Research on Intelligent Decision of Pulmonary Tuberculosis Disease Based on Data Mining - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Research on Intelligent Decision of Pulmonary Tuberculosis Disease Based on Data Mining

(1) , (1) , (1)
1

Abstract

Aiming at the problem that the low diagnostic efficiency and low accuracy of the single data mining method for Diagnosis of pulmonary tuberculosis, In this study, the electronic records of 1203 cases of tuberculosis patients in Changping District City, Beijing City of Beijng and Beijing Institute of tuberculosis control and tuberculosis control were build, Tuberculosis disease diagnosis model is built by application of rough set and decision tree method, On the basis of this, the diagnosis system of pulmonary tuberculosis was constructed. In this study, the combining method of rough set and decision tree was approached to attribute reduction, the model reduced redundant 57 attributes and remained 22 attributes, and articled 7 the decision rules. The model accuracy is 89.46%. Compared with the non reduction method, the decision rule was reduced by 128%, and the accuracy of the model remained unchanged. The research results showed that the algorithm can reduce the time and space complexity of the algorithm while ensuring the accuracy of the model, so as to improve the efficiency of the mining, and provide some references for clinical diagnosis.
Fichier principal
Vignette du fichier
478221_1_En_43_Chapter.pdf (287.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02180005 , version 1 (12-07-2019)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Guifen Chen, Wang Ke, Ma Li. Research on Intelligent Decision of Pulmonary Tuberculosis Disease Based on Data Mining. 10th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Oct 2016, Dongying, China. pp.425-434, ⟨10.1007/978-3-030-06155-5_43⟩. ⟨hal-02180005⟩
52 View
9 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More