{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T18:15:35Z","timestamp":1774635335080,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institutes of Health\/National Library of Medicine","award":["R56LM013365"],"award-info":[{"award-number":["R56LM013365"]}]},{"name":"Gordon and Betty Moore Foundation through Grant","award":["GBMF8040"],"award-info":[{"award-number":["GBMF8040"]}]},{"name":"Stanford Clinical Excellence Research Center"},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["5T15LM007033"],"award-info":[{"award-number":["5T15LM007033"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Endocrinology and Metabolism Training","award":["5T32DK007217-45"],"award-info":[{"award-number":["5T32DK007217-45"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>The study sought to determine whether machine learning can predict initial inpatient total daily dose (TDD) of insulin from electronic health records more accurately than existing guideline-based dosing recommendations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Using electronic health records from a tertiary academic center between 2008 and 2020 of 16,848 inpatients receiving subcutaneous insulin who achieved target blood glucose control of 100-180 mg\/dL on a calendar day, we trained an ensemble machine learning algorithm consisting of regularized regression, random forest, and gradient boosted tree models for 2-stage TDD prediction. We evaluated the ability to predict patients requiring more than 6 units TDD and their point-value TDDs to achieve target glucose control.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The method achieves an area under the receiver-operating characteristic curve of 0.85 (95% confidence interval [CI], 0.84-0.87) and area under the precision-recall curve of 0.65 (95% CI, 0.64-0.67) for classifying patients who require more than 6 units TDD. For patients requiring more than 6 units TDD, the mean absolute percent error in dose prediction based on standard clinical calculators using patient weight is in the range of 136%-329%, while the regression model based on weight improves to 60% (95% CI, 57%-63%), and the full ensemble model further improves to 51% (95% CI, 48%-54%).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Owingto the narrow therapeutic window and wide individual variability, insulin dosing requires adaptive and predictive approaches that can be supported through data-driven analytic tools.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Machine learning approaches based on readily available electronic medical records can discriminate which inpatients will require more than 6 units TDD and estimate individual doses more accurately than standard guidelines and practices.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocab099","type":"journal-article","created":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T14:45:34Z","timestamp":1620398734000},"page":"2212-2219","source":"Crossref","is-referenced-by-count":49,"title":["Machine learning for initial insulin estimation in hospitalized patients"],"prefix":"10.1093","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7149-849X","authenticated-orcid":false,"given":"Minh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, California, USA"}]},{"given":"Ivana","family":"Jankovic","sequence":"additional","affiliation":[{"name":"Division of Endocrinology, Department of Medicine, Stanford University, School of Medicine, Stanford, California, USA"}]},{"given":"Laurynas","family":"Kalesinskas","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, California, USA"}]},{"given":"Michael","family":"Baiocchi","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Population Health, Stanford University, Stanford, California, USA"}]},{"given":"Jonathan H","family":"Chen","sequence":"additional","affiliation":[{"name":"Stanford Center for Biomedical Informatics Research, Department of Medicine, Stanford University, Stanford, California, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"issue":"1","key":"2021091817524145400_ocab099-B1","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1210\/jc.2011-2098","article-title":"Management of hyperglycemia in hospitalized patients in non-critical care setting: an Endocrine Society clinical practice guideline","volume":"97","author":"Umpierrez","year":"2012","journal-title":"J Clin Endocrinol Metab"},{"issue":"4","key":"2021091817524145400_ocab099-B2","doi-asserted-by":"crossref","first-page":"509","DOI":"10.2337\/dc16-0989","article-title":"Management of inpatient hyperglycemia and diabetes in older adults","volume":"40","author":"Umpierrez","year":"2017","journal-title":"Diabetes Care"},{"issue":"12","key":"2021091817524145400_ocab099-B3","doi-asserted-by":"crossref","first-page":"3001","DOI":"10.1097\/CCM.0b013e3181b083f7","article-title":"Hyperglycemia-related mortality in critically ill patients varies with admission diagnosis","volume":"37","author":"Falciglia","year":"2009","journal-title":"Crit Care Med"},{"issue":"Supplement 1","key":"2021091817524145400_ocab099-B4","doi-asserted-by":"crossref","DOI":"10.2337\/db20-1235-P","article-title":"1235-P: Identifying trends in the management of inpatient diabetes at a University Teaching Hospital, 2008-2018","volume":"69","author":"Jankovic","year":"2020","journal-title":"Diabetes"},{"issue":"Supplement 1","key":"2021091817524145400_ocab099-B5","doi-asserted-by":"crossref","first-page":"S193","DOI":"10.2337\/dc20-S015","article-title":"15. Diabetes care in