Asthma diagnosis system based on decision tree and improved SMOTE algorithm

Abstract

The invention belongs to the field of data mining, and particularly relates to an asthma diagnosis system based on a decision tree and an improved SMOTE algorithm. According to the method, blood routine data and blood routine examination data of an asthma patient are utilized, the sampling rate of an SMOTE oversampling technology is optimized by adopting a particle swarm optimization algorithm, an improved SMOTE oversampling technology is obtained, and modeling diagnosis is performed on the data by utilizing a decision tree. Whether the patient suffers from the asthma or not can be automatically diagnosed according to the blood routine examination data of the patient, the influence caused by fatigue of a doctor, misjudgment or insufficient experience is reduced, and meanwhile the efficiency of diagnosing the asthma is improved.

Description

technical field [0001] The invention relates to the field of data mining, in particular to an asthma diagnosis system based on a decision tree and an improved SMOTE algorithm. Background technique [0002] Bronchial asthma (asthma for short) is a chronic inflammatory disease of the airway that involves a variety of cells (such as eosinophils, mast cells, T lymphocytes, neutrophils, airway epithelial cells, etc.) and cell components. Asthma belongs to the chronic strain inflammatory response of the airway. The clinical manifestations of patients with acute exacerbation are repeated wheezing, dyspnea, chest tightness and cough, and decreased exercise tolerance accompanied by airway hyperresponsiveness and obstruction. Asthma is a chronic respiratory disease that seriously endangers human health. It has a high incidence and cannot be cured. Seriously affected the normal work and life of patients. Many patients do not receive timely treatment or the treatment method is wrong, ...

AI Technical Summary

Problems solved by technology

Commonly used methods to assess the condition of asthma, such as sputum smear observation of eosinophils, lung function (SPIR) and impulse oscillation measurement (IOS), are difficult to detect, time-consuming, laborious, and expensive

The above detection methods require a large number of practitioners with professional knowledge and diagnostic experience, but the number of patients is large and the number of practitioners is relatively small

This will bring great fatigue to medical staff, and even easily lead to misdiagnosis and misdiagnosis.

And because of the lack of unified clinical indicators, different doctors will give different diagnostic results, which has great limitations and dangers.

Some patients often have paroxysmal cough as the only symptom, which is often misdiagnosed as bronchitis clinically. Some adolescent patients have chest tightness and shortness of breath during exercise as the only clinical manifestation. Correct, it is easy to lead to misdiagnosis or missed diagnosis

Images