{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:49:15Z","timestamp":1791503355026,"version":"4.3.4"},"reference-count":34,"publisher":"Georg Thieme Verlag KG","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"H\u00f4pitaux Universitaires de Gen\u00e8ve","award":["PRD 7-2019-I"],"award-info":[{"award-number":["PRD 7-2019-I"]}],"id":[{"id":"https:\/\/ror.org\/01m1pv723","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Thromb Haemost"],"abstract":"<jats:p>Pulmonary embolism (PE) is frequently suspected in emergency departments (EDs). Safely ruling out PE without additional testing could reduce imaging use and ED crowding. Machine learning (ML) may improve accuracy and efficiency.<\/jats:p>\n                  <jats:p>To evaluate ML models for ruling out PE without additional testing in ED patients with suspected PE, while maintaining a failure rate &lt;2%.<\/jats:p>\n                  <jats:p>We retrospectively analyzed pooled data from four prospective European studies of ED patients with suspected PE (2000\u20132013). A total of 5,038 patients were randomly split into training (n\u2009=\u20092,400) and validation (n\u2009=\u20092,638) datasets. ML models classified patients into low, intermediate, and high pre-test probability groups. In intermediate-risk patients, post-test probability was refined using either a fixed D-dimer threshold or a second ML model. The primary outcome was the failure rate assessed in the validation cohort and defined as the proportion of missed PE diagnoses.<\/jats:p>\n                  <jats:p>The best-performing algorithm combined weighted ridge regression (pre-test) with weighted random forest (post-test), achieving a failure rate of 1.44% (95% CI: 1.04\u20131.99) and a Matthews correlation coefficient of 0.470 (95% CI: 0.440\u20130.500). This model ruled out PE without any testing in 9.7% of patients, with an estimated imaging proportion of 54.1%, comparable to 4-level Pulmonary Embolism Clinical Probability Score (4PEPS; 52.9%) and lower than Pulmonary Embolism Rule-out Criteria (PERC; 66.8%).<\/jats:p>\n                  <jats:p>A two-step ML algorithm performed comparably to the best existing clinical decision rules, with a failure rate whose confidence interval remained below the prespecified 2% criterion and an estimated imaging proportion similar to 4PEPS. Prospective external validation is warranted.<\/jats:p>","DOI":"10.1055\/a-2939-4076","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T23:14:39Z","timestamp":1790637279000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Models for Suspected Pulmonary Embolism in Emergency Department Patients: A Multicentre Diagnostic Study"],"prefix":"10.1055","author":[{"given":"Christophe A.","family":"Fehlmann","sequence":"first","affiliation":[{"name":"Geneva University Hospitals, Switzerland","place":["Geneva"],"department":["Department of Acute Medicine, Division of Emergency Medicine"]},{"name":"Intensive Care and Emergency Medicine, Faculty of Medicine, University of Geneva, Switzerland","place":["Geneva"],"department":["Department of Anaesthesiology, Clinical Pharmacology"]},{"name":"School of Epidemiology and Public Health, University of Ottawa, Ontario, Canada","place":["Ottawa"]},{"name":"Ottawa Hospital Research Institute, Canada","place":["Ottawa"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2225-8320","authenticated-orcid":false,"given":"Ben","family":"Meuleman","sequence":"first","affiliation":[{"name":"University of Geneva, Switzerland","place":["Geneva"],"department":["Swiss Center for Affective Sciences"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-1269","authenticated-orcid":false,"given":"Helia","family":"Robert-Ebadi","sequence":"additional","affiliation":[{"name":"Geneva University Hospitals and Faculty of Medicine, Switzerland","place":["Geneva"],"department":["Department of Medicine, Division of Angiology and Haemostasis"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Righini","sequence":"additional","affiliation":[{"name":"Geneva University Hospitals and Faculty of Medicine, Switzerland","place":["Geneva"],"department":["Department of Medicine, Division of Angiology and Haemostasis"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnaud","family":"Perrier","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Geneva, Switzerland","place":["Geneva"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marlieke E.A.","family":"de Kraker","sequence":"additional","affiliation":[{"name":"Geneva University Hospitals and Faculty of Medicine, Switzerland","place":["Geneva"],"department":["Infection Control Programme and World Health Organization Collaborating Centre on Infection Prevention and Control and Antimicrobial Resistance"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7265-1887","authenticated-orcid":false,"given":"Mohamed","family":"Abbas","sequence":"additional","affiliation":[{"name":"Geneva University Hospitals and Faculty of Medicine, Switzerland","place":["Geneva"],"department":["Infection Control Programme and World Health Organization Collaborating Centre on Infection Prevention and Control and Antimicrobial Resistance"]},{"name":"Imperial College London, United