{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T12:55:06Z","timestamp":1791550506073,"version":"4.3.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T00:00:00Z","timestamp":1654214400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T00:00:00Z","timestamp":1654214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["PJT - 166161"],"award-info":[{"award-number":["PJT - 166161"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004411","name":"Heart and Stroke Foundation of Canada","doi-asserted-by":"publisher","award":["Mid-Career Investigator Award"],"award-info":[{"award-number":["Mid-Career Investigator Award"]}],"id":[{"id":"10.13039\/100004411","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1 TR002243"],"award-info":[{"award-number":["UL1 TR002243"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Machine learning is increasingly being used to predict clinical outcomes. Most comparisons of different methods have been based on empirical analyses in specific datasets. We used Monte Carlo simulations to determine when machine learning methods perform better than statistical learning methods in a specific setting. We evaluated six learning methods: stochastic gradient boosting machines using trees as the base learners, random forests, artificial neural networks, the lasso, ridge regression, and linear regression estimated using ordinary least squares (OLS). Our simulations were informed by empirical analyses in patients with acute myocardial infarction (AMI) and congestive heart failure (CHF) and used six data-generating processes, each based on one of the six learning methods, to simulate continuous outcomes in the derivation and validation samples. The outcome was systolic blood pressure at hospital discharge, a continuous outcome. We applied the six learning methods in each of the simulated derivation samples and evaluated performance in the simulated validation samples. The primary observation was that neural networks tended to result in estimates with worse predictive accuracy than the other five methods in both disease samples and across all six data-generating processes. Boosted trees and OLS regression tended to perform well across a range of scenarios.<\/jats:p>","DOI":"10.1038\/s41598-022-13015-5","type":"journal-article","created":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T18:02:46Z","timestamp":1654279366000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Empirical analyses and simulations showed that different machine and statistical learning methods had differing performance for predicting blood pressure"],"prefix":"10.1038","volume":"12","author":[{"given":"Peter C.","family":"Austin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"suffix":"Jr","given":"Frank E.","family":"Harrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Douglas S.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ewout W.","family":"Steyerberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,3]]},"reference":[{"key":"13015_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","volume":"110","author":"E Christodoulou","year":"2019","unstructured":"Christodoulou, E. et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J. Clin. Epidemiol. 110, 12\u201322 (2019).","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"13015_CR2","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12859-018-2264-5","volume":"19","author":"R Couronne","year":"2018","unstructured":"Couronne, R., Probst, P. & Boulesteix, A. L. Random forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinform. 19(1), 270 (2018).","journal-title":"BMC Bioinform."},{"issue":"2","key":"13015_CR3","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.injury.2019.01.007","volume":"50","author":"S Hassanipour","year":"2019","unstructured":"Hassanipour, S. et al. Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis. Injury 50(2), 244\u2013250 (2019).","journal-title":"Injury"},{"key":"13015_CR4","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1002\/ehf2.13073","volume":"8","author":"S Shin","year":"2021","unstructured":"Shin, S. et al. Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality. ESC Heart Fail. 8, 106\u2013115 (2021).","journal-title":"ESC Heart Fail."},{"issue":"21","key":"13015_CR5","doi-asserted-by":"publisher","first-page":"2330","DOI":"10.1001\/jama.2009.1731","volume":"302","author":"JV Tu","year":"2009","unstructured":"Tu, J. V. et al. Effectiveness of public report cards for improving the quality of cardiac care: the EFFECT study: a randomized trial. J. Am. Med. Assoc. 302(21), 2330\u20132337 (2009).","journal-title":"J. Am. Med. Assoc."},{"issue":"5","key":"13015_CR6","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1002\/bimj.201100251","volume":"54","author":"PC Austin","year":"2012","unstructured":"Austin, P. C. et al. Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?. Biom. J. 54(5), 657\u2013673 (2012).","journal-title":"Biom. J."},{"key":"13015_CR7","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1177\/09622802211002867","volume":"30","author":"PC Austin","year":"2021","unstructured":"Austin, P. C., Harrell, F. E. Jr. & Steyerberg, E. W. Predictive performance of machine and statistical learning methods: Impact of data-generating processes on external validity in the \u201clarge N, small p\u201d setting. Stat. Methods Med Res. 30, 1465\u20131483 (2021).","journal-title":"Stat. Methods Med Res."},{"issue":"15","key":"13015_CR8","doi-asserted-by":"publisher","first-page":"2937","DOI":"10.1002\/sim.2770","volume":"26","author":"PC Austin","year":"2007","unstructured":"Austin, P. C. A comparison of regression trees, logistic regression, generalized additive models, and multivariate adaptive regression splines for predicting AMI mortality. Stat. Med. 26(15), 2937\u20132957 (2007).","journal-title":"Stat. Med."},{"issue":"1","key":"13015_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random Forests. Mach. Learn. 45(1), 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"13015_CR10","first-page":"477","volume":"22","author":"P Buhlmann","year":"2007","unstructured":"Buhlmann, P. & Hathorn, T. Boosting algorithms: Regularization, prediction and model fitting. Stat. Sci. 22, 477\u2013505 (2007).","journal-title":"Stat. Sci."},{"key":"13015_CR11","unstructured":"Freund, Y. & Schapire, R. Experiments with a new boosting algorithm. In Machine Learning: Proceedings of the Thirteenth International Conference 148\u2013156 (Morgan Kauffman, 1996)."