{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:00:46Z","timestamp":1785416446321,"version":"3.56.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T00:00:00Z","timestamp":1601596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T00:00:00Z","timestamp":1601596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["K23 HL127296"],"award-info":[{"award-number":["K23 HL127296"]}],"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":["R01 HL146824"],"award-info":[{"award-number":["R01 HL146824"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>With cardiovascular disease increasing, substantial research has focused on the development of prediction tools. We compare deep learning and machine learning models to a baseline logistic regression using only \u2018known\u2019 risk factors in predicting incident myocardial infarction (MI) from harmonized EHR data.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>Large-scale case-control study with outcome of 6-month incident MI, conducted using the top 800, from an initial 52\u2009k procedures, diagnoses, and medications within the UCHealth system, harmonized to the Observational Medical Outcomes Partnership common data model, performed on 2.27 million patients. We compared several over- and under- sampling techniques to address the imbalance in the dataset. We compared regularized logistics regression, random forest, boosted gradient machines, and shallow and deep neural networks. A baseline model for comparison was a logistic regression using a limited set of \u2018known\u2019 risk factors for MI. Hyper-parameters were identified using 10-fold cross-validation.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>Twenty thousand Five hundred and ninety-one patients were diagnosed with MI compared with 2.25 million who did not. A deep neural network with random undersampling provided superior classification compared with other methods. However, the benefit of the deep neural network was only moderate, showing an F1 Score of 0.092 and AUC of 0.835, compared to a logistic regression model using only \u2018known\u2019 risk factors. Calibration for all models was poor despite adequate discrimination, due to overfitting from low frequency of the event of interest.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Conclusions<\/jats:title>\n<jats:p>Our study suggests that DNN may not offer substantial benefit when trained on harmonized data, compared to traditional methods using established risk factors for MI.<\/jats:p>\n<\/jats:sec>","DOI":"10.1186\/s12911-020-01268-x","type":"journal-article","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T14:02:56Z","timestamp":1601647376000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data"],"prefix":"10.1186","volume":"20","author":[{"given":"Divneet","family":"Mandair","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Premanand","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Simon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn L.","family":"Colborn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6708-1648","authenticated-orcid":false,"given":"Michael A.","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,2]]},"reference":[{"key":"1268_CR1","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1001\/jamacardio.2018.0385","volume":"3","author":"Global Burden of Cardiovascular Diseases Collaboration","year":"2018","unstructured":"Global Burden of Cardiovascular Diseases Collaboration, et al. The Burden of Cardiovascular Diseases Among US States, 1990\u20132016. JAMA Cardiol. 2018;3:375\u201389.","journal-title":"JAMA Cardiol"},{"key":"1268_CR2","doi-asserted-by":"publisher","first-page":"e181079","DOI":"10.1001\/jamanetworkopen.2018.1079","volume":"1","author":"Y Wang","year":"2018","unstructured":"Wang Y, et al. Risk factors associated with major cardiovascular events 1 year after acute myocardial infarction. JAMA Netw Open. 2018;1:e181079.","journal-title":"JAMA Netw Open"},{"key":"1268_CR3","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1001\/archinternmed.2010.88","volume":"170","author":"RW Yeh","year":"2010","unstructured":"Yeh RW, Go AS. Rethinking the epidemiology of acute myocardial infarction: challenges and opportunities. Arch Intern Med. 2010;170:759\u201364.","journal-title":"Arch Intern Med"},{"key":"1268_CR4","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/1472-6947-14-75","volume":"14","author":"N Liu","year":"2014","unstructured":"Liu N, et al. Prediction of adverse cardiac events in emergency department patients with chest pain using machine learning for variable selection. BMC Med Inform Decis Mak. 2014;14:75.","journal-title":"BMC Med Inform Decis Mak."