Kingdom","place":["London"],"department":["Department of Infectious Disease Epidemiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s12959-016-0078-0","article-title":"Incidence of venous thromboembolism in France: a retrospective analysis of a national insurance claims database","volume":"14","author":"S Bou\u00e9e","year":"2016","journal-title":"Thromb J"},{"issue":"01","key":"ref2","doi-asserted-by":"crossref","first-page":"e005753","DOI":"10.1161\/CIRCOUTCOMES.119.005753","article-title":"Over-testing for suspected pulmonary embolism in American emergency departments: the continuing epidemic","volume":"13","author":"J A Kline","year":"2020","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"43","key":"ref3","doi-asserted-by":"crossref","first-page":"3033","DOI":"10.1093\/eurheartj\/ehu283","article-title":"2014 ESC guidelines on the diagnosis and management of acute pulmonary embolism","volume":"35","author":"S V Konstantinides","year":"2014","journal-title":"Eur Heart J"},{"issue":"13","key":"ref4","doi-asserted-by":"crossref","first-page":"1336","DOI":"10.1001\/jama.2022.16815","article-title":"Acute pulmonary embolism: a review","volume":"328","author":"Y Freund","year":"2022","journal-title":"JAMA"},{"issue":"03","key":"ref5","doi-asserted-by":"crossref","first-page":"165","DOI":"10.7326\/0003-4819-144-3-200602070-00004","article-title":"Prediction of pulmonary embolism in the emergency department: the revised Geneva score","volume":"144","author":"G Le Gal","year":"2006","journal-title":"Ann Intern Med"},{"issue":"05","key":"ref6","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/j.annemergmed.2004.04.002","article-title":"Prospective validation of Wells criteria in the evaluation of patients with suspected pulmonary embolism","volume":"44","author":"S J Wolf","year":"2004","journal-title":"Ann Emerg Med"},{"issue":"08","key":"ref7","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1111\/j.1538-7836.2004.00790.x","article-title":"Clinical criteria to prevent unnecessary diagnostic testing in emergency department patients with suspected pulmonary embolism","volume":"2","author":"J A Kline","year":"2004","journal-title":"J Thromb Haemost"},{"issue":"02","key":"ref8","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1111\/j.1538-7836.2010.04147.x","article-title":"The pulmonary embolism rule-out criteria (PERC) rule does not safely exclude pulmonary embolism","volume":"9","author":"O Hugli","year":"2011","journal-title":"J Thromb Haemost"},{"issue":"01","key":"ref9","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1111\/j.1538-7836.2004.01097.x","article-title":"More on: clinical criteria to prevent unnecessary diagnostic testing in emergency department patients with suspected pulmonary embolism","volume":"3","author":"M Righini","year":"2005","journal-title":"J Thromb Haemost"},{"issue":"11","key":"ref10","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1001\/jama.2014.2135","article-title":"Age-adjusted D-dimer cutoff levels to rule out pulmonary embolism: the ADJUST-PE study","volume":"311","author":"M Righini","year":"2014","journal-title":"JAMA"},{"issue":"02","key":"ref11","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1055\/s-0041-1723936","article-title":"Suspected acute pulmonary embolism: gestalt, scoring systems, and artificial intelligence","volume":"42","author":"D Douillet","year":"2021","journal-title":"Semin Respir Crit Care Med"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd ed","author":"T Hastie","year":"2009"},{"issue":"01","key":"ref13","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"E J Topol","year":"2019","journal-title":"Nat Med"},{"issue":"05","key":"ref14","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1111\/bjh.18737","article-title":"Machine learning to predict major bleeding during anticoagulation for venous thromboembolism: possibilities and limitations","volume":"201","author":"D Mora","year":"2023","journal-title":"Br J Haematol"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1087702","DOI":"10.3389\/fcvm.2023.1087702","article-title":"Prediction of in-hospital adverse clinical outcomes in patients with pulmonary thromboembolism, machine learning based models","volume":"10","author":"Y Jenab","year":"2023","journal-title":"Front Cardiovasc Med"},{"issue":"01","key":"ref16","first-page":"13","article-title":"Machine learning with D-dimer in the risk stratification for pulmonary embolism: a derivation and internal validation study","volume":"11","author":"H Villacorta","year":"2022","journal-title":"Eur Heart J Acute Cardiovasc Care"},{"issue":"01","key":"ref17","doi-asserted-by":"crossref","first-page":"12868","DOI":"10.1038\/s41598-021-92287-9","article-title":"Prediction of venous thromboembolism with machine learning techniques in young-middle-aged inpatients","volume":"11","author":"H Liu","year":"2021","journal-title":"Sci Rep"},{"issue":"08","key":"ref18","doi-asserted-by":"crossref","first-page":"e198719","DOI":"10.1001\/jamanetworkopen.2019.8719","article-title":"Development and performance of the Pulmonary Embolism Result Forecast Model (PERFORM) for computed tomography clinical decision support","volume":"2","author":"I