{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T10:35:45Z","timestamp":1777372545894,"version":"3.51.4"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NIH\/NIDDK","award":["5K08DK131286"],"award-info":[{"award-number":["5K08DK131286"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    This study introduces Glucose Level Understanding and Control Optimized for Safety and Efficacy (GLUCOSE), a distributional offline reinforcement learning algorithm for optimizing insulin dosing after cardiac surgery. Trained on 5228 patients, tested on 920, and externally validated on 649, GLUCOSE achieved a mean estimated reward of 0.0 [\u20130.07, 0.06] in internal testing and \u20130.63 [\u20130.74, \u20130.52] in external validation, outperforming clinician returns of \u20131.29 [\u20131.37, \u20131.20] and \u20131.02 [\u20131.16, \u20130.89]. In multi-phase human validation, GLUCOSE first showed a significantly lower mean absolute error (MAE) in insulin dosing, with 0.9 units MAE versus clinicians\u2019 1.97 units (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001) in internal testing and 1.90 versus 2.24 units (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009=\u20090.003) in external validation. The second and third phases found GLUCOSE\u2019s performance as comparable to or exceeding that of senior clinicians in MAE, safety, effectiveness, and acceptability. These findings suggest GLUCOSE as a robust tool for improving postoperative glucose management.\n                  <\/jats:p>","DOI":"10.1038\/s41746-025-01709-9","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T02:43:13Z","timestamp":1748313793000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A distributional reinforcement learning model for optimal glucose control after cardiac surgery"],"prefix":"10.1038","volume":"8","author":[{"given":"Jacob M.","family":"Desman","sequence":"first","affiliation":[]},{"given":"Zhang-Wei","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Moein","family":"Sabounchi","sequence":"additional","affiliation":[]},{"given":"Ashwin S.","family":"Sawant","sequence":"additional","affiliation":[]},{"given":"Jaskirat","family":"Gill","sequence":"additional","affiliation":[]},{"given":"Ana C.","family":"Costa","sequence":"additional","affiliation":[]},{"given":"Gagan","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Rajeev","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Arpeta","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Paul","family":"McCarthy","sequence":"additional","affiliation":[]},{"given":"Veena","family":"Nandwani","sequence":"additional","affiliation":[]},{"given":"Doug","family":"Powell","sequence":"additional","affiliation":[]},{"given":"Alexandra","family":"Carideo","sequence":"additional","affiliation":[]},{"given":"Donnie","family":"Goodwin","sequence":"additional","affiliation":[]},{"given":"Sanam","family":"Ahmed","sequence":"additional","affiliation":[]},{"given":"Umesh","family":"Gidwani","sequence":"additional","affiliation":[]},{"given":"Matthew A.","family":"Levin","sequence":"additional","affiliation":[]},{"given":"Robin","family":"Varghese","sequence":"additional","affiliation":[]},{"given":"Farzan","family":"Filsoufi","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Freeman","sequence":"additional","affiliation":[]},{"given":"Avniel","family":"Shetreat-Klein","sequence":"additional","affiliation":[]},{"given":"Alexander W.","family":"Charney","sequence":"additional","affiliation":[]},{"given":"Ira","family":"Hofer","sequence":"additional","affiliation":[]},{"given":"Lili","family":"Chan","sequence":"additional","affiliation":[]},{"given":"David","family":"Reich","sequence":"additional","affiliation":[]},{"given":"Patricia","family":"Kovatch","sequence":"additional","affiliation":[]},{"given":"Roopa","family":"Kohli-Seth","sequence":"additional","affiliation":[]},{"given":"Monica","family":"Kraft","sequence":"additional","affiliation":[]},{"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[]},{"given":"John A.","family":"Kellum","sequence":"additional","affiliation":[]},{"given":"Girish N.","family":"Nadkarni","sequence":"additional","affiliation":[]},{"given":"Ankit","family":"Sakhuja","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"1709_CR1","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1051\/ject\/200638168","volume":"38","author":"S Najmaii","year":"2006","unstructured":"Najmaii, S., Redford, D. & Larson, D. F. Hyperglycemia as an effect of cardiopulmonary bypass: intra-operative glucose management. J. Extra Corpor. Technol. 