{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T00:06:46Z","timestamp":1795046806605,"version":"4.10.2"},"reference-count":40,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"unspecified","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Teva Branded Pharmaceutical Products R&D Inc","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Resp Res"],"accepted":{"date-parts":[[2025,4,1]]},"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>By using data obtained with digital inhalers, machine learning models have the potential to detect early signs of deterioration and predict impending exacerbations of chronic obstructive pulmonary disease (COPD) for individual patients. This analysis aimed to determine if a machine learning algorithm capable of predicting impending exacerbations could be developed using data from an integrated digital inhaler.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and methods<\/jats:title>\n                    <jats:p>A 12-week, open-label clinical study enrolled patients (\u226540 years old) with COPD to use ProAir Digihaler, a digital dry powder inhaler with integrated sensors, to deliver their reliever medication (albuterol, 90\u2009\u00b5g\/dose; 1\u20132 inhalations every 4\u2009hours, as needed). The Digihaler recorded inhaler use through timestamps, peak inspiratory flow (PIF), inhalation volume, inhalation duration, and time to PIF throughout the study. By applying machine learning methodology to data downloaded from the inhalers after study completion, along with clinical and demographic information, a model predictive of impending exacerbations was generated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The predictive analysis included 336 patients, 98 of whom experienced a total of 111 exacerbations. PIF and inhalation volume were observed to decline in the days preceding an exacerbation. Using gradient-boosting trees with data from the Digihaler and baseline patient characteristics, the machine learning model was able to predict an exacerbation over the following 5\u2009days with a receiver operating characteristic area under curve of 0.77 (95% CI: 0.71\u20130.83). Features of the model with the highest weight were baseline inhalation parameters and changes in inhalation parameters before an exacerbation compared with baseline.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We demonstrated the development of a proof-of-concept machine learning model predictive of impending COPD exacerbations using data from the integrated digital reliever inhaler. This approach may potentially support patient monitoring, help improve disease management, and enable pre-emptive interventions to minimise exacerbations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical trial registration number<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"clintrialgov\" xlink:href=\"NCT03256695\">NCT03256695<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjresp-2024-002577","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T16:10:13Z","timestamp":1747066213000},"page":"e002577","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":18,"title":["Predictive machine learning algorithm for COPD exacerbations using a digital inhaler with integrated sensors"],"prefix":"10.1136","volume":"12","clinical-trial-number":[{"clinical-trial-number":"nct03256695","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct03256695","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct03256695","registry":"10.18810\/clinical-trials-gov"}],"author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5962-2184","authenticated-orcid":false,"given":"Laurie D","family":"Snyder","sequence":"first","affiliation":[{"name":"Department of Medicine, Duke University School of Medicine, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"DePietro","sequence":"additional","affiliation":[{"name":"Teva Branded Pharmaceutical Products R&D Inc, Parsippany, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Reich","sequence":"additional","affiliation":[{"name":"Teva Pharmaceutical Industries Ltd, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Megan L","family":"Neely","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, North Carolina, USA"},{"name":"Duke University Medical Center, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Njira","family":"Lugogo","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roy","family":"Pleasants","sequence":"additional","affiliation":[{"name":"UNC, Chapel Hill, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Li","sequence":"additional","affiliation":[{"name":"Teva Branded Pharmaceutical Products R&D Inc, Parsippany, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lena","family":"Granovsky","sequence":"additional","affiliation":[{"name":"Teva Pharmaceutical Industries Ltd, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Randall","family":"Brown","sequence":"additional","affiliation":[{"name":"Teva Branded Pharmaceutical Products R&D Inc, Parsippany, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guilherme","family":"Safioti","sequence":"additional","affiliation":[{"name":"Teva Branded Pharmaceutical Products R&D Inc, Parsippany, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"2026010701503854000_12.1.e002577.1","unstructured":"World Health Organization . Chronic obstructive pulmonary disease (copd). 