{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:11:05Z","timestamp":1763536265160,"version":"3.38.0"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1016\/j.artmed.2024.102920","type":"journal-article","created":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T23:37:26Z","timestamp":1719358646000},"page":"102920","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["End-to-end offline reinforcement learning for glycemia control"],"prefix":"10.1016","volume":"154","author":[{"given":"Tristan","family":"Beolet","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1220-1606","authenticated-orcid":false,"given":"Alice","family":"Adenis","sequence":"additional","affiliation":[]},{"given":"Erik","family":"Huneker","sequence":"additional","affiliation":[]},{"given":"Maxime","family":"Louis","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.artmed.2024.102920_b1","doi-asserted-by":"crossref","first-page":"844","DOI":"10.2337\/dc20-1809","article-title":"Diabeloop DBLG1 closed-loop system enables patients with type 1 diabetes to significantly improve their glycemic control in real-life situations without serious adverse events: 6-month follow-up","volume":"44","author":"Amadou","year":"2021","journal-title":"Diabetes Care"},{"issue":"7","key":"10.1016\/j.artmed.2024.102920_b2","doi-asserted-by":"crossref","first-page":"1719","DOI":"10.1016\/j.numecd.2022.03.031","article-title":"Minimed medtronic 780G optimizes glucose control in patients with type 1 diabetes mellitus","volume":"32","author":"Pintaudi","year":"2022","journal-title":"Nutr Metab Cardiovasc Dis"},{"issue":"8","key":"10.1016\/j.artmed.2024.102920_b3","doi-asserted-by":"crossref","first-page":"507","DOI":"10.4155\/tde-2020-0055","article-title":"Review of the Omnipod\u00ae 5 automated glucose control system powered by HorizonTM for the treatment of type 1 diabetes","volume":"11","author":"Cobry","year":"2020","journal-title":"Ther Deliv"},{"issue":"12","key":"10.1016\/j.artmed.2024.102920_b4","doi-asserted-by":"crossref","first-page":"2309","DOI":"10.1111\/dom.14815","article-title":"Lived experience of CamAPS FX closed loop system in youth with type 1 diabetes and their parents","volume":"24","author":"Hood","year":"2022","journal-title":"Diabetes Obes Metab"},{"issue":"5","key":"10.1016\/j.artmed.2024.102920_b5","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1089\/dia.2020.0507","article-title":"Safety and performance of the Tandem t: slim X2 with Control-IQ automated insulin delivery system in toddlers and preschoolers","volume":"23","author":"Ekhlaspour","year":"2021","journal-title":"Diabetes Technol Ther"},{"issue":"6","key":"10.1016\/j.artmed.2024.102920_b6","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1089\/dia.2022.0011","article-title":"Accuracy and safety of dexcom G7 continuous glucose monitoring in adults with diabetes","volume":"24","author":"Garg","year":"2022","journal-title":"Diabetes Technol Ther"},{"issue":"2","key":"10.1016\/j.artmed.2024.102920_b7","doi-asserted-by":"crossref","first-page":"203","DOI":"10.2337\/cd17-0130","article-title":"Freestyle libre glucose monitoring system","volume":"36","author":"Blum","year":"2018","journal-title":"Clin Diabetes"},{"issue":"10","key":"10.1016\/j.artmed.2024.102920_b8","doi-asserted-by":"crossref","first-page":"1740","DOI":"10.1109\/TBME.2007.893506","article-title":"Meal simulation model of the glucose-insulin system","volume":"54","author":"Dalla Man","year":"2007","journal-title":"IEEE Trans Biomed Eng"},{"key":"10.1016\/j.artmed.2024.102920_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104376","article-title":"Offline reinforcement learning for safer blood glucose control in people with type 1 diabetes","volume":"142","author":"Emerson","year":"2023","journal-title":"J Biomed Inform"},{"issue":"2","key":"10.1016\/j.artmed.2024.102920_b10","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.cmpb.2012.03.002","article-title":"An Actor\u2013Critic based controller for glucose regulation in type 1 diabetes","volume":"109","author":"Daskalaki","year":"2013","journal-title":"Comput Methods Programs Biomed"},{"key":"10.1016\/j.artmed.2024.102920_b11","series-title":"2013 35th annual international conference of the IEEE engineering in medicine and biology society","first-page":"3487","article-title":"Personalized tuning of a reinforcement learning control algorithm for glucose regulation","author":"Daskalaki","year":"2013"},{"issue":"4","key":"10.1016\/j.artmed.2024.102920_b12","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1109\/JBHI.2020.3014556","article-title":"Basal glucose control in type 1 diabetes using deep reinforcement learning: An in silico validation","volume":"25","author":"Zhu","year":"2020","journal-title":"IEEE J Biomed Health Inf"},{"issue":"18","key":"10.1016\/j.artmed.2024.102920_b13","doi-asserted-by":"crossref","first-page":"5058","DOI":"10.3390\/s20185058","article-title":"An insulin bolus advisor for type 1 diabetes using deep reinforcement learning","volume":"20","author":"Zhu","year":"2020","journal-title":"Sensors"},{"year":"2019","series-title":"Reinforcement learning for blood glucose control: Challenges and opportunities","author":"Fox","key":"10.1016\/j.artmed.2024.102920_b14"},{"key":"10.1016\/j.artmed.2024.102920_b15","unstructured":"Louis M, Ugalde HR, Gauthier P, Adenis A, Tourki Y, Huneker E. Safe Reinforcement Learning for Automatic Insulin Delivery in Type I Diabetes. In: Reinforcement learning for real life workshop, neurIPS 2022. 