38, 168\u2013173 (2006).","journal-title":"J. Extra Corpor. Technol."},{"key":"1709_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.ecl.2017.10.005","volume":"47","author":"RJ Galindo","year":"2018","unstructured":"Galindo, R. J., Fayfman, M. & Umpierrez, G. E. Perioperative management of hyperglycemia and diabetes in cardiac surgery patients. Endocrinol. Metab. Clin. North Am. 47, 203\u2013222 (2018).","journal-title":"Endocrinol. Metab. Clin. North Am."},{"key":"1709_CR3","doi-asserted-by":"publisher","first-page":"e15911","DOI":"10.1097\/MD.0000000000015911","volume":"98","author":"V Moorthy","year":"2019","unstructured":"Moorthy, V., Sim, M. A., Liu, W., Chew, S. T. H. & Ti, L. K. Risk factors and impact of postoperative hyperglycemia in nondiabetic patients after cardiac surgery: A prospective study. Med. (Baltim.) 98, e15911 (2019).","journal-title":"Med. (Baltim.)"},{"key":"1709_CR4","doi-asserted-by":"publisher","first-page":"46","DOI":"10.4158\/EP161427.OR","volume":"23","author":"E Lowden","year":"2017","unstructured":"Lowden, E. et al. Evaluation of outcomes and complications in patients who experience Hypoglycemia after Cardiac Surgery. Endocr. Pract. 23, 46\u201355 (2017).","journal-title":"Endocr. Pract."},{"key":"1709_CR5","doi-asserted-by":"publisher","first-page":"408","DOI":"10.2337\/dc15-1817","volume":"39","author":"G Greco","year":"2016","unstructured":"Greco, G. et al. Diabetes and the association of postoperative hyperglycemia with clinical and economic outcomes in cardiac surgery. Diab Care 39, 408\u2013417 (2016).","journal-title":"Diab Care"},{"key":"1709_CR6","doi-asserted-by":"crossref","unstructured":"Ruan, J. et al. Association between hyperglycemia at ICU admission and postoperative acute kidney injury in patients undergoing cardiac surgery: Analysis of the MIMIC-IV database. J. Intensive Med. 4, 526\u2013536 (2024).","DOI":"10.1016\/j.jointm.2024.04.004"},{"key":"1709_CR7","doi-asserted-by":"publisher","first-page":"823","DOI":"10.2337\/dc06-2184","volume":"30","author":"LR Schmeltz","year":"2007","unstructured":"Schmeltz, L. R. et al. Reduction of surgical mortality and morbidity in diabetic patients undergoing cardiac surgery with a combined intravenous and subcutaneous insulin glucose management strategy. Diab Care 30, 823\u2013828 (2007).","journal-title":"Diab Care"},{"key":"1709_CR8","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1161\/CIRCULATIONAHA.107.706416","volume":"118","author":"R Ascione","year":"2008","unstructured":"Ascione, R., Rogers, C. A., Rajakaruna, C. & Angelini, G. D. Inadequate blood glucose control is associated with in-hospital mortality and morbidity in diabetic and nondiabetic patients undergoing cardiac surgery. Circulation 118, 113\u2013123 (2008).","journal-title":"Circulation"},{"key":"1709_CR9","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1177\/1474515111430887","volume":"11","author":"K Giakoumidakis","year":"2012","unstructured":"Giakoumidakis, K., Nenekidis, I. & Brokalaki, H. The correlation between peri-operative hyperglycemia and mortality in cardiac surgery patients: A systematic review. Eur. J. Cardiovasc Nurs. 11, 105\u2013113 (2012).","journal-title":"Eur. J. Cardiovasc Nurs."},{"key":"1709_CR10","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1016\/j.athoracsur.2008.11.011","volume":"87","author":"HL Lazar","year":"2009","unstructured":"Lazar, H. L. et al. The Society of Thoracic Surgeons practice guideline series: Blood glucose management during adult cardiac surgery. Ann. Thorac. Surg. 87, 663\u2013669 (2009).","journal-title":"Ann. Thorac. Surg."