{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T01:35:01Z","timestamp":1794620101662,"version":"4.9.1"},"reference-count":28,"publisher":"European Respiratory Society (ERS)","issue":"1","license":[{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["5K23HL15189202"],"award-info":[{"award-number":["5K23HL15189202"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["5K25HL133481"],"award-info":[{"award-number":["5K25HL133481"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["P01HL01498"],"award-info":[{"award-number":["P01HL01498"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["P01HL152961"],"award-info":[{"award-number":["P01HL152961"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["publications.ersnet.org"],"crossmark-restriction":true},"short-container-title":["ERJ Open Res"],"accepted":{"date-parts":[[2022,10,20]]},"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Pulmonary arterial hypertension (PAH) is a heterogeneous and complex pulmonary vascular disease associated with substantial morbidity. Machine-learning algorithms (used in many PAH risk calculators) can combine established parameters with thousands of circulating biomarkers to optimise PAH prognostication, but these approaches do not offer the clinician insight into what parameters drove the prognosis. The approach proposed in this study diverges from other contemporary phenotyping methods by identifying patient-specific parameters driving clinical risk.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We trained a random forest algorithm to predict 4-year survival risk in a cohort of 167 adult PAH patients evaluated at Stanford University, with 20% withheld for (internal) validation. Another cohort of 38 patients from Sheffield University were used as a secondary (external) validation. Shapley values, borrowed from game theory, were computed to rank the input parameters based on their importance to the predicted risk score for the entire trained random forest model (global importance) and for an individual patient (local importance).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Between the internal and external validation cohorts, the random forest model predicted 4-year risk of death\/transplant with sensitivity and specificity of 71.0\u2013100% and 81.0\u201389.0%, respectively. The model reinforced the importance of established prognostic markers, but also identified novel inflammatory biomarkers that predict risk in some PAH patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>These results stress the need for advancing individualised phenotyping strategies that integrate clinical and biochemical data with outcome. The computational platform presented in this study offers a critical step towards personalised medicine in which a clinician can interpret an algorithm's assessment of an individual patient.<\/jats:p><\/jats:sec>","DOI":"10.1183\/23120541.00484-2022","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T17:27:45Z","timestamp":1669310865000},"page":"00484-2022","update-policy":"https:\/\/doi.org\/10.1183\/ers-crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Computational platform for doctor\u2013artificial intelligence cooperation in pulmonary arterial hypertension prognostication: a pilot study"],"prefix":"10.1183","volume":"9","author":[{"given":"Vitaly O.","family":"Kheyfets","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew J.","family":"Sweatt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mardi","family":"Gomberg-Maitland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dunbar D.","family":"Ivy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3492-4143","authenticated-orcid":false,"given":"Robin","family":"Condliffe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0184-6502","authenticated-orcid":false,"given":"David G.","family":"Kiely","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4192-9505","authenticated-orcid":false,"given":"Allan","family":"Lawrie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley A.","family":"Maron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roham T.","family":"Zamanian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kurt R.","family":"Stenmark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"81","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"2024101711451622000_9.1.00484-2022.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2020.04.039"},{"key":"2024101711451622000_9.1.00484-2022.2","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1164\/rccm.202012-4317SO","article-title":"Pulmonary arterial hypertension: diagnosis, treatment, and novel advances","volume":"203","author":"Maron","year":"2021","journal-title":"Am J Respir Crit Care Med"},{"key":"2024101711451622000_9.1.00484-2022.3","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1056\/NEJMoa2024277","article-title":"Sotatercept for the treatment of pulmonary arterial hypertension","volume":"384","author":"Humbert","year":"2021","journal-title":"N Engl J Med"},{"key":"2024101711451622000_9.1.00484-2022.4","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01032-2015"},{"key":"2024101711451622000_9.1.00484-2022.