{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:01:08Z","timestamp":1774422068464,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Cardiovascular disease (CVD) is the leading cause of death in the United States (US). Better cardiovascular health (CVH) is associated with CVD prevention. Predicting future CVH levels may help providers better manage patients\u2019 CVH. We hypothesized that CVH measures can be predicted based on previous measurements from longitudinal electronic health record (EHR) data.\n<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>The Guideline Advantage (TGA) dataset was used and contained EHR data from 70 outpatient clinics across the United States (US). We studied predictions of 5 CVH submetrics: smoking status (SMK), body mass index (BMI), blood pressure (BP), hemoglobin A1c (A1C), and low-density lipoprotein (LDL). We applied embedding techniques and long short-term memory (LSTM) networks \u2013 to predict future CVH category levels from all the previous CVH measurements of 216,445 unique patients for each CVH submetric.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The LSTM model performance was evaluated by the area under the receiver operator curve (AUROC): the micro-average AUROC was 0.99 for SMK prediction; 0.97 for BMI; 0.84 for BP; 0.91 for A1C; and 0.93 for LDL prediction. Model performance was not improved by using all 5 submetric measures compared with using single submetric measures.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>We suggest that future CVH levels can be predicted using previous CVH measurements for each submetric, which has implications for population cardiovascular health management. Predicting patients\u2019 future CVH levels might directly increase patient CVH health and thus quality of life, while also indirectly decreasing the burden and cost for clinical health system caused by CVD and cancers.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-020-01345-1","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T14:08:54Z","timestamp":1609942134000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Predicting cardiovascular health trajectories in time-series electronic health records with LSTM models"],"prefix":"10.1186","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-0920","authenticated-orcid":false,"given":"Aixia","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahmatollah","family":"Beheshti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosef M.","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"II","given":"James R.","family":"Langabeer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randi E.","family":"Foraker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,6]]},"reference":[{"issue":"3","key":"1345_CR1","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1177\/0898264316635590","volume":"29","author":"Y Jin","year":"2017","unstructured":"Jin Y, Tanaka T, Banduneli S, Takegawkar SA. Overall cardiovascular health is associated with all-cause and cardiovascular disease mortality among older community-dwelling men and women. J Aging Health. 2017;29(3):437\u201353.","journal-title":"J Aging Health"},{"key":"1345_CR2","volume-title":"Life\u2019s simple 7","author":"AHA","year":"2013","unstructured":"AHA. In: Association AH, editor. Life\u2019s simple 7; 2013. http:\/\/mylifecheck.heart.org\/."},{"issue":"12","key":"1345_CR3","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1001\/jama.2012.339","volume":"307","author":"Q Yang","year":"2012","unstructured":"Yang Q, Cogswell ME, Flanders W, et al. TRends in cardiovascular health metrics and associations with all-cause and cvd mortality among us adults. JAMA. 2012;307(12):1273\u201383. https:\/\/doi.org\/10.1001\/jama.2012.339.","journal-title":"JAMA."},{"issue":"10","key":"1345_CR4","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1016\/j.mayocp.2012.07.015","volume":"87","author":"EG Artero","year":"2012","unstructured":"Artero EG, Espa\u00f1a-Romero V, Lee D, et al. Ideal cardiovascular health and mortality: aerobics center longitudinal study. Mayo Clin Proc. 2012;87(10):944\u201352. https:\/\/doi.org\/10.1016\/j.mayocp.2012.07.015.","journal-title":"Mayo Clin Proc"},{"key":"1345_CR5","doi-asserted-by":"publisher","unstructured":"Folsom AR, Yatsuya H, Nettleton JA, Lutsey PL, Cushman M, Rosamond WD. Community prevalence of ideal cardiovascular health, by the American heart association definition, and relationship with cardiovascular disease incidence. J Am Coll Cardiol. 