2024. Available: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/chronic-obstructive-pulmonary-disease-(copd) [Accessed 19 Dec 2024]."},{"key":"2026010701503854000_12.1.e002577.2","doi-asserted-by":"publisher","DOI":"10.1136\/thx.2003.008730"},{"key":"2026010701503854000_12.1.e002577.3","doi-asserted-by":"publisher","DOI":"10.2147\/CEOR.S34321"},{"key":"2026010701503854000_12.1.e002577.4","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.rmed.2018.01.008","article-title":"Hospitalizations due to exacerbations of COPD: A big data perspective","volume":"145","author":"Serra-Picamal","year":"2018","journal-title":"Respir Med"},{"key":"2026010701503854000_12.1.e002577.5","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0150737","article-title":"Readmission for Acute Exacerbation within 30 Days of Discharge Is Associated with a Subsequent Progressive Increase in Mortality Risk in COPD Patients: A Long-Term Observational Study","volume":"11","author":"Guerrero","year":"2016","journal-title":"PLoS One"},{"key":"2026010701503854000_12.1.e002577.6","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1016\/j.jaip.2017.01.004","article-title":"Inhaler Errors in the CRITIKAL Study: Type, Frequency, and Association with Asthma Outcomes","volume":"5","author":"Price","year":"2017","journal-title":"J Allergy Clin Immunol Pract"},{"key":"2026010701503854000_12.1.e002577.7","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.00166410"},{"key":"2026010701503854000_12.1.e002577.8","first-page":"1304","article-title":"Dry powder inhalers: an overview","volume":"50","author":"Atkins","year":"2005","journal-title":"Respir Care"},{"key":"2026010701503854000_12.1.e002577.9","doi-asserted-by":"crossref","first-page":"2547","DOI":"10.1007\/s12325-019-01066-6","article-title":"Understanding Dry Powder Inhalers: Key Technical and Patient Preference Attributes","volume":"36","author":"Levy","year":"2019","journal-title":"Adv Ther"},{"key":"2026010701503854000_12.1.e002577.10","doi-asserted-by":"publisher","DOI":"10.15326\/jcopdf.4.3.2017.0183"},{"key":"2026010701503854000_12.1.e002577.11","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.01.00216501"},{"key":"2026010701503854000_12.1.e002577.12","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.rmed.2016.05.011","article-title":"Overuse of short-acting beta-agonist bronchodilators in COPD during periods of clinical stability","volume":"116","author":"Fan","year":"2016","journal-title":"Respir Med"},{"key":"2026010701503854000_12.1.e002577.13","doi-asserted-by":"publisher","DOI":"10.1164\/ajrccm.149.3.8118625"},{"key":"2026010701503854000_12.1.e002577.14","doi-asserted-by":"crossref","DOI":"10.1186\/s12890-015-0077-0","article-title":"Reliever salbutamol use as a measure of exacerbation risk in chronic obstructive pulmonary disease","volume":"15","author":"Jenkins","year":"2015","journal-title":"BMC Pulm Med"},{"key":"2026010701503854000_12.1.e002577.15","doi-asserted-by":"crossref","DOI":"10.1186\/s12931-017-0566-1","article-title":"Rescue medication use as a patient-reported outcome in COPD: a systematic review and regression analysis","volume":"18","author":"Punekar","year":"2017","journal-title":"Respir Res"},{"key":"2026010701503854000_12.1.e002577.16","doi-asserted-by":"crossref","DOI":"10.1183\/13993003.01739-2019","article-title":"Day-to-day variability of forced oscillatory mechanics for early detection of acute exacerbations in COPD","volume":"56","author":"Zimmermann","year":"2020","journal-title":"Eur Respir J"},{"key":"2026010701503854000_12.1.e002577.17","unstructured":"ProAir digihaler. Available: https:\/\/www.digihaler.com\/globalassets\/proair_digihaler\/proair_digihaler_pi.pdf [Accessed 19 Dec 2024]."