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2019.02.004"},{"key":"2024101711451622000_9.1.00484-2022.6","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.chest.2020.08.2069","article-title":"Development and validation of an abridged version of the REVEAL 2.0 risk score calculator, REVEAL Lite 2, for use in patients with pulmonary arterial hypertension","volume":"159","author":"Benza","year":"2021","journal-title":"Chest"},{"key":"2024101711451622000_9.1.00484-2022.7","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1161\/CIRCRESAHA.118.313911","article-title":"Discovery of distinct immune phenotypes using machine learning in pulmonary arterial hypertension","volume":"124","author":"Sweatt","year":"2019","journal-title":"Circ Res"},{"key":"2024101711451622000_9.1.00484-2022.8","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.ccm.2020.10.004","article-title":"Personalized medicine for pulmonary hypertension: the future management of pulmonary hypertension requires a new taxonomy","volume":"42","author":"Wilkins","year":"2021","journal-title":"Clin Chest Med"},{"key":"2024101711451622000_9.1.00484-2022.9","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.04625-2020"},{"key":"2024101711451622000_9.1.00484-2022.10","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1164\/rccm.202105-1118OC","article-title":"Using the plasma proteome for risk stratifying patients with pulmonary arterial hypertension","volume":"205","author":"Rhodes","year":"2022","journal-title":"Am J Respir Crit Care Med"},{"key":"2024101711451622000_9.1.00484-2022.11","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/S2213-2600(17)30161-3","article-title":"Plasma proteome analysis in patients with pulmonary arterial hypertension: an observational cohort study","volume":"5","author":"Rhodes","year":"2017","journal-title":"Lancet Respir Med"},{"key":"2024101711451622000_9.1.00484-2022.12","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2024101711451622000_9.1.00484-2022.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2024101711451622000_9.1.00484-2022.14","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-5-81"},{"key":"2024101711451622000_9.1.00484-2022.15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"2024101711451622000_9.1.00484-2022.16","unstructured":"Shapley L . Notes on the N-Person Game \u2013 II: The Value of an N-Person Game. Santa Monica, The RAND Corporation, 1951."},{"key":"2024101711451622000_9.1.00484-2022.17","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA. Red Hook, Curran Associates, 2017: pp. 4768\u20134777."},{"key":"2024101711451622000_9.1.00484-2022.18","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-3"},{"key":"2024101711451622000_9.1.00484-2022.19","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil A , Caruana R . Predicting Good Probabilities with Supervised Learning. Proceedings of the 22nd International Conference on Machine Learning, Germany. New York, Association for Computing Machinery, 2005: 625\u2013632. doi10.1145\/1102351.1102430","DOI":"10.1145\/1102351.1102430"},{"key":"2024101711451622000_9.1.00484-2022.20","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.02591-2020"},{"key":"2024101711451622000_9.1.00484-2022.21","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00008-2020"},{"key":"2024101711451622000_9.1.00484-2022.22","doi-asserted-by":"crossref","first-page":"103444","DOI":"10.1016\/j.ebiom.2021.103444","article-title":"A diagnostic miRNA signature for pulmonary arterial hypertension using a consensus machine learning approach","volume":"69","author":"Errington","year":"2021","journal-title":"EBioMedicine"},{"key":"2024101711451622000_9.1.00484-2022.23","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.00151313"},{"key":"2024101711451622000_9.1.00484-2022.24","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.109.933762"},{"key":"2024101711451622000_9.1.00484-2022.25","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.113.301141"},{"key":"2024101711451622000_9.1.00484-2022.26","doi-asserted-by":"publisher","DOI":"10.1186\/1465-9921-15-47"},{"key":"2024101711451622000_9.1.00484-2022.27","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/s00059-019-4795-6","article-title":"Key inflammatory pathways underlying vascular remodeling in pulmonary hypertension","volume":"44","author":"Berghausen","year":"2019","journal-title":"Herz"},{"key":"2024101711451622000_9.1.00484-2022.28","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7"}],"container-title":["ERJ Open Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1183\/23120541.00484-2022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T05:22:10Z","timestamp":1740374530000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.ersnet.org\/lookup\/doi\/10.1183\/23120541.00484-2022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,24]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,2,6]]},"published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1183\/23120541.00484-2022"],"URL":"https:\/\/doi.org\/10.1183\/23120541.00484-2022","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1183\/23120541.00484-2022.supp1","asserted-by":"subject"}]},"ISSN":["2312-0541"],"issn-type":[{"value":"2312-0541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,24]]}}}