},{"key":"1709_CR11","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.jcrc.2017.09.013","volume":"42","author":"JB Williams","year":"2017","unstructured":"Williams, J. B. et al. Glycemic control in patients undergoing coronary artery bypass graft surgery: Clinical features, predictors, and outcomes. J. Crit. Care 42, 328\u2013333 (2017).","journal-title":"J. Crit. Care"},{"key":"1709_CR12","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.athoracsur.2016.05.121","volume":"103","author":"LE Johnston","year":"2017","unstructured":"Johnston, L. E. et al. Postoperative Hypoglycemia Is Associated With Worse Outcomes After Cardiac Operations. Ann. Thorac. Surg. 103, 526\u2013532 (2017).","journal-title":"Ann. Thorac. Surg."},{"key":"1709_CR13","doi-asserted-by":"crossref","unstructured":"Martinez, M., Santamarina, J., Pavesi, A., Musso, C. & Umpierrez, G. E. Glycemic variability and cardiovascular disease in patients with type 2 diabetes. BMJ Open Diabetes Res Care 9, e002032 (2021).","DOI":"10.1136\/bmjdrc-2020-002032"},{"key":"1709_CR14","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1089\/dia.2011.0104","volume":"13","author":"D Rodbard","year":"2011","unstructured":"Rodbard, D. Glycemic variability: Measurement and utility in clinical medicine and research-one viewpoint. Diab Technol. Ther. 13, 1077\u20131080 (2011).","journal-title":"Diab Technol. Ther."},{"key":"1709_CR15","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.2337\/dc09-9029","volume":"32","author":"ES Moghissi","year":"2009","unstructured":"Moghissi, E. S. et al. American Association of Clinical Endocrinologists and American Diabetes Association consensus statement on inpatient glycemic control. Diab Care 32, 1119\u20131131 (2009).","journal-title":"Diab Care"},{"key":"1709_CR16","doi-asserted-by":"publisher","first-page":"2212","DOI":"10.1093\/jamia\/ocab099","volume":"28","author":"M Nguyen","year":"2021","unstructured":"Nguyen, M., Jankovic, I., Kalesinskas, L., Baiocchi, M. & Chen, J. H. Machine learning for initial insulin estimation in hospitalized patients. J. Am. Med Inf. Assoc. 28, 2212\u20132219 (2021).","journal-title":"J. Am. Med Inf. Assoc."},{"key":"1709_CR17","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1093\/jamia\/ocab060","volume":"28","author":"O Fitzgerald","year":"2021","unstructured":"Fitzgerald, O. et al. Incorporating real-world evidence into the development of patient blood glucose prediction algorithms for the ICU. J. Am. Med Inf. Assoc. 28, 1642\u20131650 (2021).","journal-title":"J. Am. Med Inf. Assoc."},{"key":"1709_CR18","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s11892-022-01477-w","volume":"22","author":"A Zale","year":"2022","unstructured":"Zale, A. & Mathioudakis, N. Machine learning models for inpatient glucose prediction. Curr. Diab Rep. 22, 353\u2013364 (2022).","journal-title":"Curr. Diab Rep."},{"key":"1709_CR19","doi-asserted-by":"crossref","unstructured":"Montaser, E., D\u00edez, J. L. & Bondia, J. Glucose prediction under variable-length time-stamped daily events: A seasonal stochastic local modeling framework. Sensors (Basel) 21, 3188 (2021).","DOI":"10.3390\/s21093188"},{"key":"1709_CR20","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L. P., Littman, M. L. & Moore, A. W. Reinforcement learning: A survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996).","journal-title":"J. Artif. Intell. Res."},{"key":"1709_CR21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.01643","author":"S Levine","year":"2020","unstructured":"Levine, S., Kumar, A., Tucker, G. & Fu, J. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv https:\/\/doi.org\/10.48550\/arXiv.2005.01643 (2020).","journal-title":"arXiv"},{"key":"1709_CR22","unstructured":"Bellemare, M. G., Dabney, W. & Munos, R. in International conference on machine learning. 449-458 (PMLR)."},{"key":"1709_CR23","unstructured":"Dabney, W., Rowland, M., Bellemare, M. & Munos, R. Proceedings of the AAAI conference on artificial intelligence."},{"key":"1709_CR24","unstructured":"Dabney, W., Ostrovski, G., Silver, D. & Munos, R. in International conference on machine learning. 1096-1105 (PMLR)."