENAN UNIV OF SCI & TECH