},{"key":"1268_CR5","doi-asserted-by":"publisher","first-page":"e0202344","DOI":"10.1371\/journal.pone.0202344","volume":"13","author":"AJ Steele","year":"2018","unstructured":"Steele AJ, Denaxas SC, Shah AD, Hemingway H, Luscombe NM. Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease. PLoS One. 2018;13:e0202344.","journal-title":"PLoS One"},{"key":"1268_CR6","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1109\/JBHI.2014.2330898","volume":"19","author":"D Tay","year":"2015","unstructured":"Tay D, Poh CL, Van Reeth E, Kitney RI. The effect of sample age and prediction resolution on myocardial infarction risk prediction. IEEE J Biomed Health Inform. 2015;19:1178\u201385.","journal-title":"IEEE J Biomed Health Inform"},{"key":"1268_CR7","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1002\/bimj.201100251","volume":"54","author":"PC Austin","year":"2012","unstructured":"Austin PC, Lee DS, Steyerberg EW, Tu JV. Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods? Biom J. 2012;54:657\u201373.","journal-title":"Biom J"},{"key":"1268_CR8","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.hrtlng.2017.09.003","volume":"46","author":"H Mansoor","year":"2017","unstructured":"Mansoor H, Elgendy IY, Segal R, Bavry AA, Bian J. Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction: a machine learning approach. Heart Lung. 2017;46:405\u201311.","journal-title":"Heart Lung"},{"key":"1268_CR9","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.ijcard.2017.05.067","volume":"246","author":"R Shouval","year":"2017","unstructured":"Shouval R, et al. Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: an acute coronary syndrome Israeli survey data mining study. Int J Cardiol. 2017;246:7\u201313.","journal-title":"Int J Cardiol"},{"key":"1268_CR10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s12911-017-0500-y","volume":"17","author":"J Wallert","year":"2017","unstructured":"Wallert J, Tomasoni M, Madison G, Held C. Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data. BMC Med Inform Decis Mak. 2017;17:99.","journal-title":"BMC Med Inform Decis Mak"},{"key":"1268_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436\u201344.","journal-title":"Nature"},{"key":"1268_CR12","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1126\/science.aam6960","volume":"356","author":"M Morav\u010d\u00edk","year":"2017","unstructured":"Morav\u010d\u00edk M, et al. DeepStack: expert-level artificial intelligence in heads-up no-limit poker. Science. 2017;356:508\u201313.","journal-title":"Science"},{"key":"1268_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.media.2016.07.007","volume":"35","author":"T Kooi","year":"2017","unstructured":"Kooi T, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal. 2017;35:303\u201312.","journal-title":"Med Image Anal"},{"key":"1268_CR14","first-page":"736","volume":"107","author":"X Song","year":"2004","unstructured":"Song X, Mitnitski A, Cox J, Rockwood K. Comparison of machine learning techniques with classical statistical models in predicting health outcomes. Stud Health Technol Inform. 2004;107:736\u201340.","journal-title":"Stud Health Technol Inform."},{"key":"1268_CR15","first-page":"273","volume":"264","author":"SN Payrovnaziri","year":"2019","unstructured":"Payrovnaziri SN, Barrett LA, Bis D, Bian J, He Z. Enhancing prediction models for one-year mortality in patients with acute myocardial infarction and post myocardial infarction syndrome. Stud Health Technol Inform. 2019;264:273\u20137.","journal-title":"Stud Health Technol Inform"},{"key":"1268_CR16","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1146\/annurev-publhealth-032315-021353","volume":"37","author":"JA Casey","year":"2016","unstructured":"Casey JA, Schwartz BS, Stewart WF, Adler NE. Using electronic health Records for Population Health Research: a review of methods and applications. Annu Rev Public Health. 