人工智能作为一种可以辅助甚至是替代人类某些功能的新型技术,其在疾病诊断、治疗和管理中的应用,对于提高疾病诊断的准确率、实现个体化治疗和管理均有很大作用。支气管哮喘是最常见的气道慢性炎症性疾病之一,其诊断、治疗和管理与监测方面一直备受关注。人工智能可通过表示学习、机器学习、深度学习和自然语言处理等技术收集并分析大量的文字、图像和听觉数据,建立复杂、非线性的关系,以此构建模型,来协助医生对支气管哮喘进行识别、治疗和管理。本文主要从支气管哮喘的诊断分型、治疗和管理与监测角度论述了人工智能在儿童支气管哮喘中的应用及研究进展,并简要分析各种智能辅助方法的优势和局限性。
Abstract
Artificial intelligence (AI), as an emerging technology capable of augmenting or even replacing certain human functions, has significant potential in enhancing the accuracy of disease diagnosis, enabling personalized treatment, and improving disease management. Bronchial asthma, one of the most prevalent chronic inflammatory airway diseases, has long been a focus in terms of its diagnosis, treatment, and management. AI can utilize techniques such as representation learning, machine learning, deep learning, and natural language processing to collect and analyze vast amounts of textual, visual, and auditory data. By establishing complex, non-linear relationships, AI can construct models to assist physicians in the identification, treatment, and management of bronchial asthma. This paper primarily discusses the application and research progress of AI in pediatric bronchial asthma from the perspectives of diagnostic classification, treatment, and management and monitoring. Additionally, it briefly analyzes the advantages and limitations of various intelligent assistance methods.
关键词
支气管哮喘 /
人工智能 /
诊断 /
管理
Key words
bronchial asthma /
artificial intelligence /
diagnosis /
management
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Vianello A, Caminati M, Andretta M, et al. Prevalence of severe asthma according to the drug regulatory agency perspective: An Italian experience[J]. World Allergy Organ J, 2019,12(4):100032.
[2] Reddel HK, Bacharier LB, Bateman ED, et al. Global initiative for asthma strategy 2021: Executive summary and rationale for key changes[J]. Eur Respir J, 2021,59(1):2102730.
[3] Huang K, Yang T, Xu J, et al. Prevalence, risk factors, and management of asthma in China: A national cross-sectional study[J]. Lancet, 2019,394(10196):407-418.
[4] Shaw D, Green R, Berry M, et al. A cross-sectional study of patterns of airway dysfunction, symptoms and morbidity in primary care asthma[J]. Prim Care Respir J, 2012,21(3):283-287.
[5] 刘传合, 陈育志. 儿童哮喘流行病学及防治现状分析[J]. 中国实用儿科杂志, 2013,28(11):809-811.
Liu CH, Chen YZ.Analysis of the epidemiology, prevention and treatment of childhood asthma[J]. Chin J Pract Pediatr, 2013,28(11):809-811.(in Chinese)
[6] 全国儿科哮喘协作组, 中国疾病预防控制中心环境与健康相关产品安全所. 第三次中国城市儿童哮喘流行病学调查[J]. 中华儿科杂志, 2013,51(10):729-735.
The National Cooperative Group on Childhood Asthma, Institute of Environmental Health and Related Product Safety, Chinese Center for Disease Control and Prevention. Third nationwide survey of childhood asthma in urban areas of China[J]. Chin J Pediatr, 2013,51(10):729-735.(in Chinese)
[7] Shim J, Kim B, Kim S, et al. A smartphone-based application for cough counting in patients with acute asthma exacerbation[J]. J Thorac Dis,2023,15(7):4053-4065.
[8] Porter P, Abeyratne U, Swarnkar V, et al. A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children[J]. Respir Res, 2019,20(1):81.
[9] Balamurali BT, Hee HI, Kapoor S, et al. Deep neural network-based respiratory pathology classification using cough sounds[J]. Sensors (Basel), 2021,21(16):5555.
[10] Wu C, Sleiman J, Fakhry B, et al. Novel machine learning identifies 5 asthma phenotypes using cluster analysis of real-world data[J]. J Allergy Clin Immunol Pract, 2024,12(8):2084-2091.
[11] Hafke-Dys H, Kuźnar-Kamińska B, Grzywalski T, et al. Artificial intelligence approach to the monitoring of respiratory sounds in asthmatic patients[J]. Front Physiol, 2021,12:745635.
[12] Rietveld S, Oud M, Dooijes EH. Classification of asthmatic breath sounds: Preliminary results of the classifying capacity of human examiners versus artificial neural networks[J]. Comput Biomed Res,1999,32(5):440-448.