},{"key":"1709_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AEW Johnson","year":"2023","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"1709_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178","volume":"5","author":"TJ Pollard","year":"2018","unstructured":"Pollard, T. J. et al. The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci. Data 5, 180178 (2018).","journal-title":"Sci. Data"},{"key":"1709_CR27","first-page":"20132","volume":"34","author":"S Fujimoto","year":"2021","unstructured":"Fujimoto, S. & Gu, S. S. A minimalist approach to offline reinforcement learning. Adv. neural Inf. Process. Syst. 34, 20132\u201320145 (2021).","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"1709_CR28","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","volume":"24","author":"M Komorowski","year":"2018","unstructured":"Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C. & Faisal, A. A. The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nat. Med. 24, 1716\u20131720 (2018).","journal-title":"Nat. Med."},{"key":"1709_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00388-6","volume":"4","author":"A Peine","year":"2021","unstructured":"Peine, A. et al. Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care. npj Digital Med. 4, 32 (2021).","journal-title":"npj Digital Med."},{"key":"1709_CR30","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00893-w","volume":"6","author":"H Lee","year":"2023","unstructured":"Lee, H. et al. Development and validation of a reinforcement learning model for ventilation control during emergence from general anesthesia. npj Digital Med. 6, 145 (2023).","journal-title":"npj Digital Med."},{"key":"1709_CR31","unstructured":"Le, H., Voloshin, C. & Yue, Y. in International Conference on Machine Learning. 3703-3712 (PMLR)."},{"key":"1709_CR32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.09055","author":"TL Paine","year":"2020","unstructured":"Paine, T. L., et al. Hyperparameter selection for offline reinforcement learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.2007.09055 (2020).","journal-title":"arXiv"},{"key":"1709_CR33","unstructured":"Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"1709_CR34","doi-asserted-by":"publisher","DOI":"10.1101\/2023.04.20.23288845","author":"O Fitzgerald","year":"2023","unstructured":"Fitzgerald, O., Perez-Concha, O., Gallego-Luxan, B., Rudd, L. & Jorm, L. Curation and description of a blood glucose management and nutritional support cohort using the eICU collaborative research database. medRxiv https:\/\/doi.org\/10.1101\/2023.04.20.23288845 (2023).","journal-title":"medRxiv"},{"key":"1709_CR35","doi-asserted-by":"publisher","DOI":"10.1186\/s13019-018-0700-2","volume":"13","author":"M Navaratnarajah","year":"2018","unstructured":"Navaratnarajah, M. et al. Effect of glycaemic control on complications following cardiac surgery: literature review. J. Cardiothorac. Surg. 13, 10 (2018).","journal-title":"J. Cardiothorac. Surg."},{"key":"1709_CR36","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1056\/NEJMoa011300","volume":"345","author":"G van den Berghe","year":"2001","unstructured":"van den Berghe, G. et al. Intensive insulin therapy in critically ill patients. N. Engl. J. Med 345, 1359\u20131367 (2001).","journal-title":"N. Engl. J. Med"},{"key":"1709_CR37","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1001\/jama.300.8.933","volume":"300","author":"RS Wiener","year":"2008","unstructured":"Wiener, R. S., Wiener, D. C. & Larson, R. J. Benefits and risks of tight glucose control in critically ill adults: a meta-analysis. Jama 300, 933\u2013944 (2008).","journal-title":"Jama"},{"key":"1709_CR38","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s00134-007-0934-2","volume":"34","author":"RP Dellinger","year":"2008","unstructured":"Dellinger, R. P., et al. Surviving Sepsis Campaign: international guidelines for management of severe sepsis and septic shock: 2008. Intensive Care Med. 34, 17\u201360 (2008).","journal-title":"Intensive Care Med."},{"key":"1709_CR39","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1038\/nrd.2015.36","volume":"15","author":"AN Zaykov","year":"2016","unstructured":"Zaykov, A. N., Mayer, J. P. & DiMarchi, R. D. Pursuit of a perfect insulin. Nat. Rev. Drug Discov. 