诊断学理论与实践 ›› 2026, Vol. 25 ›› Issue (04): 413-418.doi: 10.16150/j.1671-2870.2026.04.004
收稿日期:2026-05-25
修回日期:2026-06-16
接受日期:2026-07-08
出版日期:2026-08-25
发布日期:2026-08-31
通讯作者:
李庆云 E-mail:liqingyun68@hotmai.com基金资助:
SUN Xianwen1,2,3, LI Qingyun1,2,3(
)
Received:2026-05-25
Revised:2026-06-16
Accepted:2026-07-08
Published:2026-08-25
Online:2026-08-31
摘要:
2026版慢性阻塞性肺疾病全球倡议(Global Initiative for Chronic Obstructive Lung Disease,GOLD)首次将人工智能(artificial intelligence,AI)技术整合进慢性阻塞性肺疾病(chronic obstructive pulmonary disease,COPD)的全程管理框架。AI模型涵盖传统机器学习、深度学习、基础大模型及生成式AI四大类。AI在表型分型、急性加重预警、治疗反应预测等方面展现潜力。通过无监督学习,AI可识别出多种肺气肿影像学分型,不同分型与死亡风险、住院风险等显著相关;深度学习模型在长期和短期急性加重预测中优于传统工具,预警系统可有效降低住院率;机器学习模型在吸入激素有效性预测、肺康复依从性提升及肺减容术成功率预测中表现良好。同时,AI应用面临误诊、算法偏倚、数据隐私及责任归属等伦理挑战,需通过全流程验证、动态知情同意及公平性评估等策略应对。总体而言,AI赋能COPD管理推动从被动治疗向主动预防的范式转变,但仍需在创新、证据与伦理间寻求平衡。
中图分类号:
孙娴雯, 李庆云. 人工智能在慢性阻塞性肺疾病全程管理中的应用——GOLD 2026解读[J]. 诊断学理论与实践, 2026, 25(04): 413-418.
SUN Xianwen, LI Qingyun. Application of artificial intelligence in comprehensive management of chronic obstructive pulmonary disease:interpretation of GOLD 2026[J]. Journal of Diagnostics Concepts & Practice, 2026, 25(04): 413-418.
表1
AI模型的主要类型和应用场景
| 模型类型 | 模型名称 | 代表类型 | COPD应用 |
|---|---|---|---|
| 传统 | 监督学习 | XGBoost、随机森林、逻辑回归 | COPD患病风险预测、患者分型、急性加重预警[ |
| 机器 | 无监督学习 | 聚类、主成分分析、降维算法 | 识别COPD分子亚型、气流受限表型分组、微生物组分层[ |
| 学习 | 强化学习 | 标准强化学习框架 | 动态调整COPD患者给药方案、个性化康复策略优化[ |
| 深度学习 (深度神经网络) | 判别式深度网络 | 卷积神经网络 | CT肺气肿、气腔潴留自动量化,匹配GOLD分级[ |
| 深度生存网络 | 结合多组学预测COPD合并心血管疾病远期风险[ | ||
| 基础大模型 | 大语言模型 | 自然语言处理 | 提取病历文本、出院小结、临床诊疗建议、患者健康教育[ |
| 多模态基础模型 | CT影像+电子病历文本融合 | COPD急性加重风险预测、影像-临床联合预后评估[ | |
| 生成式AI | 生成深度网络 | 生成式对抗网络、扩散模型、生成式大语言模型 | CT影像数据增强、自动生成放射报告,弥补临床数据稀缺[ |
| [1] | The Global Initiative for Chronic Obstructive Lung Disea-se. Global strategy for prevention, diagnosis and management of COPD: 2026 report[R/OL]. 2026. [2026-06-16]. https://goldcopd.org/2026-gold-report-and-pocket-guide/. |
| [2] |
Peng J, Chen C, Zhou M, et al. A machine-learning approach to forecast aggravation risk in patients with acute exacerbation of chronic obstructive pulmonary disease with clinical indicators[J]. Sci Rep, 2020, 10:3118.
