Hemodialysis treatment plan analysis method based on double-machine learning and system thereof

A technology of machine learning and hemodialysis, applied in the field of intelligent analysis, can solve the problems of heavy burden on clinicians in the hemodialysis room and low efficiency of hemodialysis in the hemodialysis center, and achieve the effect of reducing the burden and improving efficiency

Pending Publication Date: 2019-04-26
江苏易透健康科技有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a hemodialysis treatment plan analysis method based on dual-robot learning, which can solve the problems of heavy burden on clinicians in the hemodialysis room and low hemodialysis efficiency in the hemodialysis center. Also provides a hemodialysis treatment plan analysis system based on dual robot learning

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
  • Hemodialysis treatment plan analysis method based on double-machine learning and system thereof
  • Hemodialysis treatment plan analysis method based on double-machine learning and system thereof
  • Hemodialysis treatment plan analysis method based on double-machine learning and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The invention helps the clinicians in the hemodialysis room to form plans for initial visits and follow-up visits by establishing a predictive model, including data preprocessing, screening of important features, establishment of predictive models and formation of plans.

[0031] Such as figure 1 As shown, first of all, because the data collection systems of major hemodialysis centers have been unified and standardized, and full-time personnel are dispatched to collect data in each center according to the plan formulated by data analysts and clinical professionals, independent double entry is adopted , the method of system program verification, so the authenticity, accuracy and practicality of the data are ensured.

[0032] After the training sample data is aggregated, the database is desensitized, cleaned, classified, and processed. Based on the above data preprocessing, the database has been controlled in terms of format and discrete values, but further preprocessing ...

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

The invention discloses a hemodialysis analysis method based on double-machine learning. The method is characterized by comprising the following steps of preprocessing gathered training samples of a hemodialysis center; filling the preprocessed training sample according to a Hot-Deck method, deleting the training samples with variable deletion percentage over alpha, performing variable filling onthe training samples with variable deletion percentage which does not exceed alpha, and obtaining the filled training sample; performing important characteristic screening on the filled training sample through Lasso sparse constraint and Random Forest respectively, and combining two sets of screened training samples for obtaining a final training sample; loading the final training sample into a multivariate linear regression model, performing continuous iteration for obtaining a final prediction model. The method of the invention is combined with a predicating model for a machine learning andhemodialysis first analysis plan in artificial intelligence, thereby reducing the load of a hemodialysis room clinical doctor and improving hemodialysis efficiency of a hemodialysis center.

Description

technical field [0001] The invention relates to the field of intelligent analysis, in particular to a method and system for analyzing a hemodialysis treatment plan based on dual-robot learning. Background technique [0002] Artificial intelligence is experiencing explosive growth. While affecting multiple industries, it is also having an impact on the innovation of the healthcare industry. "AI+medicine" has become a hot field, which has attracted great attention in the academic, medical and management circles. However, there is no relatively mature program to realize the clinician experience to establish the hemodialysis follow-up plan and the prediction model of the hemodialysis first-dialysis plan. Contents of the invention [0003] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a hemodialysis treatment plan analysis method based on dual-robot learning, which can solve the problems of heavy burden on clin...

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 Applications(China)
IPC IPC(8): G16H50/20
CPCG16H50/20
Inventor 王晓骁陶静曹益陆吴永凯
Owner 江苏易透健康科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap