{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T22:53:42Z","timestamp":1791759222694,"version":"4.3.4"},"reference-count":35,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T00:00:00Z","timestamp":1644192000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007632","name":"Changhua Christian Hospital","doi-asserted-by":"publisher","award":["109-CC-IRP-032."],"award-info":[{"award-number":["109-CC-IRP-032."]}],"id":[{"id":"10.13039\/501100007632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JPM"],"abstract":"<jats:p>Background: The study developed accurate explainable machine learning (ML) models for predicting first-time acute exacerbation of chronic obstructive pulmonary disease (COPD, AECOPD) at an individual level. Methods: We conducted a retrospective case\u2013control study. A total of 606 patients with COPD were screened for eligibility using registry data from the COPD Pay-for-Performance Program (COPD P4P program) database at Changhua Christian Hospital between January 2017 and December 2019. Recursive feature elimination technology was used to select the optimal subset of features for predicting the occurrence of AECOPD. We developed four ML models to predict first-time AECOPD, and the highest-performing model was applied. Finally, an explainable approach based on ML and the SHapley Additive exPlanations (SHAP) and a local explanation method were used to evaluate the risk of AECOPD and to generate individual explanations of the model\u2019s decisions. Results: The gradient boosting machine (GBM) and support vector machine (SVM) models exhibited superior discrimination ability (area under curve [AUC] = 0.833 [95% confidence interval (CI) 0.745\u20130.921] and AUC = 0.836 [95% CI 0.757\u20130.915], respectively). The decision curve analysis indicated that the GBM model exhibited a higher net benefit in distinguishing patients at high risk for AECOPD when the threshold probability was &lt;0.55. The COPD Assessment Test (CAT) and the symptom of wheezing were the two most important features and exhibited the highest SHAP values, followed by monocyte count and white blood cell (WBC) count, coughing, red blood cell (RBC) count, breathing rate, oral long-acting bronchodilator use, chronic pulmonary disease (CPD), systolic blood pressure (SBP), and others. Higher CAT score; monocyte, WBC, and RBC counts; BMI; diastolic blood pressure (DBP); neutrophil-to-lymphocyte ratio; and eosinophil and lymphocyte counts were associated with AECOPD. The presence of symptoms (wheezing, dyspnea, coughing), chronic disease (CPD, congestive heart failure [CHF], sleep disorders, and pneumonia), and use of COPD medications (triple-therapy long-acting bronchodilators, short-acting bronchodilators, oral long-acting bronchodilators, and antibiotics) were also positively associated with AECOPD. A high breathing rate, heart rate, or systolic blood pressure and methylxanthine use were negatively correlated with AECOPD. Conclusions: The ML model was able to accurately assess the risk of AECOPD. The ML model combined with SHAP and the local explanation method were able to provide interpretable and visual explanations of individualized risk predictions, which may assist clinical physicians in understanding the effects of key features in the model and the model\u2019s decision-making process.<\/jats:p>","DOI":"10.3390\/jpm12020228","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T20:36:42Z","timestamp":1644266202000},"page":"228","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Explainable Machine Learning Model for Predicting First-Time Acute Exacerbation in Patients with Chronic Obstructive Pulmonary Disease"],"prefix":"10.3390","volume":"12","author":[{"given":"Chew-Teng","family":"Kor","sequence":"first","affiliation":[{"name":"Big Data Center, Changhua Christian Hospital, Changhua 500, Taiwan"},{"name":"Graduate Institute of Statistics and Information Science, National Changhua University of Education, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Rong","family":"Li","sequence":"additional","affiliation":[{"name":"Thoracic Medicine Research Center, Changhua Christian Hospital, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Ru","family":"Lin","sequence":"additional","affiliation":[{"name":"Big Data Center, Changhua Christian Hospital, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng-Hao","family":"Lin","sequence":"additional","affiliation":[{"name":"Thoracic Medicine Research Center, Changhua Christian Hospital, Changhua 500, Taiwan"},{"name":"Division of Chest Medicine, Department of Internal Medicine, Changhua Christian Hospital, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing-Yen","family":"Wang","sequence":"additional","affiliation":[{"name":"Division of Thoracic Surgery, Department of Surgery, Changhua Christian Hospital, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9407-8578","authenticated-orcid":false,"given":"Ching-Hsiung","family":"Lin","sequence":"additional","affiliation":[{"name":"Division