A risk early warning method for thalassemia based on cs-rf

A risk warning and anemia technology, applied in medical data mining, instruments, biological models, etc., can solve problems that have not been applied in the field of thalassemia, so as to avoid the birth of thalassemia patients, improve accuracy and efficiency, The effect of reducing the waste of medical resources

CN109346182BActive Publication Date: 2021-06-18KUNMING UNIV OF SCI & TECH
7 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-06-18

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a risk early warning method for thalassemia based on CS‑RF, and belongs to the technical field of data mining and prediction. First, establish a database of electronic ledger data records, use the subject's blood sample number as the identifier ID, and the corresponding inspection record as a sample S; perform data preprocessing on the sample data set, and obtain the data set DataSet applicable to the algorithm. The data set contains N samples and M features, and the DataSet is divided into a training set Traindata and a test set Testdata with a ratio of 3:1; then, use the cuckoo search algorithm (CS) to optimize parameters and initialize to form a random forest (RF) decision tree number ntree and segmentation attribute mtry; randomly select training samples to train the decision tree DT to form an optimized RF-CS model; vote on the classification results of each decision tree, and vote the majority as the risk assessment result; Finally, the test data testdata is used as the model input, and the early warning result is output as a reference for clinical diagnosis.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a risk early warning method for thalassemia based on CS-RF, and belongs to the technical field of data mining and prediction. Background technique

[0002] Thalassemia Disease (TD) is a marine, globin gene-deficient and recessively inherited disease that occurs mostly in the Mediterranean coast, especially in Yunnan (10%), Guangdong and other places in my country. Among them, children with severe thalassemia are in danger of dying immediately or before the age of six, which has caused a heavy blow to the families of the children.

[0003] The early warning method based on the CS-RF algorithm can assist diagnosis, help reduce misdiagnosis rate, save medical resources, etc., and further guide its subsequent diagnosis and treatment process. At present, there have been cases of bone marrow stem cell transplantation, but the post-treatment effect is not good. In addition, the research on thalassemia basically stays on the accumula...

Examples

Embodiment 1

[0058] Embodiment 1: as Figure 1-3 As shown, a CS-RF-based risk early warning method for thalassemia, the specific steps of the method are as follows:

[0059] Step1, establish a database. According to the electronic ledger data, a database of subject records is established, the subject's blood sample number is used as the identifier ID, and the corresponding test record is taken as a sample S, each sample S contains the blood of the subject with thalassemia and Electrophoresis inspection results, the corresponding column is the checked attribute value set TZset; specifically:

[0060] For the convenience of elaborating the present invention, it is assumed that some of the attribute sets in the comprehensive attributes of early warning of thalassemia in the present invention are shown in the following table:

[0061]

[0062] Step2, data preprocessing. After cleaning, mining and filling the sample data set in the database, the modeling data set DataSet is obtained. The ...