2022."},{"issue":"5","key":"10.1016\/j.artmed.2024.102920_b16","doi-asserted-by":"crossref","first-page":"E992","DOI":"10.1152\/ajpendo.00304.2001","article-title":"Partitioning glucose distribution\/transport, disposal, and endogenous production during IVGTT","volume":"282","author":"Hovorka","year":"2002","journal-title":"Amer J Physiol-Endocrinol Metab"},{"issue":"3","key":"10.1016\/j.artmed.2024.102920_b17","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1089\/dia.2017.0420","article-title":"Best use of models to advance the artificial pancreas","volume":"20","author":"Steil","year":"2018","journal-title":"Diabetes Technol Ther"},{"year":"2020","series-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","key":"10.1016\/j.artmed.2024.102920_b18"},{"key":"10.1016\/j.artmed.2024.102920_b19","doi-asserted-by":"crossref","DOI":"10.1109\/JBHI.2023.3303367","article-title":"Offline deep reinforcement learning and off-policy evaluation for personalized basal insulin control in type 1 diabetes","author":"Zhu","year":"2023","journal-title":"IEEE J Biomed Health Inf"},{"key":"10.1016\/j.artmed.2024.102920_b20","series-title":"CEUR workshop proceedings","first-page":"71","article-title":"The OhioT1DM dataset for blood glucose level prediction: update 2020","volume":"Vol. 2675","author":"Marling","year":"2020"},{"issue":"7","key":"10.1016\/j.artmed.2024.102920_b21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0158722","article-title":"Model-free machine learning in biomedicine: Feasibility study in type 1 diabetes","volume":"11","author":"Daskalaki","year":"2016","journal-title":"PLoS One"},{"key":"10.1016\/j.artmed.2024.102920_b22","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D. Continuous control with deep reinforcement learning. In: 4th international conference on learning representations, ICLR 2016."},{"key":"10.1016\/j.artmed.2024.102920_b23","doi-asserted-by":"crossref","unstructured":"Nambiar M, Ghosh S, Ong P, Chan YE, Bee YM, Krishnaswamy P. Deep offline reinforcement learning for real-world treatment optimization applications. In: Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining. 2023, p. 4673\u201384.","DOI":"10.1145\/3580305.3599800"},{"key":"10.1016\/j.artmed.2024.102920_b24","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2024.102920_b25","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2024.102920_b26","series-title":"International conference on machine learning","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2019"},{"issue":"1","key":"10.1016\/j.artmed.2024.102920_b27","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1177\/1932296813514502","article-title":"The UVA\/PADOVA type 1 diabetes simulator: new features","volume":"8","author":"Man","year":"2014","journal-title":"J Diabetes Sci Technol"},{"year":"2020","series-title":"Model-based reinforcement learning for type 1 diabetes blood glucose control","author":"Yamagata","key":"10.1016\/j.artmed.2024.102920_b28"},{"key":"10.1016\/j.artmed.2024.102920_b29","series-title":"International conference on machine learning","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"10.1016\/j.artmed.2024.102920_b30","series-title":"International conference on machine learning","first-page":"1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"10.1016\/j.artmed.2024.102920_b31","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"year":"2023","series-title":"Understanding insulin on board (IOB) calculations","author":"OpenAPS","key":"10.1016\/j.artmed.2024.102920_b32"},{"issue":"4","key":"10.1016\/j.artmed.2024.102920_b33","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1177\/1932296821994825","article-title":"Multi-timescale rhythmicity of blood glucose and insulin delivery reveals key advantages of hybrid closed loop therapy","volume":"16","author":"Grant","year":"2022","journal-title":"J Diabetes Sci Technol"},{"issue":"38","key":"10.1016\/j.artmed.2024.102920_b34","doi-asserted-by":"crossref","first-page":"eadg2132","DOI":"10.1126\/sciadv.adg2132","article-title":"Understanding temporal changes and seasonal variations in glycemic trends using wearable data","volume":"9","author":"Belsare","year":"2023","journal-title":"Sci