of Chest Medicine, Department of Internal Medicine, Changhua Christian Hospital, Changhua 500, Taiwan"},{"name":"Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung 402, Taiwan"},{"name":"Department of Recreation and Holistic Wellness, MingDao University, Changhua 523, Taiwan"},{"name":"Artificial Intelligence Development Center, Changhua Christian Hospital, Changhua 500, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1111\/resp.12660","article-title":"Global burden of COPD","volume":"21","author":"Tan","year":"2016","journal-title":"Respirology"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Blasi, F., Cesana, G., Conti, S., Chiodini, V., Aliberti, S., Fornari, C., and Mantovani, L.G. (2014). The Clinical and Economic Impact of Exacerbations of Chronic Obstructive Pulmonary Disease: A Cohort of Hospitalized Patients. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0101228"},{"key":"ref_3","unstructured":"(2021, February 02). Global Initiative for Chronic Obstructive Lung Disease. Global Strategy for The Diagnosis, Management, and Prevention of Chronic Obstructive Pulmonary Disease (2021 Report). Available online: https:\/\/goldcopd.org\/wp-content\/uploads\/2020\/11\/GOLD-REPORT-2021-v1.1-25Nov20_WMV.pdf."},{"key":"ref_4","first-page":"166","article-title":"Prevention of Exacerbations in Chronic Obstructive Pulmonary Disease: Knowns and Unknowns","volume":"1","author":"Calverley","year":"2014","journal-title":"Chronic Obstr. Pulm. Dis."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1513\/AnnalsATS.202006-704ED","article-title":"Using Health Administrative Data to Predict Chronic Obstructive Pulmonary Disease Exacerbations","volume":"17","author":"Jiang","year":"2020","journal-title":"Ann. Am. Thorac. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.2147\/COPD.S139470","article-title":"Impact and prevention of severe exacerbations of COPD: A review of the evidence","volume":"12","author":"Halpin","year":"2017","journal-title":"Int. J. Chronic Obstr. Pulm. Dis."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1016\/j.rmed.2009.04.001","article-title":"Characteristics of patients admitted for the first time for COPD exacerbation","volume":"103","author":"Balcells","year":"2009","journal-title":"Respir. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s00408-011-9301-8","article-title":"Risk of Nonlower Respiratory Serious Adverse Events Following COPD Exacerbations in the 4-year UPLIFT\u00ae Trial","volume":"189","author":"Halpin","year":"2011","journal-title":"Lung"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1016\/S2213-2600(20)30049-7","article-title":"COPD exacerbations: Finally, a more than acceptable risk score","volume":"8","author":"Bhatt","year":"2020","journal-title":"Lancet Respir. Med."},{"key":"ref_10","first-page":"1","article-title":"A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators","volume":"10","author":"Peng","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1513\/AnnalsATS.202001-070OC","article-title":"Predicting Severe Chronic Obstructive Pulmonary Disease Exacerbations. Developing a Population Surveillance Approach with Administrative Data","volume":"17","author":"Tavakoli","year":"2020","journal-title":"Ann. Am. Thorac. Soc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"The Lancet Respiratory Medicine (2018). Opening the black box of machine learning. Lancet Respir. Med., 6, 801.","DOI":"10.1016\/S2213-2600(18)30425-9"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1038\/s41591-021-01461-z","article-title":"AI in medicine must be explainable","volume":"27","author":"Kundu","year":"2021","journal-title":"Nat. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1001\/jama.2017.7797","article-title":"Unintended Consequences of Machine Learning in Medicine","volume":"318","author":"Cabitza","year":"2017","journal-title":"JAMA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2869","DOI":"10.2147\/COPD.S329454","article-title":"Effectiveness of Nationwide COPD Pay-for-Performance Program on COPD Exacerbations in Taiwan","volume":"16","author":"Cheng","year":"2021","journal-title":"Int. J. Chronic Obstr. Pulm. Dis."},{"key":"ref_16","first-page":"1","article-title":"Factors associated with chronic obstructive pulmonary disease exacerbation, based on big data analysis","volume":"9","author":"Lee","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.jclinepi.2016.02.031","article-title":"Adequate sample size for developing prediction models is not simply related to events per variable","volume":"76","author":"Ogundimu","year":"2016","journal-title":"J. Clin. Epidemiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2002122","DOI":"10.1183\/13993003.02122-2020","article-title":"Should the number of acute exacerbations in the previous year be used to guide treatments in COPD?","volume":"57","author":"Sadatsafavi","year":"2021","journal-title":"Eur. Respir. J."