the hospital: standards of medical care in diabetes\u20142020","volume":"43","year":"2020","journal-title":"Diabetes Care"},{"key":"2021091817524145400_ocab099-B6","author":"Inzucchi"},{"issue":"9","key":"2021091817524145400_ocab099-B7","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.2337\/dc07-0295","article-title":"Randomized study of basal-bolus insulin therapy in the inpatient management of patients with type 2 diabetes (RABBIT 2 Trial)","volume":"30","author":"Umpierrez","year":"2007","journal-title":"Diabetes Care"},{"issue":"10","key":"2021091817524145400_ocab099-B8","first-page":"648","article-title":"Glucose management in hospitalized patients","volume":"96","author":"Kodner","year":"2017","journal-title":"Am Fam Physician"},{"issue":"2","key":"2021091817524145400_ocab099-B9","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1080\/20009666.2019.1593782","article-title":"Retrospective study of inpatient diabetes management service, length of stay and 30-day readmission rate of patients with diabetes at a community hospital","volume":"9","author":"Mandel","year":"2019","journal-title":"J Community Hosp Intern Med Perspect"},{"issue":"3","key":"2021091817524145400_ocab099-B10","doi-asserted-by":"crossref","first-page":"512","DOI":"10.4158\/EP09319.CO","article-title":"State-of-the-art inpatient diabetes care: the evolution of an academic hospital","volume":"16","author":"Pietras","year":"2010","journal-title":"Endocr Pract"},{"issue":"1","key":"2021091817524145400_ocab099-B11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/s10111-012-0247-2","article-title":"Inpatient diabetes care: complexity, resilience and quality of care","volume":"16","author":"Ross","year":"2014","journal-title":"Cogn Tech Work"},{"issue":"9","key":"2021091817524145400_ocab099-B12","doi-asserted-by":"crossref","first-page":"621","DOI":"10.7326\/M16-1413","article-title":"Association between a virtual glucose management service and glycemic control in hospitalized adult patients: an observational study","volume":"166","author":"Rushakoff","year":"2017","journal-title":"Ann Intern Med"},{"issue":"5","key":"2021091817524145400_ocab099-B13","doi-asserted-by":"crossref","first-page":"e10775","DOI":"10.2196\/10775","article-title":"Artificial intelligence for diabetes management and decision support: literature review","volume":"20","author":"Contreras","year":"2018","journal-title":"J Med Internet Res"},{"key":"2021091817524145400_ocab099-B14","first-page":"874","article-title":"Predicting nocturnal hypoglycemia from continuous glucose monitoring data with extended prediction horizon","volume":"2019","author":"Vu","year":"2019","journal-title":"AMIA Annu Symp Proc"},{"issue":"3","key":"2021091817524145400_ocab099-B15","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1007\/s41666-020-00068-2","article-title":"Dilated recurrent neural networks for glucose forecasting in type 1 diabetes","volume":"4","author":"Zhu","year":"2020","journal-title":"J Healthc Inform Res"},{"issue":"4","key":"2021091817524145400_ocab099-B16","doi-asserted-by":"crossref","first-page":"e1005232","DOI":"10.1371\/journal.pcbi.1005232","article-title":"Personalized glucose forecasting for type 2 diabetes using data assimilation","volume":"13","author":"Albers","year":"2017","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"2021091817524145400_ocab099-B17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/JBHI.2015.2464088","article-title":"An advanced bolus calculator for type 1 diabetes: system architecture and usability results","volume":"20","author":"Pesl","year":"2016","journal-title":"IEEE J Biomed Health Inform"},{"issue":"4","key":"2021091817524145400_ocab099-B18","doi-asserted-by":"crossref","first-page":"e0121569","DOI":"10.1371\/journal.pone.0121569","article-title":"Applying a novel combination of techniques to develop a predictive model for diabetes complications","volume":"10","author":"Sangi","year":"2015","journal-title":"PloS One"},{"key":"2021091817524145400_ocab099-B19","first-page":"470","article-title":"Hierarchical Bayesian logistic Regression to forecast metabolic control in type 2 DM patients","volume":"2016","author":"Dagliati","year":"2016","journal-title":"AMIA Annu Symp Proc"},{"issue":"1","key":"2021091817524145400_ocab099-B20","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1177\/1932296818777524","article-title":"In silico assessment of literature insulin bolus calculation methods accounting for glucose rate of change","volume":"13","author":"Cappon","year":"2019","journal-title":"J Diabetes Sci Technol"},{"issue":"2","key":"2021091817524145400_ocab099-B21","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1177\/1932296818759558","article-title":"A neural-network-based approach to personalize insulin bolus calculation using continuous glucose monitoring","volume":"12","author":"Cappon","year":"2018","journal-title":"J Diabetes Sci Technol"},{"issue":"1","key":"2021091817524145400_ocab099-B22","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/TBME.2020.3004031","article-title":"Machine-learning based model to improve insulin bolus calculation in type 1 diabetes therapy","volume":"68","author":"Noaro","year":"2021","journal-title":"IEEE Trans Biomed Eng"},{"key":"2021091817524145400_ocab099-B23","article-title":"Application of artificial intelligence techniques for the estimation of basal insulin in patients with type I diabetes","author":"Guzman G\u00f3mez","journal-title":"Int J