[13] Enseki M, Nukaga M, Tabata H, et al. A clinical method for detecting bronchial reversibility using a breath sound spectrum analysis in infants[J]. Respir Investig, 2017,55(3):219-228.
[14] Ruchonnet-Métrailler I, Siebert JN, Hartley M, et al. Automated interpretation of lung sounds by deep learning in children with asthma: Scoping review and strengths, weaknesses, opportunities, and threats analysis[J]. J Med Internet Res, 2024,26:e53662.
[15] Zhang K, Li Z, Zhang J, et al. Biodegradable smart face masks for machine learning-assisted chronic respiratory disease diagnosis[J]. ACS sensors, 2022,7(10):3135-3143.
[16] Das N, Happaerts S, Gyselinck I, et al. Collaboration between explainable artificial intelligence and pulmonologists improves the accuracy of pulmonary function test interpretation[J]. Eur Respir J, 2023,61(5):2201720.
[17] 傅唯佳, 汤梁峰, 叶成杰, 等. 运用人工智能技术进行肺功能数据库构建并辅助诊断实践[J]. 中国医疗器械信息, 2022,28(14):147-150.
Fu WJ, Tang LF, Ye CJ, et al. Implementation of an artificial intelligence based clinical decision support system on historical pulmonary function reports[J]. China Med Device Inf, 2022,28(14):147-150.(in Chinese)
[18] Pertzov B, Ronen M, Rosengarten D, et al. Use of capnography for prediction of obstruction severity in non-intubated COPD and asthma patients[J]. Respir Res, 2021,22(1):154.
[19] Yu G, Li Z, Li S, et al. The role of artificial intelligence in identifying asthma in pediatric inpatient setting[J]. Ann Transl Med, 2020,8(21):1367.
[20] Ross MK, Yoon J, van der Schaar A, et al. Discovering pediatric asthma phenotypes on the basis of response to controller medication using machine learning[J]. Ann Am Thorac Soc, 2018,15(1):49-58.
[21] Wu W, Bang S, Bleecker ER, et al. Multiview cluster analysis identifies variable corticosteroid response phenotypes in severe asthma[J]. Am J Respir Crit Care Med, 2019, 199(11):1358-1367.
[22] Yao H, Wang L, Zhou X, et al. Predicting the therapeutic efficacy of AIT for asthma using clinical characteristics, serum allergen detection metrics, and machine learning techniques[J]. Comput Biol Med, 2023,166:107544.
[23] Inselman JW, Jeffery MM, Maddux JT, et al. A prediction model for asthma exacerbations after stopping asthma biologics[J]. Ann Allergy Asthma Immunol, 2023,130(3):305-311.
[24] Khasha R, Sepehri MM, Mahdaviani SA. An ensemble learning method for asthma control level detection with leveraging medical knowledge-based classifier and supervised learning[J]. J Med Syst, 2020,43(6):158.
[25] Jiao T, Schnitzer ME, Forget A, et al. Identifying asthma patients at high risk of exacerbation in a routine visit: A machine learning model[J]. Respir Med, 2022,198:106866.
[26] Emeryk A, Derom E, Janeczek K, et al. Home monitoring of asthma exacerbations in children and adults with use of an AI-aided stethoscope[J]. Ann Fam Med,2023,21(6):517-525.
[27] de Hond AAH, Kant IMJ, Honkoop PJ, et al. Machine learning did not beat logistic regression in time series prediction for severe asthma exacerbations[J]. Sci Rep, 2022,12(1):20363.
[28] Lopez K, Li H, Lipkin-Moore Z, et al. Deep learning prediction of hospital readmissions for asthma and COPD[J]. Respir Res, 2023,24(1):311.
[29] Hu Y, Chen Y, Liu S, et al. Residential greenspace and childhood asthma: An intra-city study[J]. Sci Total Environ, 2023,857(Pt 3):159792.
[30] Hwang H, Jang J, Lee E, et al. Prediction of the number of asthma patients using environmental factors based on deep learning algorithms[J]. Respir Res, 2023,24(1):302.
[31] Li Y, Hsu HL, Chun Y, et al. Machine learning-driven identification of early-life air toxic combinations associated with childhood asthma outcomes[J]. J Clin Invest, 2021,131(22):e152088.
[32] Yu H, Zhou Y, Wang R, et al. Associations between trees and grass presence with childhood asthma prevalence using deep learning image segmentation and a novel green view index[J]. Environ Pollut, 2021,286:117582.
基金
陕西省技术创新引导专项(S2022-YD-QFY-0063);西安市科技局医学研究一般项目(24YXYJ0145)
PDF(501 KB)