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hussain, A., Choi, H.-E., Kim, H.-J., Aich, S., Saqlain, M., and Kim, H.-C. (2021). Forecast the Exacerbation in Patients of Chronic Obstructive Pulmonary Disease with Clinical Indicators Using Machine Learning Techniques. Diagnostics, 11.","DOI":"10.3390\/diagnostics11050829"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"Bzdok","year":"2018","journal-title":"Nat. Methods"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105267","DOI":"10.1016\/j.cmpb.2019.105267","article-title":"Comparison of machine learning algorithms for the identification of acute exacerbations in chronic obstructive pulmonary disease","volume":"188","author":"Wang","year":"2019","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/1471-2350-12-90","article-title":"Genome Wide Association Study to predict severe asthma exacerbations in children using random forests classifiers","volume":"12","author":"Xu","year":"2011","journal-title":"BMC Med. Genet."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1136\/thoraxjnl-2014-205507","article-title":"The path to personalised medicine in COPD","volume":"69","author":"Agusti","year":"2014","journal-title":"Thorax"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1136\/thoraxjnl-2012-202772","article-title":"The COPD control panel: Towards personalised medicine in COPD","volume":"68","author":"Agusti","year":"2012","journal-title":"Thorax"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1164\/rccm.201410-1935PP","article-title":"Personalized Respiratory Medicine: Exploring the Horizon, Addressing the Issues. Summary of a BRN-AJRCCM Workshop Held in Barcelona on June 12, 2014","volume":"191","author":"Auffray","year":"2015","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1183\/13993003.01359-2015","article-title":"Treatable traits: Toward precision medicine of chronic airway diseases","volume":"47","author":"Agusti","year":"2016","journal-title":"Eur. Respir. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12967-020-02658-5","article-title":"Precision medicine in the era of artificial intelligence: Implications in chronic disease management","volume":"18","author":"Subramanian","year":"2020","journal-title":"J. Transl. Med."},{"key":"ref_28","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Oh, T.R., Song, S.H., Choi, H.S., Suh, S.H., Kim, C.S., Jung, J.Y., Choi, K.H., Oh, K.-H., Ma, S.K., and Bae, E.H. (2021). Predictive Model for High Coronary Artery Calcium Score in Young Patients with Non-Dialysis Chronic Kidney Disease. J. Pers. Med., 11.","DOI":"10.3390\/jpm11121372"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lu, C., Song, J., Li, H., Yu, W., Hao, Y., Xu, K., and Xu, P. (2022). Predicting Venous Thrombosis in Osteoarthritis Using a Machine Learning Algorithm: A Population-Based Cohort Study. J. Pers. Med., 12.","DOI":"10.3390\/jpm12010114"},{"key":"ref_31","first-page":"1","article-title":"Expansion of a Population of Large Monocytes (Atypical Monocytes) in Peripheral Blood of Patients with Acute Exacerbations of Chronic Obstructive Pulmonary Diseases","volume":"2018","author":"Yang","year":"2018","journal-title":"Mediat. Inflamm."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.2147\/COPD.S86198","article-title":"Bronchodilators use in patients with COPD","volume":"10","author":"Hsu","year":"2015","journal-title":"Int. J. Chronic Obstr. Pulm. Dis."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.ccm.2020.05.007","article-title":"Systemic Medications in Chronic Obstructive Pulmonary Disease: Use and Outcomes","volume":"41","author":"Roche","year":"2020","journal-title":"Clin. Chest Med."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tseng, C.-M., Chen, Y.-T., Ou, S.-M., Hsiao, Y.-H., Li, S.-Y., Wang, S.-J., Yang, A.C.-C., Chen, T.-J., and Perng, D.-W. (2013). The Effect of Cold Temperature on Increased Exacerbation of Chronic Obstructive Pulmonary Disease: A Nationwide Study. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0057066"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s00484-008-0187-y","article-title":"Diurnal temperature range and emergency room admissions for chronic obstructive pulmonary disease in Taiwan","volume":"53","author":"Liang","year":"2008","journal-title":"Int. J. Biometeorol."}],"container-title":["Journal of Personalized Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4426\/12\/2\/228\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:15:36Z","timestamp":1760134536000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4426\/12\/2\/228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,7]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["jpm12020228"],"URL":"https:\/\/doi.org\/10.3390\/jpm12020228","relation":{},"ISSN":["2075-4426"],"issn-type":[{"value":"2075-4426","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,7]]}}}