Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Myeloma high-risk screening method based on GBDT model and application of myeloma high-risk screening method

A myeloma, high-risk technology, applied in the field of screening high-risk myeloma, to achieve the effect of improving early treatment rate, high accuracy, and profound clinical significance

Pending Publication Date: 2021-04-13
SHENGJING HOSPITAL OF CHINA MEDICAL UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no method at home and abroad to establish a high-risk screening model for myeloma based on routine assays and using artificial intelligence

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
  • Myeloma high-risk screening method based on GBDT model and application of myeloma high-risk screening method
  • Myeloma high-risk screening method based on GBDT model and application of myeloma high-risk screening method
  • Myeloma high-risk screening method based on GBDT model and application of myeloma high-risk screening method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] Embodiment 1 The establishment of a method for predicting the risk of myeloma based on the GBDT model.

[0037]GBDT (Gradient Boosting DecisionTree) is an integrated learning algorithm, which consists of DecisionTree (decision tree) and Gradient Boosting (gradient boosting). The GBDT output is the accumulation of the output results of each decision tree. Using the combination of gradient boosting and regression decision trees, each time a new decision tree model is established, it is in the direction of the gradient of the loss function of the previous model, so that the decision model is continuously improved. .

[0038] 1. Decision tree algorithm.

[0039] Decision tree algorithm is an important algorithm in machine learning and data mining. It is mainly used to deal with some problems under given rule conditions. Like most algorithm models, this algorithm can be used to classify and regress data, so as to establish an effective data model to deal with related probl...

Embodiment 2

[0066] Example 2 The clinical application of the myeloma risk prediction method based on the GBDT model.

[0067] The Medical Ethics Committee of Shengjing Hospital of China Medical University approved this study (2020PS055J) according to the principles of the Declaration of Helsinki. The ethics committee waived the requirement for individual informed consent when conducting a retrospective study of electronic medical records. 1. Screening of patients and data.

[0068] In this retrospective study, the institutional database of Shengjing Hospital of China Medical University was screened to investigate patients who underwent routine blood tests, liver function tests, renal function tests, and immunoglobulin tests for the first time in our hospital from January 2010 to January 2020. These included 1741 cases of multiple myeloma (MM) and 2446 cases of non-myeloma (infectious disease, rheumatic immune system disease, liver disease and kidney disease). The inventors also collecte...

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 myeloma high-risk screening method based on a GBDT model and application of the myeloma high-risk screening method. The invention belongs to the technical field of tumor early-stage high-risk screening and artificial intelligence, and particularly relates to a multiple myeloma high-risk screening model established by utilizing artificial intelligence based on clinical conventional assay results and application of the multiple myeloma high-risk screening model, and the model can be used for screening high-risk myeloma. According to conventional test results of blood routine tests, liver and kidney functions, ions, immunoglobulin and the like of 1741 clinical patients with multiple myeloma (MM) and 2446 clinical patients with non-myeloma (infectious diseases, rheumatic immune system diseases, liver diseases and kidney diseases), an artificial intelligence method is utilized to predict the possibility of myeloma, and the accuracy can reach 90% or above. The method has wide application prospect. The multiple myeloma early warning model has the advantages of being easy to popularize and convenient to use, cognition of primary hospitals to myeloma and early screening of patients are greatly improved, and the multiple myeloma early warning model has profound clinical significance.

Description

technical field [0001] The invention belongs to the technical field of early high-risk screening of tumors and artificial intelligence, and relates to the establishment and application of a multiple myeloma early warning model, in particular to the establishment of a multiple myeloma high-risk screening model based on clinical routine test results using artificial intelligence Method and its application, the model can be used to screen high-risk myeloma. Background technique [0002] Multiple myeloma (MM) is a hematological malignancy, accounting for 1% of all cancers and 13% of hematological malignancies, characterized by malignant plasma cell proliferation in the bone marrow, clinical manifestations of anemia, renal insufficiency, Hypercalcemia and osteolytic lesions. Because myeloma involves multiple disciplines such as orthopedics, nephrology, and hematology, it is often missed and misdiagnosed. In addition, due to the lack of medical resources and the low level of dia...

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): G16B40/00G16B30/00G16B50/30G16H50/30
CPCG16B40/00G16B30/00G16B50/30G16H50/30Y02A90/10
Inventor 王慧涵陈剑何涛燕玮石花
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
Eureka Blog
Learn More
PatSnap group products