Diabetic nephropathy screening method, model and system based on AI technology
A technology for kidney disease and diabetes, applied in the field of models for kidney disease screening, which can solve problems such as increased risk and heavy disease burden
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0116] The present invention proposes a screening model for diabetic kidney disease based on AI technology, including dynamic covariates and Logistic regression calculation methods.
[0117] Further, the dynamic covariate is K-dimensional data, and the K-dimensional data is data after PCA dimension reduction processing; the PCA dimension reduction processing includes the following steps:
[0118] Form the sample data into a matrix X with n rows and m columns by column; zero-meanize each row of X, and subtract the mean value of this row; find the covariance matrix C=1 / mXXT; find the eigenvalues of the covariance matrix and Corresponding eigenvectors; arrange the eigenvectors into a matrix from top to bottom according to the size of the corresponding eigenvalues, and take the first k rows to form a matrix P; Y=PX is the data after dimensionality reduction to k dimensions, thereby obtaining K-dimensional data .
[0119] Further, the Logistic regression calculation method, the ...
Embodiment 2
[0121] The present invention also proposes a method for screening diabetic kidney disease based on AI technology, comprising the following steps:
[0122] Steps of S1 data collection: Obtain the electronic medical record data of diabetic patients from the hospital electronic medical record database according to the inclusion criteria and exclusion criteria, and obtain the sample data;
[0123] Steps of S2 data cleaning and standardization preprocessing: the cleaning and standardization of sample data is based on the established medical entity standard library and the specified unit conversion; find out the different unit names in the sample data, and use the unified unit to compare the different unit names Perform unified replacement; assign and convert non-numeric data in sample data; formulate non-numeric data conversion rules, and perform assignment and conversion on non-numeric data in sample data according to the conversion rules; perform outlier processing on numerical da...
Embodiment 3
[0163] The present invention proposes a diabetic kidney disease screening system based on AI technology. The system includes a user data input module, a diabetic kidney disease screening module, and a screening result output module.
[0164] The user data input module is used to send the input user data to the diabetic kidney disease screening module;
[0165] The screening result output module is used to display the screening result of the diabetic kidney disease screening model, the result being the risk of diabetic nephropathy, such as "yes" or "no".
[0166] The diabetic kidney disease screening module includes a PCA dimension reduction processing sub-module and a high-quality model, and the diabetic kidney disease screening module adopts the following steps to establish:
[0167] (1) Steps of data collection: Obtain the electronic medical record data of diabetic patients from the hospital electronic medical record database according to the inclusion and exclusion criteria, ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com