doi: 10.1038/s41598-020-60042-1 pmid: 32080330 |
| [3] |
Hussain A, Choi H E, Kim H J, et al. Forecast the exacerbation in patients of chronic obstructive pulmonary disea-se with clinical indicators using machine learning techniques[J]. Diagnostics, 2021, 11(5):829.
doi: 10.3390/diagnostics11050829 URL |
| [4] |
Zafari H, Langlois S, Zulkernine F, et al. AI in predicting COPD in the Canadian population[J]. Biosystems, 2022, 211:104585.
doi: 10.1016/j.biosystems.2021.104585 URL |
| [5] | Nikolaou V, Massaro S, Garn W, et al. Fast decliner phenotype of chronic obstructive pulmonary disease (COPD): Applying machine learning for predicting lung function loss[J]. BMJ Open Respir Res, 2021, 8(1):e000980. |
| [6] |
Madapoosi S S, Cruickshank-Quinn C, Opron K, et al. Lung microbiota and metabolites collectively associate with clinical outcomes in milder stage chronic obstructive pulmonary disease[J]. Am J Respir Crit Care Med, 2022, 206(4):427-439.
doi: 10.1164/rccm.202110-2241OC URL |
| [7] |
Pépin J L, Degano B, Tamisier R, et al. Remote monito-ring for prediction and management of acute exacerbations in chronic obstructive pulmonary disease (AECOPD)[J]. Life, 2022, 12(4):499.
doi: 10.3390/life12040499 URL |
| [8] | Hasenstab K A, Yuan N, Retson T, et al. Automated CT staging of chronic obstructive pulmonary disease severity for predicting disease progression and mortality with a deep learning convolutional neural network[J]. Radiol Cardiothorac Imag, 2021, 3(2):e200477. |
| [9] | Barbieri S, Mehta S, Wu B, et al. Predicting cardiovascular risk from national administrative databases using a combined survival analysis and deep learning approach[J]. Int J Epidemiol, 2022, 51(3):931-944. |
| [10] |
Yu P, Xu H, Hu X, et al. Leveraging generative AI and large language models: A comprehensive roadmap for healthcare integration[J]. Healthcare, 2023, 11(20):2776.
doi: 10.3390/healthcare11202776 URL |
| [11] |
Currie G M, Rohren E M. The nuclear nephrology artificial intelligence ecosystem[J]. Semin Nucl Med, 2026, 56(2):313-328.
doi: 10.1053/j.semnuclmed.2025.11.002 URL |
| [12] |
Kim K, Hong G S, Kim N. Primer on generative artificial intelligence and large language models in medical ima-ging[J]. J Korean Soc Radiol, 2024, 85(5):848.
doi: 10.3348/jksr.2024.0066 URL |
| [13] |
Yuksekgonul M, Bianchi F, Boen J, et al. Optimizing gene-rative AI by backpropagating language model feedback[J]. Nature, 2025, 639(8055):609-616.
doi: 10.1038/s41586-025-08661-4 |
| [14] |
Fortis S, Georgopoulos D, Tzanakis N, et al. Chronic obstructive pulmonary disease (COPD) and COPD-like phenotypes[J]. Front Med, 2024, 11:1375457.
doi: 10.3389/fmed.2024.1375457 URL |
| [15] |
Maniscalco M, Fuschillo S, Candia C, et al. The role of metabolomics in chronic obstructive pulmonary disease: From analytic techniques to clinical applications[J]. J Breath Res, 2026, 20(1):015001.
doi: 10.1088/1752-7163/ae2f95 |
| [16] |
Angelini E D, Yang J, Balte P P, et al. Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans[J]. Thorax, 2023, 78(11):1067-1079.
doi: 10.1136/thorax-2022-219158 pmid: 37268414 |
| [17] |
Burkes R M, Zafar M A, Panos R J. The role of chest computed tomography in the evaluation and management of chronic obstructive pulmonary disease[J]. Curr Opin Pulm Med, 2024, 30(2):129-135.
