Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations
-
Published:2023-05
Issue:5
Volume:29
Page:1201-1210
-
ISSN:1078-8956
-
Container-title:Nature Medicine
-
language:en
-
Short-container-title:Nat Med
Author:
Doudesis DimitriosORCID, Lee Kuan KenORCID, Boeddinghaus JasperORCID, Bularga Anda, Ferry Amy V.ORCID, Tuck ChrisORCID, Lowry Matthew T. H.ORCID, Lopez-Ayala PedroORCID, Nestelberger Thomas, Koechlin Luca, Bernabeu Miguel O.ORCID, Neubeck Lis, Anand AtulORCID, Schulz KarenORCID, Apple Fred S., Parsonage William, Greenslade Jaimi H.ORCID, Cullen LouiseORCID, Pickering John W.ORCID, Than Martin P., Gray Alasdair, Mueller Christian, Mills Nicholas L.ORCID, Richards A. Mark, Pemberton Chris, Troughton Richard W., Aldous Sally J., Brown Anthony F. T., Dalton Emily, Hammett Chris, Hawkins Tracey, O’Kane Shanen, Parke Kate, Ryan Kimberley, Schluter Jessica, Wild Karin, Wussler Desiree, Miró Òscar, Martin-Sanchez F. Javier, Keller Dagmar I., Christ Michael, Buser Andreas, Giménez Maria Rubini, Barker Stephanie, Blades Jennifer, Chapman Andrew R., Fujisawa Takeshi, Kimenai Dorien M., Leung Jeremy, Li Ziwen, McDermott Michael, Newby David E., Schulberg Stacey D., Shah Anoop S. V., Sorbie Andrew, Soutar Grace, Strachan Fiona E., Taggart Caelan, Vicencio Daniel Perez, Wang Yiqing, Wereski Ryan, Williams Kelly, Weir Christopher J., Berry Colin, Reid Alan, Maguire Donogh, Collinson Paul O., Sandoval Yader, Smith Stephen W.,
Abstract
AbstractAlthough guidelines recommend fixed cardiac troponin thresholds for the diagnosis of myocardial infarction, troponin concentrations are influenced by age, sex, comorbidities and time from symptom onset. To improve diagnosis, we developed machine learning models that integrate cardiac troponin concentrations at presentation or on serial testing with clinical features and compute the Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome (CoDE-ACS) score (0–100) that corresponds to an individual’s probability of myocardial infarction. The models were trained on data from 10,038 patients (48% women), and their performance was externally validated using data from 10,286 patients (35% women) from seven cohorts. CoDE-ACS had excellent discrimination for myocardial infarction (area under curve, 0.953; 95% confidence interval, 0.947–0.958), performed well across subgroups and identified more patients at presentation as low probability of having myocardial infarction than fixed cardiac troponin thresholds (61 versus 27%) with a similar negative predictive value and fewer as high probability of having myocardial infarction (10 versus 16%) with a greater positive predictive value. Patients identified as having a low probability of myocardial infarction had a lower rate of cardiac death than those with intermediate or high probability 30 days (0.1 versus 0.5 and 1.8%) and 1 year (0.3 versus 2.8 and 4.2%; P < 0.001 for both) from patient presentation. CoDE-ACS used as a clinical decision support system has the potential to reduce hospital admissions and have major benefits for patients and health care providers.
Funder
British Heart Foundation RCUK | Medical Research Council The University of Basel, the University Hospital of Basel, the Swiss Academy of Medical Sciences, the Gottfried and Julia Bangerter-Rhyner Foundation, the Swiss National Science Foundation Swiss Heart Foundation, the University of Basel, the Swiss Academy of Medical Science, the Gottfried and Julia Bangerter-Rhyner Foundation, and the “Freiwillige Akademische Gesellschaft Basel.” Advance Queensland Fellowship the Swiss National Science Foundation, the Swiss Heart Foundation, the Commission for Technology and Innovation, and the University Hospital Basel.
Publisher
Springer Science and Business Media LLC
Subject
General Biochemistry, Genetics and Molecular Biology,General Medicine
Reference69 articles.
1. Than, M. et al. A 2-h diagnostic protocol to assess patients with chest pain symptoms in the Asia-Pacific region (ASPECT): a prospective observational validation study. Lancet 377, 1077–1084 (2011). 2. Body, R. et al. Rapid exclusion of acute myocardial infarction in patients with undetectable troponin using a high-sensitivity assay. J. Am. Coll. Cardiol. 58, 1332–1339 (2011). 3. Reichlin, T. et al. One-hour rule-out and rule-in of acute myocardial infarction using high-sensitivity cardiac troponin T. Arch. Intern. Med. 172, 1211–1218 (2012). 4. Shah, A. S. et al. High-sensitivity cardiac troponin I at presentation in patients with suspected acute coronary syndrome: a cohort study. Lancet 386, 2481–2488 (2015). 5. Chapman, A. R. et al. Comparison of the efficacy and safety of early Rule-Out pathways for acute myocardial infarction. Circulation 135, 1586–1596 (2017).
Cited by
53 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|