Supercharge Your Innovation With Domain-Expert AI Agents!

Rheumatoid arthritis prediction method and device based on machine learning

A technology of machine learning and prediction method, applied in the field of machine learning, which can solve the problems of low RA prediction accuracy and prediction efficiency, and cannot well indicate RA risk probability.

Pending Publication Date: 2022-06-07
PEKING UNIV THIRD HOSPITAL
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing prediction method, the detection value of each indicator is divided into negative / positive by using the threshold value of each indicator, and then the results of the two divisions are combined to determine the prediction result, but such a method cannot well indicate the risk probability of RA
[0003] In addition, the existing methods do not take other indicators highly related to RA into consideration, resulting in low prediction accuracy and efficiency of RA

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
  • Rheumatoid arthritis prediction method and device based on machine learning
  • Rheumatoid arthritis prediction method and device based on machine learning
  • Rheumatoid arthritis prediction method and device based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] like figure 1 As shown, the method for predicting rheumatoid arthritis based on machine learning provided by this application includes the following steps:

[0039] S110: Building a Machine Learning Model for Rheumatoid Arthritis.

[0040] Specifically, as an example, as figure 2 As shown, building a machine learning model includes the following steps:

[0041] S210: Obtain the prediction accuracy rates of multiple data analysis methods by using multiple features related to rheumatoid arthritis in all samples of the same first sample set, so as to obtain the data analysis method with the highest prediction accuracy rate.

[0042] Specifically, the first sample set includes samples from a rheumatoid arthritis patient group and a control group, wherein the control group includes two types: a healthy control group and a control group with other immune diseases.

[0043] Setting healthy samples and other disease samples in the first sample set is helpful to more clearly...

Embodiment 2

[0067] Based on the above-mentioned rheumatoid arthritis prediction method, the present application also provides a rheumatoid arthritis prediction device. like image 3 As shown, the device for predicting rheumatoid arthritis includes a model building module 310 , a feature value collection module 320 and a prediction module 330 .

[0068] The model building module 310 is used to build a machine learning model of rheumatoid arthritis.

[0069] The feature value collection module 320 is used to collect multiple features related to rheumatoid arthritis in the patient's sample.

[0070] The prediction module 330 is used to input the multiple features into the machine learning model to predict the rheumatoid arthritis risk probability of the sample.

[0071] Specifically, the model building module 310 includes an accuracy rate obtaining module 3101 , an initial model building module 3102 and a training module 3103 .

[0072] The accuracy rate obtaining module 3101 is configure...

example

[0076] 379 cases in the control group and 271 cases in rheumatoid arthritis patients were collected, with a total of 670 sample data. The six-dimension features of age, gender, rheumatoid factor, anti-cyclic citrullinated polypeptide antibody, 14-3-3η, and Anti-CARP were extracted from each sample, and the five-dimension features except gender were analyzed by z -score normalization processing.

[0077] Then, the features of the above six dimensions are input into the prediction model constructed based on the following seven data analysis methods, and then the five-fold cross-validation method is used to evaluate the accuracy. The results are as follows:

[0078] method Five-fold cross-validation accuracy Naive Bayes Classifier 0.872±0.020 Gradient Boosting Decision Tree Algorithm 0.904±0.025 K-nearest neighbor algorithm 0.879±0.013 Logistic regression analysis 0.903±0.013 Random Forest Algorithm 0.903±0.019 Artificial neural netw...

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 rheumatoid arthritis prediction method and device based on machine learning. The rheumatoid arthritis prediction method comprises the following steps: establishing a machine learning model of rheumatoid arthritis; collecting a plurality of features associated with rheumatoid arthritis in a sample of the patient; and inputting the plurality of features into a machine learning model, and predicting the risk probability of rheumatoid arthritis of the sample. According to the rheumatoid arthritis prediction method and device based on machine learning provided by the invention, the risk probability of rheumatoid arthritis is predicted by integrating a plurality of features through the machine learning model, and compared with a prediction method by simply integrating negative / positive division results of two features, the prediction accuracy is greatly improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, and more particularly, to a method and device for predicting rheumatoid arthritis based on machine learning. Background technique [0002] Rheumatoid arthritis (RA) is a chronic multisystem autoimmune disease caused by persistent inflammatory inflammatory synovitis and subsequent erosion of joint structures. It is considered a complex disease whose etiology is influenced by genetic and environmental risk factors. RA is usually based on two laboratory indicators to predict the probability of developing RA: rheumatoid factor (RF) and anti-cyclic citrullinated peptide antibody (anti-CCP). In the existing prediction method, the detection value of each indicator is divided into negative / positive by using the threshold value of the indicator, and then the results of the two are combined to determine the prediction result, but such methods cannot well indicate the risk probability of...

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
IPC IPC(8): G16H50/20
CPCG16H50/20G16H50/70G06N20/00G06F18/2415
Inventor 崔丽艳白林鹭熊敬维王攀张园周剑锁梁永明冯丽梅吴永华王天成
Owner PEKING UNIV THIRD HOSPITAL
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com