},{"key":"2026010701503854000_12.1.e002577.18","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1089\/jamp.2021.0031","article-title":"Investigating the Accuracy of the Digihaler, a New Electronic Multidose Dry-Powder Inhaler, in Measuring Inhalation Parameters","volume":"35","author":"Chrystyn","year":"2022","journal-title":"J Aerosol Med Pulm Drug Deliv"},{"key":"2026010701503854000_12.1.e002577.19","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.2147\/JAA.S377631","article-title":"A Predictive Machine Learning Tool for Asthma Exacerbations: Results from a 12-Week, Open-Label Study Using an Electronic Multi-Dose Dry Powder Inhaler with Integrated Sensors","volume":"15","author":"Lugogo","year":"2022","journal-title":"J Asthma Allergy"},{"key":"2026010701503854000_12.1.e002577.20","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.119.041980"},{"key":"2026010701503854000_12.1.e002577.21","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCHEARTFAILURE.119.006513","article-title":"Continuous Wearable Monitoring Analytics Predict Heart Failure Hospitalization: The LINK-HF Multicenter Study","volume":"13","author":"Stehlik","year":"2020","journal-title":"Circ Heart Fail"},{"key":"2026010701503854000_12.1.e002577.22","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000003891"},{"key":"2026010701503854000_12.1.e002577.23","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"2026010701503854000_12.1.e002577.24","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"2026010701503854000_12.1.e002577.25","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/nature14541","article-title":"Probabilistic machine learning and artificial intelligence","volume":"521","author":"Ghahramani","year":"2015","journal-title":"Nature New Biol"},{"key":"2026010701503854000_12.1.e002577.26","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.001593"},{"key":"2026010701503854000_12.1.e002577.27","doi-asserted-by":"publisher","DOI":"10.1038\/nbt0908-1011"},{"key":"2026010701503854000_12.1.e002577.28","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203450"},{"key":"2026010701503854000_12.1.e002577.29","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200801-060ST"},{"key":"2026010701503854000_12.1.e002577.30","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . Xgboost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016:785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"2026010701503854000_12.1.e002577.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"2026010701503854000_12.1.e002577.32","doi-asserted-by":"crossref","DOI":"10.1186\/1465-9921-13-44","article-title":"Prediction and course of symptoms and lung function around an exacerbation in chronic obstructive pulmonary disease","volume":"13","author":"van den Berge","year":"2012","journal-title":"Respir Res"},{"key":"2026010701503854000_12.1.e002577.33","first-page":"13","article-title":"COPD: the patient perspective","volume":"11 Spec Iss","author":"Jones","year":"2016","journal-title":"Int J Chron Obstruct Pulmon Dis"},{"key":"2026010701503854000_12.1.e002577.34","doi-asserted-by":"crossref","DOI":"10.2196\/13286","article-title":"Passive Monitoring of Short-Acting Beta-Agonist Use via Digital Platform in Patients With Chronic Obstructive Pulmonary Disease: Quality Improvement Retrospective Analysis","volume":"3","author":"Chen","year":"2019","journal-title":"JMIR Form Res"},{"key":"2026010701503854000_12.1.e002577.35","doi-asserted-by":"publisher","DOI":"10.1136\/qhc.11.4.376"},{"key":"2026010701503854000_12.1.e002577.36","doi-asserted-by":"crossref","DOI":"10.1186\/s12931-017-0710-y","article-title":"Critical inhaler errors in asthma and COPD: a systematic review of impact on health outcomes","volume":"19","author":"Usmani","year":"2018","journal-title":"Respir Res"},{"key":"2026010701503854000_12.1.e002577.37","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200310-1443OC"},{"key":"2026010701503854000_12.1.e002577.38","doi-asserted-by":"publisher","DOI":"10.1136\/thx.2005.040527"},{"key":"2026010701503854000_12.1.e002577.39","doi-asserted-by":"crossref","first-page":"9773","DOI":"10.3390\/s150509773","article-title":"Tidal volume estimation using the blanket fractal dimension of the tracheal sounds acquired by smartphone","volume":"15","author":"Reljin","year":"2015","journal-title":"Sensors (Basel)"},{"key":"2026010701503854000_12.1.e002577.40","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-24909-9","article-title":"Machine learning did not beat logistic regression in time series prediction for severe asthma exacerbations","volume":"12","author":"de Hond","year":"2022","journal-title":"Sci Rep"}],"container-title":["BMJ Open Respiratory Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjresp-2024-002577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T09:51:17Z","timestamp":1767779477000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopenrespres.bmj.com\/lookup\/doi\/10.1136\/bmjresp-2024-002577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,5,12]]},"published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1136\/bmjresp-2024-002577"],"URL":"https:\/\/doi.org\/10.1136\/bmjresp-2024-002577","relation":{},"ISSN":["2052-4439"],"issn-type":[{"value":"2052-4439","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}