Adv"},{"issue":"8","key":"10.1016\/j.artmed.2024.102920_b35","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1111\/pedi.13455","article-title":"ISPAD Clinical Practice Consensus Guidelines 2022: Glycemic targets and glucose monitoring for children, adolescents, and young people with diabetes","volume":"23","author":"de Bock","year":"2022","journal-title":"Pediatr Diabetes"},{"issue":"3","key":"10.1016\/j.artmed.2024.102920_b36","doi-asserted-by":"crossref","first-page":"400","DOI":"10.2337\/dc18-1444","article-title":"Validation of time in range as an outcome measure for diabetes clinical trials","volume":"42","author":"Beck","year":"2019","journal-title":"Diabetes Care"},{"issue":"8","key":"10.1016\/j.artmed.2024.102920_b37","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.2337\/dci19-0028","article-title":"Clinical targets for continuous glucose monitoring data interpretation: recommendations from the international consensus on time in range","volume":"42","author":"Battelino","year":"2019","journal-title":"Diabetes Care"},{"issue":"11","key":"10.1016\/j.artmed.2024.102920_b38","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.2337\/dci21-0043","article-title":"The management of type 1 diabetes in adults. A consensus report by the American diabetes association (ADA) and the European association for the study of diabetes (EASD)","volume":"44","author":"Holt","year":"2021","journal-title":"Diabetes Care"},{"issue":"Supplement_1","key":"10.1016\/j.artmed.2024.102920_b39","doi-asserted-by":"crossref","first-page":"S73","DOI":"10.2337\/dc21-S006","article-title":"6. Glycemic targets: standards of medical care in diabetes\u20142021","volume":"44","author":"Association","year":"2021","journal-title":"Diabetes Care"},{"issue":"3","key":"10.1016\/j.artmed.2024.102920_b40","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S2213-8587(18)30136-0","article-title":"Glycaemic variability in diabetes: clinical and therapeutic implications","volume":"7","author":"Ceriello","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"12","key":"10.1016\/j.artmed.2024.102920_b41","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.2337\/dc17-1600","article-title":"International consensus on use of continuous glucose monitoring","volume":"40","author":"Danne","year":"2017","journal-title":"Diabetes Care"},{"issue":"6","key":"10.1016\/j.artmed.2024.102920_b42","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1056\/NEJMoa1215740","article-title":"Glucose levels and risk of dementia","volume":"369","author":"Crane","year":"2013","journal-title":"New Engl J Med"},{"issue":"11","key":"10.1016\/j.artmed.2024.102920_b43","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","article-title":"The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care","volume":"24","author":"Komorowski","year":"2018","journal-title":"Nat Med"},{"issue":"1","key":"10.1016\/j.artmed.2024.102920_b44","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s41746-021-00388-6","article-title":"Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care","volume":"4","author":"Peine","year":"2021","journal-title":"NPJ Digit Med"},{"key":"10.1016\/j.artmed.2024.102920_b45","series-title":"International conference on machine learning","first-page":"3703","article-title":"Batch policy learning under constraints","author":"Le","year":"2019"},{"key":"10.1016\/j.artmed.2024.102920_b46","series-title":"2011 IEEE symposium on adaptive dynamic programming and reinforcement learning","first-page":"84","article-title":"Agent self-assessment: Determining policy quality without execution","author":"Hans","year":"2011"},{"key":"10.1016\/j.artmed.2024.102920_b47","series-title":"2007 international joint conference on neural networks","first-page":"1691","article-title":"A neural reinforcement learning approach to gas turbine control","author":"Schaefer","year":"2007"},{"key":"10.1016\/j.artmed.2024.102920_b48","article-title":"No more pesky hyperparameters: offline hyperparameter tuning for RL","author":"Wang","year":"2022","journal-title":"Trans Mach Learn Res"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365724001623?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365724001623?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T11:04:54Z","timestamp":1742036694000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0933365724001623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":48,"alternative-id":["S0933365724001623"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2024.102920","relation":{},"ISSN":["0933-3657"],"issn-type":[{"type":"print","value":"0933-3657"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"End-to-end offline reinforcement learning for glycemia control","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2024.102920","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102920"}}