15, 425\u2013439 (2016).","journal-title":"Nat. Rev. Drug Discov."},{"key":"1709_CR40","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.2337\/dc15-0303","volume":"38","author":"G Umpierrez","year":"2015","unstructured":"Umpierrez, G. et al. Randomized controlled trial of intensive versus conservative glucose control in patients undergoing coronary artery bypass graft surgery: GLUCO-CABG trial. Diab Care 38, 1665\u20131672 (2015).","journal-title":"Diab Care"},{"key":"1709_CR41","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1056\/NEJMoa0810625","volume":"360","author":"Investigators, N.-S. S","year":"2009","unstructured":"Investigators, N.-S. S Intensive versus conventional glucose control in critically ill patients. N. Engl. J. Med. 360, 1283\u20131297 (2009).","journal-title":"N. Engl. J. Med."},{"key":"1709_CR42","first-page":"H1775","volume":"258","author":"BM Fisher","year":"1990","unstructured":"Fisher, B. M., Gillen, G., Hepburn, D. A., Dargie, H. J. & Frier, B. M. Cardiac responses to acute insulin-induced hypoglycemia in humans. Am. J. Physiol. 258, H1775\u2013H1779 (1990).","journal-title":"Am. J. Physiol."},{"key":"1709_CR43","doi-asserted-by":"publisher","first-page":"360","DOI":"10.2337\/db08-1153","volume":"58","author":"GK Adler","year":"2009","unstructured":"Adler, G. K. et al. Antecedent hypoglycemia impairs autonomic cardiovascular function: implications for rigorous glycemic control. Diabetes 58, 360\u2013366 (2009).","journal-title":"Diabetes"},{"key":"1709_CR44","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/B978-0-444-53480-4.00036-9","volume":"126","author":"S Mohseni","year":"2014","unstructured":"Mohseni, S. Neurologic damage in hypoglycemia. Handb. Clin. Neurol. 126, 513\u2013532 (2014).","journal-title":"Handb. Clin. Neurol."},{"key":"1709_CR45","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.jcrc.2007.06.003","volume":"23","author":"O Manor-Shulman","year":"2008","unstructured":"Manor-Shulman, O., Beyene, J., Frndova, H. & Parshuram, C. S. Quantifying the volume of documented clinical information in critical illness. J. Crit. Care 23, 245\u2013250 (2008).","journal-title":"J. Crit. Care"},{"key":"1709_CR46","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1038\/s41591-023-02552-9","volume":"29","author":"G Wang","year":"2023","unstructured":"Wang, G. et al. Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial. Nat. Med. 29, 2633\u20132642 (2023).","journal-title":"Nat. Med."},{"key":"1709_CR47","unstructured":"Fox, I., Lee, J., Pop-Busui, R. & Wiens, J. in Machine Learning for Healthcare Conference. 508-536 (PMLR)."},{"key":"1709_CR48","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/JBHI.2020.3014556","volume":"25","author":"T Zhu","year":"2020","unstructured":"Zhu, T., Li, K., Herrero, P. & Georgiou, P. Basal glucose control in type 1 diabetes using deep reinforcement learning: An in silico validation. IEEE J. Biomed. Health Inform. 25, 1223\u20131232 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1709_CR49","unstructured":"Raghu, A., Komorowski, M., Celi, L. A., Szolovits, P. & Ghassemi, M. in Machine Learning for Healthcare Conference. 147-163 (PMLR)."},{"key":"1709_CR50","doi-asserted-by":"publisher","first-page":"3251","DOI":"10.1097\/CCM.0b013e3182653269","volume":"40","author":"J Jacobi","year":"2012","unstructured":"Jacobi, J., et al. Guidelines for the use of an insulin infusion for the management of hyperglycemia in critically ill patients. Crit. Care Med. 40, 3251\u20133276 (2012).","journal-title":"Crit. Care Med."},{"key":"1709_CR51","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G. & Levine, S. Conservative q-learning for offline reinforcement learning. Adv. Neural Inf. Process. Syst. 33, 1179\u20131191 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1709_CR52","unstructured":"Fujimoto, S., Meger, D. & Precup, D. in International conference on machine learning. 2052-2062 (PMLR)."