doi: 10.1097/MCP.0000000000001046 pmid: 38227648 |
| [18] |
Schwalk A J, Patel N M, Madisi N Y. Developing interventions for chronic obstructive pulmonary disease[J]. Semin Respir Crit Care Med, 2024, 45(5):582-592.
doi: 10.1055/s-0044-1787875 pmid: 38968963 |
| [19] |
Mei S, Li X, Zhou Y, et al. Deep learning for detecting and early predicting chronic obstructive pulmonary di-sease from spirogram time series[J]. npj Syst Biol Appl, 2025, 11:18.
doi: 10.1038/s41540-025-00489-y |
| [20] |
Montenegro M, Gielen J, Wang C, et al. AI and Internet of Things for chronic obstructive pulmonary disease remote monitoring: Systematic review of exacerbation prediction and key physiological variables[J]. JMIR Med Inform, 2026, 14:e84814.
doi: 10.2196/84814 URL |
| [21] |
Zhou J, Huang J, Wang Q, et al. A cough sound-based deep learning algorithm for accessible prompt detection of chronic obstructive pulmonary disease with smartphones[J]. npj Prim Care Respir Med, 2026, 36:32.
doi: 10.1038/s41533-026-00486-6 |
| [22] | Zhu B, Chen Y, Hu H. Intelligent diagnosis and treatment model based on clinical data for home rehabilitation ma-nagement of chronic obstructive pulmonary disease[J]. JoVE, 2025(224). |
| [23] |
Wu C T, Li G H, Huang C T, et al. Acute exacerbation of a chronic obstructive pulmonary disease prediction system using wearable device data, machine learning, and deep learning: Development and cohort study[J]. JMIR Mhealth Uhealth, 2021, 9(5):e22591.
doi: 10.2196/22591 URL |
| [24] | Abu-Qbeitah S, Ahmad M. Artificial intelligence and big data applications in chronic disease management: Clinical outcomes, challenges, and future directions[J]. Med Glasnik, 2026, 23(1):1-7. |
| [25] | Panettieri R, Roy J, Gontarczyk Uczkowski N, et al. Leveraging machine learning and real-world data to predict chronic obstructive pulmonary disease exacerbations[J]. Int J Chronic Obstr Pulm Dis, 2025, 20:3451-3459. |
| [26] | Chen S, Xing S, Zhang G, et al. Innovative applications and challenges of artificial intelligence in the whole-course management of chronic obstructive pulmonary di-sease[J]. Int J Chronic Obstr Pulm Dis, 2026, 21:1-18. |
| [27] |
Xue F. Intelligent diagnosis and treatment model based on clinical data for home rehabilitation of chronic obstructive pulmonary disease[J]. Am J Transl Res, 2025, 17(10):8087-8096.
doi: 10.62347/EAOX7984 URL |
| [28] |
Wu S C, Wu C Y, Chien J Y, et al. Predicting response to inhaled corticosteroid maintenance therapy in patients with chronic obstructive pulmonary disease using machine learning models[J]. Respir Med, 2025, 248:108378.
doi: 10.1016/j.rmed.2025.108378 URL |
| [29] |
Wang M, Li L, Feng M, et al. Advances in artificial intelligence applications for the management of chronic obstructive pulmonary disease[J]. Front Med, 2025, 12:1685254.
doi: 10.3389/fmed.2025.1685254 URL |
| [30] |
付琴, 张秀敏, 侯铭, 等. 智能化体感运动在老年慢性阻塞性肺疾病患者居家肺康复中的效果评价[J]. 中华护理杂志, 2025, 60(5):517-524.
doi: 10.3761/j.issn.0254-1769.2025.05.001 |
|
Fu Qin, Zhang Xiumin, Hou Ming, et al. Effect of somatosensory exercise based on artificial intelligence techno-logy in home pulmonary rehabilitation of elderly patients with COPD[J]. Chin J Nurs, 2025, 60(5):517-524.