Banerjee","year":"2019","journal-title":"JAMA Netw Open"},{"issue":"01","key":"ref19","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1038\/s41598-024-75435-9","article-title":"Prediction of pulmonary embolism by an explainable machine learning approach in the real world","volume":"15","author":"Q Zhou","year":"2025","journal-title":"Sci Rep"},{"issue":"06","key":"ref20","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1111\/ejh.14110","article-title":"Artificial intelligence in the prediction of venous thromboembolism: a systematic review and pooled analysis","volume":"111","author":"T Chiasakul","year":"2023","journal-title":"Eur J Haematol"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.thromres.2023.12.002","article-title":"Artificial intelligence for predicting pulmonary embolism: a review of machine learning approaches and performance evaluation","volume":"234","author":"R Puchades","year":"2024","journal-title":"Thromb Res"},{"issue":"17","key":"ref22","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1056\/NEJMoa042905","article-title":"Multidetector-row computed tomography in suspected pulmonary embolism","volume":"352","author":"A Perrier","year":"2005","journal-title":"N Engl J Med"},{"issue":"05","key":"ref23","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.amjmed.2003.09.041","article-title":"Diagnosing pulmonary embolism in outpatients with clinical assessment, D-dimer measurement, venous ultrasound, and helical computed tomography: a multicenter management study","volume":"116","author":"A Perrier","year":"2004","journal-title":"Am J Med"},{"issue":"9621","key":"ref24","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1016\/S0140-6736(08)60594-2","article-title":"Diagnosis of pulmonary embolism by multidetector CT alone or combined with venous ultrasonography of the leg: a randomised non-inferiority trial","volume":"371","author":"M Righini","year":"2008","journal-title":"Lancet"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"G S Collins","year":"2024","journal-title":"BMJ"},{"issue":"01","key":"ref26","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13040-023-00322-4","article-title":"The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","volume":"16","author":"D Chicco","year":"2023","journal-title":"BioData Min"},{"issue":"02","key":"ref27","first-page":"156","article-title":"Evaluating effect size in psychological research: sense and nonsense","volume":"2","author":"D C Funder","year":"2019","journal-title":"Adv Methods Pract Psychol Sci"},{"issue":"24","key":"ref28","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1001\/jama.2019.18058","article-title":"Addressing bias in artificial intelligence in health care","volume":"322","author":"R B Parikh","year":"2019","journal-title":"JAMA"},{"issue":"06","key":"ref29","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1001\/jamacardio.2021.0064","article-title":"Derivation and validation of a 4-level clinical pretest probability score for suspected pulmonary embolism to safely decrease imaging testing","volume":"6","author":"P M Roy","year":"2021","journal-title":"JAMA Cardiol"},{"key":"ref30","first-page":"10","article-title":"Construction of a risk prediction model for hospital-acquired pulmonary embolism in hospitalized patients","volume":"27","author":"L Hou","year":"2021","journal-title":"Clin Appl Thromb Hemost"},{"issue":"01","key":"ref31","doi-asserted-by":"crossref","first-page":"e12013","DOI":"10.1002\/pul2.12013","article-title":"Predicting pulmonary embolism among hospitalized patients with machine learning algorithms","volume":"12","author":"L Ryan","year":"2022","journal-title":"Pulm Circ"},{"issue":"02","key":"ref32","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.annemergmed.2009.07.023","article-title":"US emergency department performance on wait time and length of visit","volume":"55","author":"L I Horwitz","year":"2010","journal-title":"Ann Emerg Med"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.ajem.2024.09.016","article-title":"Epidemiology of pulmonary embolism diagnosis and management among United States emergency departments over an eight-year period","volume":"85","author":"M Gottlieb","year":"2024","journal-title":"Am J Emerg Med"},{"issue":"06","key":"ref34","doi-asserted-by":"crossref","first-page":"761","DOI":"10.7326\/M22-3116","article-title":"Temporal trends in the use of computed tomographic pulmonary angiography for suspected pulmonary embolism in the emergency department: a retrospective analysis","volume":"176","author":"M Roussel","year":"2023","journal-title":"Ann Intern Med"}],"container-title":["Thrombosis and Haemostasis"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-2939-4076.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:02:10Z","timestamp":1791500530000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-2939-4076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1055\/a-2939-4076","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["0340-6245","2567-689X"],"issn-type":[{"value":"0340-6245","type":"print"},{"value":"2567-689X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9,28]]},"published":{"date-parts":[[2026,9,28]]}}}