2011. https:\/\/doi.org\/10.1016\/j.jacc.2010.11.041.","DOI":"10.1016\/j.jacc.2010.11.041"},{"issue":"2","key":"1345_CR6","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.amepre.2015.07.039","volume":"50","author":"RE Foraker","year":"2016","unstructured":"Foraker RE, Abdel-Rasoul M, Kuller LH, et al. Cardiovascular health and incident cardiovascular disease and cancer: The Women\u2019s Health Initiative. Am J Prev Med. 2016;50(2):236\u201340.","journal-title":"Am J Prev Med"},{"key":"1345_CR7","doi-asserted-by":"publisher","unstructured":"Haby MM, Markwick A, Peeters A, Shaw J, Vos T. Future predictions of body mass index and overweight prevalence in Australia, 20052025. Health Promot Int. 2012. https:\/\/doi.org\/10.1093\/heapro\/dar036.","DOI":"10.1093\/heapro\/dar036"},{"key":"1345_CR8","doi-asserted-by":"publisher","unstructured":"Mead E, Batterham AM, Atkinson G, Ells LJ. Predicting future weight status from measurements made in early childhood: a novel longitudinal approach applied to millennium cohort study data. Nutr Diabetes. 2016. https:\/\/doi.org\/10.1038\/nutd.2016.3.","DOI":"10.1038\/nutd.2016.3"},{"key":"1345_CR9","doi-asserted-by":"publisher","unstructured":"Solomon JW, Nielsen RD. Predicting changes in systolic blood pressure using longitudinal patient records. J Biomed Inform. 2015. https:\/\/doi.org\/10.1016\/j.jbi.2015.06.024.","DOI":"10.1016\/j.jbi.2015.06.024"},{"key":"1345_CR10","doi-asserted-by":"publisher","unstructured":"Golino HF, Amaral LS de B, Duarte SFP, et al. Predicting increased blood pressure using machine learning. J Obes. 2014. https:\/\/doi.org\/10.1155\/2014\/637635.","DOI":"10.1155\/2014\/637635"},{"key":"1345_CR11","doi-asserted-by":"publisher","unstructured":"Koga M, Murai J, Saito H, Kasayama S. Prediction of near-future glycated hemoglobin levels using glycated albumin levels before and after treatment for diabetes. J Diabetes Investig. 2011. https:\/\/doi.org\/10.1111\/j.2040-1124.2011.00107.x.","DOI":"10.1111\/j.2040-1124.2011.00107.x"},{"issue":"2","key":"1345_CR12","doi-asserted-by":"publisher","first-page":"203","DOI":"10.2307\/1403509","volume":"62","author":"AM Garber","year":"1994","unstructured":"Garber AM, Olshen RA, Zhang H, Venkatraman ES. Predicting high-risk cholesterol levels. Int Stat Rev. 1994;62(2):203\u201328.","journal-title":"Int Stat Rev"},{"key":"1345_CR13","doi-asserted-by":"publisher","unstructured":"Mendel JR, Berg CJ, Windle RC, Windle M. Predicting young adulthood smoking among adolescent smokers and nonsmokers. Am J Health Behav. 2012. https:\/\/doi.org\/10.5993\/AJHB.36.4.11.","DOI":"10.5993\/AJHB.36.4.11"},{"key":"1345_CR14","doi-asserted-by":"publisher","DOI":"10.1533\/9780857099440.59","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning; 2016. https:\/\/doi.org\/10.1533\/9780857099440.59."},{"issue":"1","key":"1345_CR15","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar A, Oren E, Chen K, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1(1):18. https:\/\/doi.org\/10.1038\/s41746-018-0029-1.","journal-title":"NPJ Digit Med"},{"key":"1345_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"Hochreiter S& S","year":"1997","unstructured":"Hochreiter S& S. Long short-term memory. Neural Comput. 1997;9:1735\u201380.","journal-title":"Neural Comput"},{"key":"1345_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2018.8406199","volume-title":"IEEE\/IFIP network operations and management symposium: cognitive management in a cyber world, NOMS 2018","author":"A Azzouni","year":"2018","unstructured":"Azzouni A, Pujolle G. NeuTM: a neural network-based framework for traffic matrix prediction in SDN. In: IEEE\/IFIP network operations and management symposium: cognitive management in a cyber world, NOMS 2018; 2018. https:\/\/doi.org\/10.1109\/NOMS.2018.8406199."},{"issue":"4","key":"1345_CR18","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1161\/circulationaha.109.192703","volume":"121","author":"DM Lloyd-Jones","year":"2010","unstructured":"Lloyd-Jones DM, Hong Y, Labarthe D, et al. Defining and setting national goals for cardiovascular health promotion and disease reduction. Circulation. 