doi: 10.3761/j.issn.0254-1769.2025.05.001 |
|
| [31] | Tada D K, Kim G H, Goldin J G, et al. Using a fully automated, quantitative fissure integrity score extracted from chest CT scans of emphysema patients to predict endobronchial valve response[J]. J Med Imag, 2025, 12(2):024501. |
| [32] |
Yang H, Wu Y, Wu T, et al. Accuracy of deep learning in diagnosing chronic obstructive pulmonary disease: Systematic review and meta-analysis[J]. J Med Internet Res, 2026, 28:e83459.
doi: 10.2196/83459 URL |
| [33] | Smith L A, Oakden-Rayner L, Bird A, et al. Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: A systematic review and meta-analysis[J]. Lancet Digit Health, 2023, 5(12):e872-e881. |
| [34] |
Boyce L, Prybutok V. Artificial intelligence for early detection and prediction of chronic obstructive pulmonary disease exacerbations[J]. Healthcare, 2026, 14(6):806.
doi: 10.3390/healthcare14060806 URL |
| [35] | Zhou C Y, Restko M, Freije B, et al. Artificial intelligence in chronic obstructive pulmonary disease: Recent advances in imaging and physiological monitoring[J]. Curr Opin Pulm Med, 2026, 32(2):136-141. |
| [36] |
Pinheira A, Casal-Guisande M, Represas-Represas C, et al. Artificial intelligence applications in chronic obstructive pulmonary disease: A global scoping review of diagnostic, symptom-based, and outcome prediction approaches[J]. Biomedicines, 2025, 13(12):3053.
doi: 10.3390/biomedicines13123053 URL |
| [37] |
Chen Z, Hao J, Sun H, et al. Applications of digital health technologies and artificial intelligence algorithms in COPD: Systematic review[J]. BMC Med Inform Decis Mak, 2025, 25(1):77.
doi: 10.1186/s12911-025-02870-7 |
| [38] |
Wu Y, Xia S, Liang Z, et al. Artificial intelligence in COPD CT images: Identification, staging, and quantitation[J]. Respir Res, 2024, 25(1):319.
doi: 10.1186/s12931-024-02913-z |
| [39] | Pant S, Yang H J, Cho S, et al. Development of a deep learning model to predict smoking status in patients with chronic obstructive pulmonary disease: A secondary analysis of cross-sectional national survey[J]. Digit Health, 2025, 11:20552076251333660. |
| [40] |
Jeon E T, Park H, Lee J K, et al. Deep learning-based chronic obstructive pulmonary disease exacerbation prediction using flow-volume and volume-time curve ima-ging: Retrospective cohort study[J]. J Med Internet Res, 2025, 27:e69785.
doi: 10.2196/69785 URL |
| [41] | 王梓晖, 梁振宇, 张佳敏, 等. 《全球慢性阻塞性肺疾病诊断、管理及预防策略(2026版)》解读:人工智能与新兴技术[J]. 国际呼吸杂志, 2026, 46(3):209-213. |
| Wang Zihui, Liang Zhenyu, Zhang Jiamin, et al. Interpretation of the Global Strategy for the Diagnosis,Management,and Prevention of Chronic Obstructive Pulmonary Disease(2026 Report):artificial intelligence and emer-ging technologies[J]. Int J Respir, 2026, 46(3):209-213. | |
| [42] |
Calzetta L, Cazzola M, Pistocchini E, et al. Exploring AI and ML in managing overlap between cardiovascular di-sease and asthma or COPD: A scoping review[J]. Respir Med, 2026, 256:108812.