},{"key":"13015_CR12","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1214\/aos\/1016218223","volume":"28","author":"J Friedman","year":"2000","unstructured":"Friedman, J., Hastie, T. & Tibshirani, R. Additive logistic regression: A statistical view of boosting (with discussion). Ann. Stat. 28, 337\u2013407 (2000).","journal-title":"Ann. Stat."},{"issue":"4","key":"13015_CR13","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1037\/1082-989X.9.4.403","volume":"9","author":"DF McCaffrey","year":"2004","unstructured":"McCaffrey, D. F., Ridgeway, G. & Morral, A. R. Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychol. Methods 9(4), 403\u2013425 (2004).","journal-title":"Psychol. Methods"},{"key":"13015_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning","author":"T Hastie","year":"2009","unstructured":"Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning 2nd edn. (Springer, 2009).","edition":"2"},{"key":"13015_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19425-7","volume-title":"Regression Modeling Strategies","author":"FE Harrell","year":"2015","unstructured":"Harrell, F. E. Regression Modeling Strategies 2nd edn. (Springer-Verlag, 2015).","edition":"2"},{"issue":"8","key":"13015_CR16","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1016\/j.cjca.2021.02.020","volume":"37","author":"SM Cho","year":"2021","unstructured":"Cho, S. M. et al. Machine learning compared with conventional statistical models for predicting myocardial infarction readmission and mortality: A systematic review. Can. J. Cardiol. 37(8), 1207\u20131214 (2021).","journal-title":"Can. J. Cardiol."},{"issue":"4","key":"13015_CR17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0061562","volume":"8","author":"AL Boulesteix","year":"2013","unstructured":"Boulesteix, A. L., Lauer, S. & Eugster, M. J. A plea for neutral comparison studies in computational sciences. PLoS ONE 8(4), e61562 (2013).","journal-title":"PLoS ONE"},{"key":"13015_CR18","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13040-017-0155-3","volume":"10","author":"D Chicco","year":"2017","unstructured":"Chicco, D. Ten quick tips for machine learning in computational biology. BioData Min. 10, 35 (2017).","journal-title":"BioData Min."},{"key":"13015_CR19","volume-title":"Introduction to Neural Networks with Java","author":"J Heaton","year":"2008","unstructured":"Heaton, J. Introduction to Neural Networks with Java 2nd edn. (Heaton Research Inc, 2008).","edition":"2"},{"key":"13015_CR20","volume-title":"Statistical Inference","author":"G Casella","year":"1990","unstructured":"Casella, G., Berger, R. L. & Inference, S. Statistical Inference (Duxbury Press, 1990)."},{"key":"13015_CR21","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/637635","volume":"2014","author":"HF Golino","year":"2014","unstructured":"Golino, H. F. et al. Predicting increased blood pressure using machine learning. J. Obes. 2014, 637635 (2014).","journal-title":"J. Obes."},{"issue":"10","key":"13015_CR22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0240370","volume":"15","author":"LA AlKaabi","year":"2020","unstructured":"AlKaabi, L. A. et al. Predicting hypertension using machine learning: Findings from Qatar Biobank Study. PLoS ONE 15(10), e0240370 (2020).","journal-title":"PLoS ONE"},{"key":"13015_CR23","doi-asserted-by":"crossref","unstructured":"Wu, T. H., Pang, G. K. & Kwong, E.W. Predicting systolic blood pressure using machine learning. In 7th International Conference on Information and Automation for Sustainability 1\u20136 (2014).","DOI":"10.1109\/ICIAFS.2014.7069529"},{"issue":"1","key":"13015_CR24","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s12859-019-2667-y","volume":"20","author":"B Zhang","year":"2019","unstructured":"Zhang, B. et al. Predicting blood pressure from physiological index data using the SVR algorithm. BMC Bioinform. 20(1), 109 (2019).","journal-title":"BMC Bioinform."},{"issue":"6","key":"13015_CR25","doi-asserted-by":"publisher","first-page":"515","DOI":"10.7326\/0003-4819-130-6-199903160-00016","volume":"130","author":"AC Justice","year":"1999","unstructured":"Justice, A. C., Covinsky, K. E. & Berlin, J. A. Assessing the generalizability of prognostic information. Ann. Intern. Med. 130(6), 515\u2013524 (1999).","journal-title":"Ann. Intern. Med."},{"key":"13015_CR26","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1186\/1471-2288-14-137","volume":"14","author":"T van der Ploeg","year":"2014","unstructured":"van der Ploeg, T., Austin, P. C. & Steyerberg, E. W. Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints. BMC Med. Res. Methodol. 14, 137 (2014).","journal-title":"BMC Med. Res. Methodol."},{"issue":"3","key":"13015_CR27","first-page":"9","volume":"1","author":"K Kirasich","year":"2018","unstructured":"Kirasich, K., Smith, T. & Sadler, B. Random Forest vs Logistic Regression: Binary classification for heterogeneous datasets. SMU Data Sci. Rev. 1(3), 9 (2018).","journal-title":"SMU Data Sci. Rev."},{"key":"13015_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.simpat.2015.03.003","volume":"55","author":"T Vafeiadas","year":"2015","unstructured":"Vafeiadas, T. et al. A comparison of machine learning techniques for customer churn prediction. Simul. Model. Pract. Theory 55, 1\u20139 (2015).","journal-title":"Simul. Model. Pract. Theory"},{"issue":"12","key":"13015_CR29","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1093\/jamia\/ocz130","volume":"26","author":"B Van Calster","year":"2019","unstructured":"Van Calster, B. et al. Predictive analytics in health care: How can we know it works?. J. Am. Med. Inform. Assoc. 26(12), 1651\u20131654 (2019).","journal-title":"J. Am. Med. Inform. Assoc."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-13015-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-13015-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-13015-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T03:59:57Z","timestamp":1669348797000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-13015-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,3]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["13015"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-13015-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,3]]},"assertion":[{"value":"23 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"9312"}}