基于支持向量机的平稳期儿童哮喘诊断方法研究  

An asthma diagnosis method for stable phase children based on a support vector machine

作　　者：胡朝山 刘静[2,3] 张琪[2,3] 范一强 李煜圣[1] 吕娣[2,3] 唐丽娟 HU ChaoShan;LIU Jing;ZHANG Qi;FAN YiQiang;LI YuSheng;LÜDi;TANG LiJuan(College of Mechanical&Electrical Engineering,Beijing University of Chemical Technology,Beijing 100029;Department of Pediatrics,China‐Japan Friendship Hospital,Beijing 100029;Graduate School of Peking Union Medical College,Chinese Academy of Medical Sciences,Beijing 100730,China)

机构地区：[1]北京化工大学机电工程学院,北京100029 [2]中日友好医院儿科,北京100029 [3]中国医学科学院北京协和医学院研究生院,北京100730

出　　处：《北京化工大学学报（自然科学版）》2024年第5期114-120,共7页Journal of Beijing University of Chemical Technology(Natural Science Edition)

基　　金：中日友好医院高水平临床研究项目(2022-NHLHCRF-LX-01-0301);呼气相声波频谱分析在儿童咳嗽变异性哮喘中的应用研究(XK2022-05)。

摘　　要：哮喘是一种对儿童生活质量有重大影响的慢性呼吸系统疾病,它的及时预测和准确诊断对哮喘儿童的健康至关重要。但对处于哮喘平稳期的儿童而言,哮喘发作时儿童的呼吸音中不存在明显的喘鸣音等特征音,所以在听觉上处于哮喘平稳期儿童的呼吸音与健康儿童的呼吸音无明显区别,导致医护人员难以使用传统的听诊方法诊断哮喘。选用机器学习中的支持向量机算法(SVM)对儿童进行哮喘预测,研究结果表明,SVM在哮喘与健康儿童呼吸音的分类预测中表现出色,其对吸气相的预测准确率达到96.53%,而对呼气相的预测准确率达到91.66%。由此可见,SVM在儿童哮喘诊断中具有较好可行性,提高了儿童哮喘诊断的准确性和效率,为该领域提供了可靠的诊断工具。Asthma is a chronic respiratory disease that significantly impacts children's quality of life.Timely pre-diction and accurate diagnosis are crucial to the health of children with asthma.However,children in the stable stage of asthma do not exhibit wheezing or other characteristic sounds during an asthma attack.Therefore,there is no significant difference in the breath sounds of children in the stable stage of asthma and those of healthy children,making it challenging for healthcare professionals to diagnose asthma using traditional auscultation methods.This study utilized a support vector machine(SVM)algorithm in machine learning to predict the presence of asthma in children.The results indicate that SVM performed well in classifying the breath sounds of asthmatic and healthy children.The accuracy of the SVM's prediction for the inspiratory phase was 96.53%,while for the expiratory phase it was 91.66%.This demonstrates that the SVM method is highly feasible for diagnosing childhood asthma,can improve the accuracy and efficiency of diagnosis,and can provide a reliable diagnostic tool for this field.

关 键 词：哮喘 预测 机器学习 支持向量机 

分 类 号：R725[医药卫生—儿科]