Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and system for constructing a Kawasaki disease risk assessment model

A technology of risk assessment model and construction method, applied in medical simulation, medical data mining, medical informatics, etc., can solve the problems of delayed patient treatment, lack of specificity, etc., so as to reduce the cost of detection, highlight the advantages, and avoid missed diagnosis. Effect

Active Publication Date: 2021-11-12
DAOZHI PRECISION MEDICINE TECH SHANGHAI CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to insufficient sensitivity and specificity, patients with Kawasaki disease are missed and misdiagnosed, thus delaying the treatment of patients

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
  • A method and system for constructing a Kawasaki disease risk assessment model
  • A method and system for constructing a Kawasaki disease risk assessment model
  • A method and system for constructing a Kawasaki disease risk assessment model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0107] In order to verify the effectiveness of the system for constructing a Kawasaki disease risk assessment model of the present invention, this example selects 42,498 patient data in the electronic case from July 2008 to March 2018.

[0108] 1. Data processing:

[0109] After the original data set is deleted, the incomplete data set includes 8204 samples, and the complete data set contains 471 samples. According to the present invention, the data set has the form: each row represents information of a patient, and each column represents a characteristic information, such as ID, group, gender, age, CRP, FG, etc., and the format of the data set is as Table 1.

[0110] Through data sample selection and feature screening, the final generated data set contains 8675 rows and 11 columns of features, as shown in Table 1.

[0111] Table 1

[0112]

[0113] 2. Optimal model data

[0114] The incomplete data set is randomly divided into training set (5742), verification set (2462),...

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 construction method and construction system of a Kawasaki disease risk assessment model. The construction method includes: extracting effective samples that can be used for modeling evaluation from the sample data set; screening out 10 features that meet the application of on-site medical auxiliary diagnosis from the feature set of the effective samples; The data set is randomly divided into a training set and a validation set; the random forest method is used to fit the training set for model building, and the optimal model parameters are recorded according to the out-of-bag error; at the same time, the model classification threshold t is calculated using the validation set according to the ROC curve, so that A Kawasaki disease risk assessment model was constructed. The evaluation model of the present invention can quickly and effectively assist patients with suspected Kawasaki disease, which helps to reduce the rate of misdiagnosis and missed diagnosis, so that patients can obtain effective prevention, intervention and treatment in the early stage of onset, in order to achieve the best treatment The effect provides a basis.

Description

technical field [0001] The invention relates to a method for constructing a model, in particular to a method for constructing an assessment model for predicting Kawasaki disease risk based on time dominance and a random forest algorithm, a construction system, and an assessment system, which belong to the technical field of risk assessment model construction. Background technique [0002] Kawasaki disease, also known as mucocutaneous lymph node syndrome, is an autoimmune disease with systemic vasculitis as the main lesion, and has affected more than 60 countries around the world. Among them, the coronary artery is more likely to be involved, and it is a febrile eruptive disease of unknown cause. Kawasaki disease mainly manifests as persistent fever for more than 5 days, and also includes: (1) Symptoms of conjunctival congestion in both eyes, but no exudation (2) redness of the lips, red bayberry tongue, and diffuse congestion of the oral and pharyngeal mucosa; (3) erythema m...

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): G16H50/50G16H50/70G16H50/20
CPCG16H50/20G16H50/50G16H50/70
Inventor 丁国徽贾佳李光徐重飞宁倩倩周珍
Owner DAOZHI PRECISION MEDICINE TECH SHANGHAI CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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