{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T08:20:39Z","timestamp":1793866839072,"version":"4.6.1"},"reference-count":25,"publisher":"BMJ","issue":"10","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","award":["Onderzoeksprogramma Artifici\u00eble Intelligentie (AI"],"award-info":[{"award-number":["Onderzoeksprogramma Artifici\u00eble Intelligentie (AI"]}],"id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004325","name":"AstraZeneca","doi-asserted-by":"publisher","award":["KU Leuven Chair in Respiratory Diseases LSASZ7- O2"],"award-info":[{"award-number":["KU Leuven Chair in Respiratory Diseases LSASZ7- O2"]}],"id":[{"id":"10.13039\/100004325","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["Personal funding Iwein Gyselinck: 11N3922N"],"award-info":[{"award-number":["Personal funding Iwein Gyselinck: 11N3922N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["Research Project 'Artificial Intelligence (AI) for"],"award-info":[{"award-number":["Research Project 'Artificial Intelligence (AI) for"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["Senior investigator Wim Janssens: 1800715N|1800720"],"award-info":[{"award-number":["Senior investigator Wim Janssens: 1800715N|1800720"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Thorax"],"accepted":{"date-parts":[[2023,3,13]]},"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:sec><jats:title>Rationale<\/jats:title><jats:p>Estimating the causal effect of an intervention at individual level, also called individual treatment effect (ITE), may help in identifying response prior to the intervention.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>We aimed to develop machine learning (ML) models which estimate ITE of an intervention using data from randomised controlled trials and illustrate this approach with prediction of ITE on annual chronic obstructive pulmonary disease (COPD) exacerbation rates.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We used data from 8151 patients with COPD of the Study to Understand Mortality and MorbidITy in COPD (SUMMIT) trial (<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"clintrialgov\" xlink:href=\"NCT01313676\">NCT01313676<\/jats:ext-link>) to address the ITE of fluticasone furoate\/vilanterol (FF\/VI) versus control (placebo) on exacerbation rate and developed a novel metric, Q-score, for assessing the power of causal inference models. We then validated the methodology on 5990 subjects from the InforMing the PAthway of COPD Treatment (IMPACT) trial (<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"clintrialgov\" xlink:href=\"NCT02164513\">NCT02164513<\/jats:ext-link>) to estimate the ITE of FF\/umeclidinium\/VI (FF\/UMEC\/VI) versus UMEC\/VI on exacerbation rate. We used Causal Forest as causal inference model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In SUMMIT, Causal Forest was optimised on the training set (n=5705) and tested on 2446 subjects (Q-score 0.61). In IMPACT, Causal Forest was optimised on 4193 subjects in the training set and tested on 1797 individuals (Q-score 0.21). In both trials, the quantiles of patients with the strongest ITE consistently demonstrated the largest reductions in observed exacerbations rates (0.54 and 0.53, p&lt;0.001). Poor lung function and blood eosinophils, respectively, were the strongest predictors of ITE.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study shows that ML models for causal inference can be used to identify individual response to different COPD treatments and highlight treatment traits. Such models could become clinically useful tools for individual treatment decisions in COPD.<\/jats:p><\/jats:sec>","DOI":"10.1136\/thorax-2022-219382","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:23:37Z","timestamp":1680542617000},"page":"983-989","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":24,"title":["Estimating individual treatment effects on COPD exacerbations by causal machine learning on randomised controlled trials"],"prefix":"10.1136","volume":"78","clinical-trial-number":[{"clinical-trial-number":"nct01313676","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct02164513","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct01313676","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct02164513","registry":"10.18810\/clinical-trials-gov"}],"author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3790-417X","authenticated-orcid":false,"given":"Kenneth","family":"Verstraete","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-7228","authenticated-orcid":false,"given":"Iwein","family":"Gyselinck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0617-1316","authenticated-orcid":false,"given":"Helene","family":"Huts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8960-7188","authenticated-orcid":false,"given":"Nilakash","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6101-755X","authenticated-orcid":false,"given":"Marko","family":"Topalovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3482-5145","authenticated-orcid":false,"given":"Maarten","family":"De