Prediction models for chronic obstructive pulmonary disease exacerbation: A literature review
Main Article Content
Abstract
Machine learning techniques for predicting chronic obstructive pulmonary disease (COPD) exacerbation is the revolution in COPD management by allowing early detection, personalized intervention, resource optimization, and patient empowerment. The results identified 9/928 articles that fully met the selection criteria, including: 7 multicenters retrospective observations, 1 single-center prospective observation, and 1 single-center clinical trial. 117 risk factors were included in the prediction models, of which age and gender appeared most commonly (9/9 times). The models had the area under the curve ranging from 0.681 to over 0.9. The 3 highest performance models were Random Forest (> 0.9), Support Vector Machine (0.9), and Extreme Gradient Boosting (0.86), respectively, which need to be applied, further built, and developed on the Vietnamese dataset.
Article Details
Keywords
Chronic Obstructive Pulmonary Disease Exacerbation, model, prediction, machine learning
References
2. Bộ Y tế. Quyết định 2767/QĐ-BYT ngày 4/7/2023 về việc ban hành tài liệu chuyên môn “Hướng dẫn chẩn đoán và điều trị bệnh phổi tắc nghẽn mạn tính”. In:2023.
3. Hurst J R, Skolnik N, Hansen G J, et al. Understanding the impact of chronic obstructive pulmonary disease exacerbations on patient health and quality of life. European journal of internal medicine. 2020;73:1-6.
4. Chmiel FP, Burns DK, Pickering JB, et al. Prediction of Chronic Obstructive Pulmonary Disease Exacerbation Events by Using Patient Self-reported Data in a Digital Health App: Statistical Evaluation and Machine Learning Approach. JMIR Med Inform. 2022; 10(3): e26499.
5. Fakhraei R, Matelski J, Gershon A, et al. Development of Multivariable Prediction Models for the Identification of Patients Admitted to Hospital with an Exacerbation of COPD and the Prediction of Risk of Readmission: A Retrospective Cohort Study using Electronic Medical Record Data. COPD. 2023; 20(1): 274-283.
6. Huebner ST, Henny S, Giezendanner S, et al. Prediction of Acute COPD Exacerbation in the Swiss Multicenter COPD Cohort Study (TOPDOCS) by Clinical Parameters, Medication Use, and Immunological Biomarkers. Respiration. 2022; 101(5): 441-454.
7. Singh D, Hurst J R, Martinez F J, et al. Predictive modeling of COPD exacerbation rates using baseline risk factors. Therapeutic advances in respiratory disease. 2022; 16: 17534666221107314.
8. Ställberg B, Lisspers K, Larsson K, et al. Predicting Hospitalization Due to COPD Exacerbations in Swedish Primary Care Patients Using Machine Learning - Based on the ARCTIC Study. Int J Chron Obstruct Pulmon Dis. 2021; 16: 677-688.
9. Wang C, Chen X, Du L, et al. Comparison of machine learning algorithms for the identification of acute exacerbations in chronic obstructive pulmonary disease. Comput Methods Programs Biomed. 2020; 188: 105267.
10. Wu CT, Li GH, Huang CT, 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. JMIR Mhealth Uhealth. 2021; 9(5): e22591.
11. Zeng S, Arjomandi M, Tong Y, et al. Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. J Med Internet Res. 2022; 24(1): e28953.
12. Zhang Y, Zheng S P, Hou Y F, et al. A predictive model for frequent exacerbator phenotype of acute exacerbations of chronic obstructive pulmonary disease. Journal of thoracic disease. 2023; 15(12): 6502-6514.
13. Nguyễn Thị Ngọc, Vũ Văn Sơn, Bùi Mỹ Hạnh, và cs. Đặc điểm lâm sàng, cận lâm sàng, mức độ nặng bệnh nhân đợt cấp bệnh phổi tắc nghẽn mạn tính (COPD) tại bệnh viện Phổi Trung ương. Tạp chí Y học Việt Nam. 2020; 1(495): 4-9.
14. Phùng Thị Thanh, Chu Thị Hạnh, Trần Thị Nương, và cs. Một số yếu tố nguy cơ gây đợt cấp thường xuyên ở bệnh nhân có đợt cấp bệnh phổi tắc nghẽn mạn tính nhập viện tại Trung tâm Hô hấp, Bệnh viện Bạch Mai. Tạp chí Y học Việt Nam. 2022; 1(514): 100-104.