2010;121(4):586\u2013613. https:\/\/doi.org\/10.1161\/circulationaha.109.192703.","journal-title":"Circulation."},{"key":"1345_CR19","doi-asserted-by":"publisher","unstructured":"Shickel B, Tighe PJ, Bihorac A, Rashidi P. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE J Biomed Heal Informatics. 2018. https:\/\/doi.org\/10.1109\/JBHI.2017.2767063.","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"1345_CR20","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein VI. Binary codes capable of correcting deletions, insertions, and reversals. Sov Phys Dokl. 1966;10:707\u201310 doi:citeulike-article-id:311174.","journal-title":"Sov Phys Dokl"},{"key":"1345_CR21","unstructured":"Kingma DP, Ba J. ADAM: a method for stochastic optimization. CoRR. 2015; abs\/1412.6."},{"key":"1345_CR22","unstructured":"Reimers N, Gurevych I. Optimal hyperparameters for deep LSTM-networks for sequence labeling tasks. arXiv. 2017; abs\/1707.0."},{"key":"1345_CR23","doi-asserted-by":"publisher","unstructured":"Wang YQ, Wang CF, Zhu L, Yuan H, Wu LX, Chen ZH. Ideal cardiovascular health and the subclinical impairments of cardiovascular diseases: a cross-sectional study in central South China. BMC Cardiovasc Disord. 2017. https:\/\/doi.org\/10.1186\/s12872-017-0697-9.","DOI":"10.1186\/s12872-017-0697-9"},{"key":"1345_CR24","doi-asserted-by":"publisher","unstructured":"Younus A, Aneni EC, Spatz ES, et al. A systematic review of the prevalence and outcomes of ideal cardiovascular health in US and Non-US Populations. Mayo Clin Proc. 2016. https:\/\/doi.org\/10.1016\/j.mayocp.2016.01.019.","DOI":"10.1016\/j.mayocp.2016.01.019"},{"key":"1345_CR25","doi-asserted-by":"publisher","unstructured":"Fang N, Jiang M, Fan Y. Ideal cardiovascular health metrics and risk of cardiovascular disease or mortality: a meta-analysis. Int J Cardiol. 2016. https:\/\/doi.org\/10.1016\/j.ijcard.2016.03.210.","DOI":"10.1016\/j.ijcard.2016.03.210"},{"key":"1345_CR26","doi-asserted-by":"publisher","unstructured":"Wang J, Shao B, Lin D, et al. Ideal cardiovascular health metrics associated with reductions in the risk of extracranial carotid artery stenosis: a population-based cohort study. Sci Rep. 2018. https:\/\/doi.org\/10.1038\/s41598-018-29754-3.","DOI":"10.1038\/s41598-018-29754-3"},{"key":"1345_CR27","doi-asserted-by":"publisher","unstructured":"Ogunmoroti O, Allen NB, Cushman M, et al. Association between life\u2019s simple 7 and noncardiovascular disease: the multi-ethnic study of atherosclerosis. J Am Heart Assoc. 2016. https:\/\/doi.org\/10.1161\/JAHA.116.003954.","DOI":"10.1161\/JAHA.116.003954"},{"issue":"3","key":"1345_CR28","doi-asserted-by":"publisher","first-page":"e004894","DOI":"10.1161\/JAHA.116.004894","volume":"6","author":"TS Polonsky","year":"2017","unstructured":"Polonsky TS, Ning H, Daviglus ML, et al. Association of cardiovascular health with subclinical disease and incident events: the multi-ethnic study of atherosclerosis. J Am Heart Assoc. 2017;6(3):e004894. https:\/\/doi.org\/10.1161\/JAHA.116.004894.","journal-title":"J Am Heart Assoc"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01345-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-020-01345-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01345-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T14:50:21Z","timestamp":1609944621000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-01345-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,6]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["1345"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-01345-1","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,6]]},"assertion":[{"value":"19 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The need for informed consent for this study was waived and approved by the Institutional Review Board at the Washington University School of Medicine in St. Louis. We obtained a written acknowledgement of proprietary rights and non-disclosure and data use agreement from the American Heart Association (The Washington University_NDA_DUA_CONTRACTID 158065_2019.04.26_K).","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":"There are no competing interests for A.G., R.B., Y.K., and J.L. R.F. is an editorial board member for the journal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5"}}