Endocrinol"},{"key":"2021091817524145400_ocab099-B24","doi-asserted-by":"publisher","DOI":"10.1101\/2020.03.02.20029017,","article-title":"Predicting inpatient glucose levels and insulin dosing by machine learning on electronic health records","author":"Liu","journal-title":"medRxiv"},{"issue":"2","key":"2021091817524145400_ocab099-B25","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/JBHI.2019.2908488","article-title":"Convolutional recurrent neural networks for glucose prediction","volume":"24","author":"Li","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"2021091817524145400_ocab099-B26","article-title":"Predicting blood glucose with an LSTM and Bi-LSTM based deep neural network","author":"Sun","journal-title":"arXiv, doi:"},{"key":"2021091817524145400_ocab099-B27","first-page":"74","article-title":"A deep learning algorithm for personalized blood glucose prediction","author":"Zhu","year":"2018:","journal-title":"In: Proceedings of the 27th International Joint Conference on Artificial Intelligence;"},{"issue":"6","key":"2021091817524145400_ocab099-B28","doi-asserted-by":"crossref","DOI":"10.1002\/cnm.2833","article-title":"A review of personalized blood glucose prediction strategies for T1DM patients","volume":"33","author":"Oviedo","year":"2017","journal-title":"Int J Numer Method Biomed Eng"},{"key":"2021091817524145400_ocab099-B29","doi-asserted-by":"crossref","DOI":"10.3389\/fams.2017.00014","article-title":"A deep learning approach to diabetic blood glucose prediction","volume":"3","author":"Mhaskar","year":"2017","journal-title":"Front Appl Math Stat"},{"issue":"2","key":"2021091817524145400_ocab099-B30","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1109\/JBHI.2019.2931842","article-title":"GluNet: a deep learning framework for accurate glucose forecasting","volume":"24","author":"Li","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"2021091817524145400_ocab099-B31","doi-asserted-by":"crossref","first-page":"Article25","DOI":"10.2202\/1544-6115.1309","article-title":"Super learner","volume":"6","author":"van der Laan","year":"2007","journal-title":"Stat Appl Genet Mol Biol"},{"issue":"4","key":"2021091817524145400_ocab099-B32","doi-asserted-by":"crossref","first-page":"e025611","DOI":"10.1136\/bmjopen-2018-025611","article-title":"Uniformity in measuring adherence to reporting guidelines: the example of TRIPOD for assessing completeness of reporting of prediction model studies","volume":"9","author":"Heus","year":"2019","journal-title":"BMJ Open"},{"key":"2021091817524145400_ocab099-B33","author":"Inzucchi","year":"2011"},{"issue":"9","key":"2021091817524145400_ocab099-B34","first-page":"1121","article-title":"Glucose control in hospitalized patients","volume":"81","author":"Sawin","year":"2010","journal-title":"Am Fam Physician"},{"issue":"2","key":"2021091817524145400_ocab099-B35","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/0002-9343(77)90233-9","article-title":"Potency and duration of action of glucocorticoids. Effects of hydrocortisone, prednisone and dexamethasone on human pituitary-adrenal function","volume":"63","author":"Meikle","year":"1977","journal-title":"Am J Med"},{"key":"2021091817524145400_ocab099-B36","doi-asserted-by":"crossref","volume-title":"Oxford Handbook of Critical Care","author":"Singer","DOI":"10.1093\/med\/9780199235339.001.0001"},{"issue":"1","key":"2021091817524145400_ocab099-B37","doi-asserted-by":"crossref","first-page":"61","DOI":"10.2165\/00003088-200544010-00003","article-title":"Pharmacokinetics and pharmacodynamics of systemically administered glucocorticoids","volume":"44","author":"Czock","year":"2005","journal-title":"Clin Pharmacokinet"},{"key":"2021091817524145400_ocab099-B38","year":"2019"},{"issue":"3","key":"2021091817524145400_ocab099-B39","doi-asserted-by":"crossref","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC Plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"issue":"1","key":"2021091817524145400_ocab099-B40","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1177\/1932296816662047","article-title":"Significance and reliability of MARD for the accuracy of CGM systems","volume":"11","author":"Reiterer","year":"2017","journal-title":"J Diabetes Sci Technol"},{"key":"2021091817524145400_ocab099-B41","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"issue":"4","key":"2021091817524145400_ocab099-B42","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1093\/intqhc\/13.4.339","article-title":"High-alert\u2019 medications and patient safety","volume":"13","year":"2001","journal-title":"Int J Qual Health Care"},{"issue":"2","key":"2021091817524145400_ocab099-B43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11892-020-01374-0","article-title":"The financial impact of an inpatient diabetes management service","volume":"21","author":"Haque","year":"2021","journal-title":"Curr Diab Rep"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/10\/2212\/40408884\/ocab099.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/10\/2212\/40408884\/ocab099.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,18]],"date-time":"2021-09-18T17:54:16Z","timestamp":1631987656000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/10\/2212\/6324041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":43,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,7,19]]},"published-print":{"date-parts":[[2021,9,18]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab099","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10,1]]},"published":{"date-parts":[[2021,7,19]]}}}