2016;37:61\u201381.","journal-title":"Annu Rev Public Health"},{"key":"1268_CR17","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.jbi.2015.03.011","volume":"55","author":"Y Chen","year":"2015","unstructured":"Chen Y, et al. Building bridges across electronic health record systems through inferred phenotypic topics. J Biomed Inform. 2015;55:82\u201393.","journal-title":"J Biomed Inform"},{"key":"1268_CR18","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.9455","volume":"6","author":"Y Huang","year":"2018","unstructured":"Huang Y, et al. Privacy-preserving predictive modeling: harmonization of contextual Embeddings from different sources. JMIR Med Inform. 2018;6:e33.","journal-title":"JMIR Med Inform"},{"key":"1268_CR19","first-page":"407","volume":"2019","author":"LA Barrett","year":"2019","unstructured":"Barrett LA, Payrovnaziri SN, Bian J, He Z. Building computational models to predict one-year mortality in ICU patients with acute myocardial infarction and post myocardial infarction syndrome. AMIA Jt Summits Transl Sci Proc. 2019;2019:407\u201316.","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"1268_CR20","doi-asserted-by":"publisher","unstructured":"Sherazi SWA, Jeong YJ, Jae MH, Bae J-W, Lee JY. A machine learning-based 1-year mortality prediction model after hospital discharge for clinical patients with acute coronary syndrome. Health Informatics J. 2019:1460458219871780. https:\/\/doi.org\/10.1177\/1460458219871780.","DOI":"10.1177\/1460458219871780"},{"key":"1268_CR21","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/s12911-019-0754-7","volume":"19","author":"D Hu","year":"2019","unstructured":"Hu D, et al. Evidential MACE prediction of acute coronary syndrome using electronic health records. BMC Med Inform Decis Mak. 2019;19:61.","journal-title":"BMC Med Inform Decis Mak."},{"key":"1268_CR22","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1136\/heartjnl-2015-308850","volume":"102","author":"M Asaria","year":"2016","unstructured":"Asaria M, et al. Using electronic health records to predict costs and outcomes in stable coronary artery disease. Heart. 2016;102:755\u201362.","journal-title":"Heart"},{"key":"1268_CR23","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1609\/aimag.v33i4.2438","volume":"33","author":"JC Weiss","year":"2012","unstructured":"Weiss JC, Natarajan S, Peissig PL, McCarty CA, Page D. Machine learning for personalized medicine: predicting primary myocardial infarction from electronic health records. AI Mag. 2012;33:33.","journal-title":"AI Mag"},{"key":"1268_CR24","first-page":"887","volume":"245","author":"G Jiang","year":"2017","unstructured":"Jiang G, Kiefer RC, Sharma DK, Prud\u2019hommeaux E, Solbrig HR. A consensus-based approach for harmonizing the OHDSI common data model with HL7 FHIR. Stud Health Technol Inform. 2017;245:887\u201391.","journal-title":"Stud Health Technol Inform."},{"key":"1268_CR25","doi-asserted-by":"publisher","first-page":"65","DOI":"10.3414\/ME13-02-0019","volume":"54","author":"G Jiang","year":"2015","unstructured":"Jiang G, et al. Harmonization of detailed clinical models with clinical study data standards. Methods Inf Med. 2015;54:65\u201374.","journal-title":"Methods Inf Med"},{"key":"1268_CR26","first-page":"1110","volume":"2","author":"R Makadia","year":"2014","unstructured":"Makadia R, Ryan PB. Transforming the Premier Perspective Hospital Database into the Observational Medical Outcomes Partnership (OMOP) Common Data Model. EGEMS (Washington, DC). 2014;2:1110.","journal-title":"EGEMS (Washington, DC)"},{"key":"1268_CR27","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","volume":"14","author":"R Blagus","year":"2013","unstructured":"Blagus R, Lusa L. SMOTE for high-dimensional class-imbalanced data. BMC Bioinform. 2013;14:106.","journal-title":"BMC Bioinform"},{"key":"1268_CR28","first-page":"119","volume":"52","author":"A Agresti","year":"1998","unstructured":"Agresti A, Coull BA. Approximate is better than \u2018exact\u2019 for interval estimation of binomial proportions. Am Stat. 1998;52:119\u201326.","journal-title":"Am Stat"},{"key":"1268_CR29","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10278-009-9237-1","volume":"23","author":"P Lakhani","year":"2010","unstructured":"Lakhani P, Langlotz CP. Automated detection of radiology reports that document non-routine communication of critical or significant results. J Digit Imaging. 