Vos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2982","authenticated-orcid":false,"given":"Wim","family":"Janssens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"key":"2024051320332704000_78.10.983.1","doi-asserted-by":"publisher","DOI":"10.2307\/2289064"},{"key":"2024051320332704000_78.10.983.2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.4.669"},{"key":"2024051320332704000_78.10.983.3","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177732676"},{"key":"2024051320332704000_78.10.983.4","doi-asserted-by":"publisher","DOI":"10.2307\/1905714"},{"key":"2024051320332704000_78.10.983.5","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1017\/S026646661400022X","article-title":"Causal analysis after Haavelmo","volume":"31","author":"Heckman","year":"2015","journal-title":"Econ Theory"},{"key":"2024051320332704000_78.10.983.6","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1214\/ss\/1177012031","article-title":"On the application of probability theory to agricultural experiments. Essay on principles. Section 9","volume":"5","author":"Splawa-Neyman","year":"1990","journal-title":"Statist Sci"},{"key":"2024051320332704000_78.10.983.7","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"2024051320332704000_78.10.983.8","doi-asserted-by":"crossref","unstructured":"Rubin DB . Matched sampling for causal effects. Cambridge University Press, 2006: 1\u2013489.","DOI":"10.1017\/CBO9780511810725"},{"key":"2024051320332704000_78.10.983.9","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.00087312"},{"key":"2024051320332704000_78.10.983.10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1713901"},{"key":"2024051320332704000_78.10.983.11","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1016\/S0140-6736(16)30069-1","article-title":"Fluticasone furoate and vilanterol and survival in chronic obstructive pulmonary disease with heightened cardiovascular risk (summit): a double-blind randomised controlled trial","volume":"387","author":"Vestbo","year":"2016","journal-title":"Lancet"},{"key":"2024051320332704000_78.10.983.12","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1164\/rccm.201607-1421OC","article-title":"Effect of fluticasone furoate and vilanterol on exacerbations of chronic obstructive pulmonary disease in patients with moderate airflow obstruction","volume":"195","author":"Martinez","year":"2017","journal-title":"Am J Respir Crit Care Med"},{"key":"2024051320332704000_78.10.983.13","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1214\/18-AOS1709","article-title":"Generalized random forests","volume":"47","author":"Athey","year":"2019","journal-title":"Ann Statist"},{"key":"2024051320332704000_78.10.983.14","first-page":"85","article-title":"A multivariate technique for multiply imputing missing values using A sequence of regression models","volume":"27","author":"Raghunathan","year":"2001","journal-title":"Surv Methodol"},{"key":"2024051320332704000_78.10.983.15","doi-asserted-by":"publisher","DOI":"10.1177\/0962280206074463"},{"key":"2024051320332704000_78.10.983.16","unstructured":"Lundberg SM , Lee SI . A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. 2017: 4766\u201375."},{"key":"2024051320332704000_78.10.983.17","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"2024051320332704000_78.10.983.18","unstructured":"Battocchi K , Dillon E , Syrgkanis V , et al . EconML: a python package for ML-based heterogeneous treatment effects estimation; 2019."},{"key":"2024051320332704000_78.10.983.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2024051320332704000_78.10.983.20","doi-asserted-by":"crossref","unstructured":"Seabold S , Perktold J . Statsmodels: econometric and statistical modeling with python. In: Proceedings of the 9th Python in Science Conference. 2010: 92\u20136.","DOI":"10.25080\/Majora-92bf1922-011"},{"key":"2024051320332704000_78.10.983.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2017.10.021"},{"key":"2024051320332704000_78.10.983.22","unstructured":"Radcliffe NJ . Using control groups to target on predicted lift: building and assessing uplift model. Direct Mark Anal J 2007:14\u201321."},{"key":"2024051320332704000_78.10.983.23","unstructured":"Alaa AM , van der Schaar M . Validating causal inference models via influence functions. In: Proceedings of the 36th International Conference on Machine Learning. 2019: 191\u2013201."},{"key":"2024051320332704000_78.10.983.24","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa0909883"},{"key":"2024051320332704000_78.10.983.25","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01370-2015"}],"container-title":["Thorax"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/thorax-2022-219382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T03:50:13Z","timestamp":1715658613000},"score":1,"resource":{"primary":{"URL":"https:\/\/thorax.bmj.com\/lookup\/doi\/10.1136\/thorax-2022-219382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":25,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,9,15]]},"published-print":{"date-parts":[[2023,10]]}},"alternative-id":["10.1136\/thorax-2022-219382"],"URL":"https:\/\/doi.org\/10.1136\/thorax-2022-219382","relation":{},"ISSN":["0040-6376","1468-3296"],"issn-type":[{"value":"0040-6376","type":"print"},{"value":"1468-3296","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,3]]}}}