Method for establishing early screening light-chain amyloidosis based on machine learning and application thereof

An amyloidosis and machine learning technology, applied in the fields of instrumentation, informatics, medical informatics, etc., to improve the early diagnosis rate, easy to popularize and use, and improve the accuracy.

Pending Publication Date: 2021-12-03
SHENGJING HOSPITAL OF CHINA MEDICAL UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although existing techniques such as immunofixation electrophoresis (IFE), serum-free light chain (FLC), and Congo red staining can be used to screen for the diagnosis of AL amyloidosis in relation to chronic renal insufficiency and heart failure, however, physicians typically do not These targeted and invasive tests are performed on patients with early symptoms

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
  • Method for establishing early screening light-chain amyloidosis based on machine learning and application thereof
  • Method for establishing early screening light-chain amyloidosis based on machine learning and application thereof
  • Method for establishing early screening light-chain amyloidosis based on machine learning and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Example 1 Establishment of a method for screening light chain amyloidosis based on machine learning

[0050] 1. The random forest model is an integrated learning algorithm based on decision trees, and its construction process is as follows:

[0051] (1) Assuming that there are N samples, then randomly select n samples with replacement; use the selected n samples to train a decision tree as the sample at the root node of the decision tree;

[0052] (2) When each sample has M attributes, when each node of the decision tree needs to be split, randomly select m attributes from the M attributes, satisfying the condition m

[0053] where p i,k is the proportion of training instances of class k on the i-th node;

[0054] (3) During the formation of the decision tree, each node must be split according to step 2 until it can no longer be split;

[0055] (4) Build a large number of decision trees according to steps 1 to 3, thus forming a random forest.

[0056] 2. The suppo...

Embodiment 2

[0078] Example 2 The clinical application of a method for early screening of light chain amyloidosis based on machine learning.

[0079] The Medical Ethics Committee of Shengjing Hospital of China Medical University approved this study (2020PS055J) according to the principles of the Declaration of Helsinki. After the approval of the ethics committee and the exemption of informed consent, the patient data were anonymized and analyzed retrospectively. The flowchart and complete model training process as figure 1 shown.

[0080] 1. Patients and Data Sources

[0081] From January 2010 to January 2020, the relevant data of 1064 patients were collected in 18 hospitals in the China Light Chain Amyloidosis Registry Network (CRENLA), including general information, blood routine, urine test, biochemical test and echocardiography. In addition, the relevant data of 1000 cases of non-AL amyloidosis (heart failure, cardiomyopathy, liver disease and kidney disease) were randomly selected...

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 belongs to the technical field of early screening and artificial intelligence of light-chain amyloidosis, and particularly relates to a method for establishing an artificial intelligence auxiliary system for early screening of light-chain amyloidosis based on machine learning in combination with clinical routine assay and echocardiography and application of the artificial intelligence auxiliary system. According to the conventional test results of 1064 clinical cases of light-chain amyloidosis and non-AL amyloidosis (heart failure, cardiomyopathy, liver diseases and kidney diseases), an early auxiliary screening model of the AL amyloidosis is established by using RF, SVM, DNN and GBDT, and the prediction possibility accuracy can reach 90% or above. The early warning model has the characteristics of easiness in popularization and convenience in use, can greatly improve the cognition of light-chain amyloidosis in primary hospitals and the early screening of patients, and has wide application prospects and profound clinical significance.

Description

technical field [0001] The invention belongs to the field of early screening of light chain amyloidosis and the technical field of artificial intelligence, and specifically relates to a method for establishing an artificial intelligence auxiliary system for early screening of light chain amyloidosis based on machine learning combined with clinical routine tests and echocardiography and its application. Background technique [0002] Primary light chain amyloidosis is a rare disease that is difficult to diagnose in its early stages. It is a disease in which amyloid is formed by the misfolding of monoclonal immunoglobulin light chains and deposited in tissues and organs, resulting in tissue structure destruction, organ dysfunction and progressive progression. Due to the clinical manifestations of multiple organ involvement (including kidney, heart, liver, skin and soft tissue, peripheral nerves, lung, glands and other organs and tissues) and the lack of awareness of most clini...

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): G16H50/20G16H50/70G06K9/62
CPCG16H50/20G16H50/70G06F18/24323
Inventor 王慧涵李剑何涛燕玮陈剑
Owner SHENGJING HOSPITAL OF CHINA MEDICAL UNIV
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