doi: 10.1016/j.rmed.2026.108812 URL |
| [43] | 郭万金, 陈亚红. 基于“1+N”模式提高慢阻肺病的早期识别和综合管理[J]. 中华健康管理学杂志, 2025, 19(11):859-863. |
| Guo Wanjin, Chen Yahong. A “1+N” model for enhan-cing early detection and comprehensive management of chronic obstructive pulmonary disease[J]. Chin J Health Manage, 2025, 19(11):859-863. | |
| [44] | 中华医学会呼吸病学分会, 中国医师协会呼吸医师分会. 中国慢性阻塞性肺疾病诊治指南(2026年修订版)计划书[J]. 中华结核和呼吸杂志, 2026, 49(7):717-712. |
| Chinese Thoracic Society, Chinese Association of Chest Physicians. Chinese practice guideline for the diagnosis and treatment of chronic obstructive pulmonary disease (2026 revision): protocol[J]. Chin J Tuberc Respir Dis, 2026, 49(7):717-712. |
| [1] | 时国朝, 倪颖梦. 呼吸系统共病诊治原则:以慢性阻塞性肺疾病共病为例[J]. 诊断学理论与实践, 2026, 25(04): 406-412. |
| [2] | 张婷婷, 黄慧, 孙宏莉. 非结核分枝杆菌实验室诊断的现状和研究进展[J]. 诊断学理论与实践, 2026, 25(03): 249-259. |
| [3] | 卢仁泉, 胡玲. 多组学技术与人工智能融合时代新型肿瘤标志物在肿瘤诊治中的研究进展[J]. 诊断学理论与实践, 2026, 25(03): 278-286. |
| [4] | 高丽, 赵楠, 陈莺, 李爽, 姚小英, 潘元美, 支楠, 王刚. 人工智能在神经内科住院医师规范化培训中的应用现状及挑战[J]. 诊断学理论与实践, 2026, 25(02): 239-244. |
| [5] | 王琰, 范磊. 人工智能在血液疾病形态学诊断中的应用进展[J]. 诊断学理论与实践, 2026, 25(01): 15-20. |
| [6] | 刘淦, 戴媛媛, 常文娇, 马筱玲. 脓毒症筛查技术进展[J]. 诊断学理论与实践, 2025, 24(06): 567-575. |
| [7] | 戴敏, 蒋裕雄, 史玉玲. 2023年至2024年银屑病诊治进展[J]. 诊断学理论与实践, 2025, 24(06): 593-604. |
| [8] | 杨蕊馨, 于颖彦. 人工智能在消化道肿瘤医学图像数据处理的应用[J]. 诊断学理论与实践, 2025, 24(06): 605-612. |
| [9] | 余梦思, 宁聪华, 孟存仁, 帕丽扎提.阿不都热依木, 钟笛, 时瑛, 薛黎. 人工智能阅片平台在医学检验专业实习生血细胞形态教学中的应用研究[J]. 诊断学理论与实践, 2025, 24(06): 668-672. |
| [10] | 洪烨娜, 张宇, SHI Kuangyu, 李彪, 郭睿. 放射性核素诊疗一体化的若干问题及对策[J]. 诊断学理论与实践, 2025, 24(03): 263-267. |
| [11] | 徐梦迪, 高峰, 朱剑, 陈蕾, 秦雨萌, 黄越, 唐银萍, 沙杰. 新型海绵胶囊联合人工智能细胞DNA检测在早期食管癌筛查中的价值[J]. 诊断学理论与实践, 2024, 23(06): 580-586. |
| [12] | 李卓含, 黄新韵, 郭睿, 李彪. 18F-FDG PET/CT在滤泡性淋巴瘤诊断和预后评估中的研究进展[J]. 诊断学理论与实践, 2024, 23(04): 439-444. |
| [13] | 常青, 陈宇清, 袁越阳, 张海, 李锋, 李兴旺. 压力控制通气时不同呼吸力学特性对吸气流量指数的影响[J]. 诊断学理论与实践, 2023, 22(05): 454-459. |
| [14] | 吴娜明, 李军, 陶娟. 恶性黑色素瘤的诊断热点[J]. 诊断学理论与实践, 2023, 22(03): 215-220. |
| [15] | 孙娴雯, 李庆云. 关注保留比率的肺功能减损(PRISm)的慢性阻塞性肺疾病表型[J]. 诊断学理论与实践, 2023, 22(03): 234-237. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||