},{"key":"1709_CR53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.11361","author":"Y Wu","year":"2019","unstructured":"Wu, Y., Tucker, G. & Nachum, O. Behavior regularized offline reinforcement learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.1911.11361 (2019).","journal-title":"arXiv"},{"key":"1709_CR54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.07219","author":"J Fu","year":"2020","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G. & Levine, S. D4rl: Datasets for deep data-driven reinforcement learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.2004.07219 (2020).","journal-title":"arXiv"},{"key":"1709_CR55","doi-asserted-by":"publisher","unstructured":"Hong, Z.-W., Agrawal, P., Combes, R. T. d. & Laroche, R. Harnessing mixed offline reinforcement learning datasets via trajectory weighting. (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.13085","DOI":"10.48550\/arXiv.2306.13085"},{"key":"1709_CR56","doi-asserted-by":"publisher","first-page":"104376","DOI":"10.1016\/j.jbi.2023.104376","volume":"142","author":"H Emerson","year":"2023","unstructured":"Emerson, H., Guy, M. & McConville, R. Offline reinforcement learning for safer blood glucose control in people with type 1 diabetes. J. Biomed. Inform. 142, 104376 (2023).","journal-title":"J. Biomed. Inform."},{"key":"1709_CR57","unstructured":"Van Hasselt, H. P., Guez, A., Hessel, M., Mnih, V. & Silver, D. Learning values across many orders of magnitude. Advances in neural information processing systems 29 (2016)."},{"key":"1709_CR58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.07566","author":"W Gu","year":"2024","unstructured":"Gu, W. & Wang, S. An improved strategy for blood glucose control using multi-step deep reinforcement learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.2403.07566 (2024).","journal-title":"arXiv"},{"key":"1709_CR59","first-page":"1","volume":"23","author":"T Seno","year":"2022","unstructured":"Seno, T. & Imai, M. d3rlpy: An offline deep reinforcement learning library. J. Mach. Learn. Res. 23, 1\u201320 (2022).","journal-title":"J. Mach. Learn. Res."},{"key":"1709_CR60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.06854","author":"C Voloshin","year":"2019","unstructured":"Voloshin, C., Le, H. M., Jiang, N. & Yue, Y. Empirical study of off-policy policy evaluation for reinforcement learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.1911.06854 (2019).","journal-title":"arXiv"},{"key":"1709_CR61","unstructured":"Tang, S. & Wiens, J. in Machine Learning for Healthcare Conference. 2-35 (PMLR)."},{"key":"1709_CR62","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. methods 17, 261\u2013272 (2020).","journal-title":"Nat. methods"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01709-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01709-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01709-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:02:07Z","timestamp":1748358127000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01709-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1709"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01709-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.01.25319851","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,27]]},"assertion":[{"value":"10 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"GLUCOSE is the subject of a provisional patent application (Application No. 63\/698,447) filed with the United States Patents and Trademarks Office, in which JMD, AS, and GNN are named inventors. G.N.N. is a founder of Renalytix, Pensieve, Verici and provides consultancy services to AstraZeneca, Reata, Renalytix, Siemens Healthineer and Variant Bio, serves a scientific advisory board member for Renalytix and Pensieve. He also has equity in Renalytix, Pensieve and Verici. GNN is also an Associate Editor for npj Digital Medicine. He had no role in editorial decisions about the manuscript. L.C. is a consultant for Vifor Pharma INC and has received honorarium from Fresenius Medical Care. J.A.K. reports receiving consulting fees from Astute Medical\/bioMerieux, Astellas, Alexion, Chugai Pharma, Novartis, Mitsubishi Tenabe and GE Healthcare and is a full time employee of Spectral Medical. All remaining authors have declared no conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"313"}}