{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T02:06:53Z","timestamp":1790129213815,"version":"4.0.1"},"reference-count":34,"publisher":"JMIR Publications Inc.","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Diabetes"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Type 1 diabetes mellitus (T1DM) is characterized by chronic insulin deficiency and consequent hyperglycemia. Patients with T1DM require long-term exogenous insulin therapy to regulate blood glucose levels and prevent the long-term complications of the disease. Currently, there are no effective algorithms that consider the unique characteristics of T1DM patients to automatically recommend personalized insulin dosage levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The objective of this study was to develop and validate a general reinforcement learning (RL) framework for the personalized treatment of T1DM using clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This research presents a model-free data-driven RL algorithm, namely Q-learning, that recommends insulin doses to regulate the blood glucose level of a T1DM patient, considering his or her state defined by glycated hemoglobin (HbA1c) levels, body mass index, engagement in physical activity, and alcohol usage. In this approach, the RL agent identifies the different states of the patient by exploring the patient\u2019s responses when he or she is subjected to varying insulin doses. On the basis of the result of a treatment action at time step t, the RL agent receives a numeric reward, positive or negative. The reward is calculated as a function of the difference between the actual blood glucose level achieved in response to the insulin dose and the targeted HbA1c level. The RL agent was trained on 10 years of clinical data of patients treated at the Mass General Hospital.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 87 patients were included in the training set. The mean age of these patients was 53 years, 59% (51\/87) were male, 86% (75\/87) were white, and 47% (41\/87) were married. The performance of the RL agent was evaluated on 60 test cases. RL agent\u2013recommended insulin dosage interval includes the actual dose prescribed by the physician in 53 out of 60 cases (53\/60, 88%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This exploratory study demonstrates that an RL algorithm can be used to recommend personalized insulin doses to achieve adequate glycemic control in patients with T1DM. However, further investigation in a larger sample of patients is needed to confirm these findings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/12905","type":"journal-article","created":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T16:51:03Z","timestamp":1563555063000},"page":"e12905","source":"Crossref","is-referenced-by-count":29,"title":["A Reinforcement Learning\u2013Based Method for Management of Type 1 Diabetes: Exploratory Study"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1843-3763","authenticated-orcid":false,"given":"Mahsa","family":"Oroojeni Mohammad Javad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2161-8091","authenticated-orcid":false,"given":"Stephen Olusegun","family":"Agboola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0122-8002","authenticated-orcid":false,"given":"Kamal","family":"Jethwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2928-8197","authenticated-orcid":false,"given":"Abe","family":"Zeid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-7714","authenticated-orcid":false,"given":"Sagar","family":"Kamarthi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2019,8,28]]},"reference":[{"key":"ref1","unstructured":"American Diabetes Association2019-04-22Statistics About Diabetes: Overall Numbers, Diabetes and Prediabetes http:\/\/www.diabetes.org\/diabetes-basics\/statistics\/"},{"key":"ref2","unstructured":"Centers for Disease Control and Prevention2019-04-22CDC Newsroom https:\/\/www.cdc.gov\/media\/pressrel\/2010\/r101022.html"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/12237"},{"key":"ref4","unstructured":"National Institute of Diabetes and Digestive and Kidney Diseases2019-04-22Kidney Disease Statistics for the United States http:\/\/www.niddk.nih.gov\/healthinformation\/healthtopics\/kidneydisease\/kidney-disease-of-diabetes\/Pages\/facts.aspx"},{"key":"ref5","unstructured":"The United States Renal Data System2019-04-222016 Annual Data Report https:\/\/www.usrds.org\/adr.aspx"},{"key":"ref6","unstructured":"Centers for Disease Control and Prevention20112019-04-22National Diabetes Fact Sheet https:\/\/www.cdc.gov\/diabetes\/pubs\/pdf\/ndfs_2011.pdf"},{"key":"ref7","unstructured":"Mayo Clinic2019-04-22Diabetes: Overview https:\/\/www.mayoclinic.org\/diseases-conditions\/diabetes\/symptoms-causes\/syc-20371444"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.26.2007.s28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2196\/11030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2196\/11590"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1211\/jpp.60.1.0001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0933-3657(02)00051-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2196\/10780"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-006-0049-x"},{"key":"ref15","first-page":"160","volume":"1","author":"Bellazzi, R","year":"1998","journal-title":"Proc AMIA Symp"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/193229680900300326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/37.168817"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/739385"},{"issue":"9","key":"ref19","first-page":"260","volume":"3","author":"Yasini, S","year":"2009","journal-title":"Int J Biomed Biol Eng"},{"issue":"3","key":"ref20","first-page":"197","volume":"8","author":"Shimoda, S","year":"1997","journal-title":"Front Med Biol Eng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF02477386"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1049\/PBCE081E","author":"Vrabie, D","year":"2012","journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BHI.2018.8333436"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/4091497"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2337\/diab.23.5.397"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1115\/IMECE2015-53420"},{"key":"ref27","author":"Sutton, RS","year":"1998","journal-title":"Reinforcement Learning: An Introduction"},{"key":"ref28","author":"Sutton, RS","year":"2018","journal-title":"Reinforcement Learning: An Introduction"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45356-3_59"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2006.10.004"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0310-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref34","author":"Mitchell, TM","year":"1997","journal-title":"Machine Learning"}],"container-title":["JMIR Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/diabetes.jmir.org\/2019\/3\/e12905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:00:29Z","timestamp":1782842429000},"score":1,"resource":{"primary":{"URL":"http:\/\/diabetes.jmir.org\/2019\/3\/e12905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,28]]},"references-count":34,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.2196\/12905","relation":{},"ISSN":["2371-4379"],"issn-type":[{"value":"2371-4379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,28]]}}}