2010;23:647\u201357.","journal-title":"J Digit Imaging"},{"key":"1268_CR30","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12872-017-0482-9","volume":"17","author":"S Johansson","year":"2017","unstructured":"Johansson S, Rosengren A, Young K, et al. Mortality and morbidity trends after the first year in survivors of acute myocardial infarction: a systematic review. BMC Cardiovasc Disord. 2017;17:53 https:\/\/doi.org\/10.1186\/s12872-017-0482-9.","journal-title":"BMC Cardiovasc Disord"},{"key":"1268_CR31","first-page":"2341","volume":"2012","author":"JC Weiss","year":"2012","unstructured":"Weiss JC, Page D, Peissig PL, Natarajan S, McCarty C. Statistical relational learning to predict primary myocardial infarction from electronic health records. Proc Innov Appl Artif Intell Conf. 2012;2012:2341\u20137.","journal-title":"Proc Innov Appl Artif Intell Conf"},{"key":"1268_CR32","doi-asserted-by":"publisher","first-page":"123","DOI":"10.3389\/fphys.2019.00123","volume":"10","author":"S Xue","year":"2019","unstructured":"Xue S, et al. Circulating MiR-17-5p, MiR-126-5p and MiR-145-3p are novel biomarkers for diagnosis of acute myocardial infarction. Front Physiol. 2019;10:123.","journal-title":"Front Physiol"},{"key":"1268_CR33","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1002\/clc.22146","volume":"36","author":"DS Cross","year":"2013","unstructured":"Cross DS, McCarty CA, Steinhubl SR, Carey DJ, Erlich PM. Development of a multi-institutional cohort to facilitate cardiovascular disease biomarker validation using existing biorepository samples linked to electronic health records. Clin Cardiol. 2013;36:486\u201391.","journal-title":"Clin Cardiol"},{"key":"1268_CR34","doi-asserted-by":"publisher","unstructured":"Kusunose K, et al. A deep learning approach for assessment of Regional Wall motion abnormality from echocardiographic images. JACC Cardiovasc Imaging. 2019. https:\/\/doi.org\/10.1016\/j.jcmg.2019.02.024.","DOI":"10.1016\/j.jcmg.2019.02.024"},{"key":"1268_CR35","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.jacep.2018.12.005","volume":"5","author":"AFA Androulakis","year":"2019","unstructured":"Androulakis AFA, et al. Entropy as a novel measure of myocardial tissue heterogeneity for prediction of ventricular arrhythmias and mortality in post-infarct patients. JACC Clin Electrophysiol. 2019;5:480\u20139.","journal-title":"JACC Clin Electrophysiol"},{"key":"1268_CR36","doi-asserted-by":"publisher","unstructured":"Zadrozny, B. & Elkan, C. Transforming Classifier Scores into Accurate Multiclass Probability Estimates. Proceed Eighth ACM SIGKDD Int Conf Knowl Discov Data Mining 694\u2013699 (ACM, 2002). https:\/\/doi.org\/10.1145\/775047.775151.","DOI":"10.1145\/775047.775151"},{"key":"1268_CR37","unstructured":"Niculescu-Mizil, A. & Caruana, R. Obtaining Calibrated Probabilities from Boosting."},{"key":"1268_CR38","doi-asserted-by":"publisher","unstructured":"Gibson WJ, et al. Machine learning versus traditional risk stratification methods in acute coronary syndrome: a pooled randomized clinical trial analysis. J Thromb Thrombolysis. 2019. https:\/\/doi.org\/10.1007\/s11239-019-01940-8.","DOI":"10.1007\/s11239-019-01940-8"},{"key":"1268_CR39","doi-asserted-by":"publisher","unstructured":"Tiwari, Premanand, Colborn, Katie, Smith, Derek, Xing, Fuyong, Gosh, Debashis, Rosenberg Michael. Development of a Prediction Model for Incident Atrial Fibrillation using Machine Learning Applied to Harmonized Electronic Health Record Data. BioRxiv [Preprint]. January 18, 2019. Available from: https:\/\/doi.org\/10.1101\/520866.","DOI":"10.1101\/520866"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01268-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-020-01268-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01268-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T23:59:30Z","timestamp":1633132770000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-01268-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,2]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1268"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-01268-x","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,2]]},"assertion":[{"value":"7 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable. Colorado\u2019s IRB has declared this study not human subjects research (exempt) due to use of retrospective data and no human interaction with patients.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"252"}}