{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:30:27Z","timestamp":1783625427764,"version":"3.55.0"},"reference-count":49,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biosensors"],"abstract":"<jats:p>Due to the complexity of blood glucose dynamics and the high variability of the physiological structure of diabetic patients, implementing a safe and effective insulin dosage control algorithm to keep the blood glucose of diabetic patients within the normal range (70\u2013180 mg\/dL) is currently a challenging task in the field of diabetes treatment. Deep reinforcement learning (DRL) has proven its potential in diabetes treatment in previous work, thanks to its strong advantages in solving complex dynamic and uncertain problems. It can address the challenges faced by traditional control algorithms, such as the need for patients to manually estimate carbohydrate intake before meals, the requirement to establish complex dynamic models, and the need for professional prior knowledge. However, reinforcement learning is essentially a highly exploratory trial-and-error learning strategy, which is contrary to the high-safety requirements of clinical practice. Therefore, achieving safer control has always been a major challenge for the clinical application of DRL. This paper addresses this challenge by combining the advantages of DRL and the traditional control algorithm\u2014model predictive control (MPC). Specifically, by using the blood glucose and insulin data generated during the interaction between DRL and patients in the learning process to learn a blood glucose prediction model, the problem of MPC needing to establish a patient\u2019s blood glucose dynamic model is solved. Then, MPC is used for forward-looking prediction and simulation of blood glucose, and a safety controller is introduced to avoid unsafe actions, thus restricting DRL control to a safer range. Experiments on the UVA\/Padova glucose kinetics simulator approved by the US Food and Drug Administration (FDA) show that the time proportion of adult patients within the healthy blood glucose range under the control of the model proposed in this paper reaches 72.51%, an increase of 2.54% compared with the baseline model, and the proportion of severe hyperglycemia and hypoglycemia events is not increased, taking an important step towards the safe control of blood glucose.<\/jats:p>","DOI":"10.3390\/bios16010047","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T11:13:18Z","timestamp":1767697998000},"page":"47","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid Closed-Loop Blood Glucose Control Algorithm with a Safety Limiter Based on Deep Reinforcement Learning and Model Predictive Control"],"prefix":"10.3390","volume":"16","author":[{"given":"Shanyong","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusheng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowei","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1002\/(SICI)1096-9136(199807)15:7<539::AID-DIA668>3.0.CO;2-S","article-title":"Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: Diagnosis and classification of diabetes mellitus. Provisional report of a WHO consultation","volume":"15","author":"Alberti","year":"1998","journal-title":"Diabet. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109119","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5537","DOI":"10.1039\/D2TB00749E","article-title":"Recent advancements in noninvasive glucose monitoring and closedloop management systems for diabetes","volume":"10","author":"Ma","year":"2022","journal-title":"J. Mater. Chem. B"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1109\/MCS.2017.2767119","article-title":"Overnight hypoglycemia and hyperglycemia mitigation for individuals with type 1 diabetes: How risks can be reduced","volume":"38","author":"Bequette","year":"2018","journal-title":"IEEE Control. Syst. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"101603","DOI":"10.1016\/j.bspc.2019.101603","article-title":"Automatic blood glucose control for type 1 diabetes: A trade-off between postprandial hyperglycemia and hypoglycemia","volume":"54","author":"Khodakaramzadeh","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"736","DOI":"10.2337\/dc17-0133","article-title":"The impact of continuous glucose monitoring on markers of quality of life in adults with type 1 diabetes: Further findings from the DIAMOND randomized clinical trial","volume":"40","author":"Polonsky","year":"2017","journal-title":"Diabetes Care"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1007\/s00125-021-05437-z","article-title":"Effect of flash glucose monitoring in adults with type 1 diabetes: A nationwide, longitudinal observational study of 14,372 flash users compared with 7691 glucose sensor naive controls","volume":"64","author":"Nathanson","year":"2021","journal-title":"Diabetologia"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"113054","DOI":"10.1016\/j.bios.2021.113054","article-title":"Continuous glucose monitoring systems-Current status and future perspectives of the flagship technologies in biosensor research","volume":"181","author":"Lee","year":"2021","journal-title":"Biosens. Bioelectron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1210\/clinem\/dgad068","article-title":"The artificial pancreas and type 1 diabetes","volume":"108","author":"Nwokolo","year":"2023","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1111\/aor.13704","article-title":"The closed-loop artificial pancreas in 2020","volume":"44","author":"Fabris","year":"2020","journal-title":"Artif. Organs"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1621","DOI":"10.1177\/193229681300700623","article-title":"Algorithms for a closed-loop artificial pancreas: The case for proportional-integral-derivative control","volume":"7","author":"Steil","year":"2013","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1177\/193229681300700624","article-title":"Algorithms for a closed-loop artificial pancreas: The case for model predictive control","volume":"7","author":"Bequette","year":"2013","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1111\/dom.12852","article-title":"MD-Logic overnight type 1 diabetes control in home settings: A multicentre, multinational, single blind randomized trial","volume":"19","author":"Nimri","year":"2017","journal-title":"Diabetes Obes. Metab."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1111\/dom.14273","article-title":"Hybrid closed-loop therapy: Where are we in 2021?","volume":"23","author":"Leelarathna","year":"2021","journal-title":"Diabetes Obes. Metab."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1109\/TBME.2008.915665","article-title":"An improved PID switching control strategy for type 1 diabetes","volume":"55","author":"Marchetti","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1089\/dia.2018.0038","article-title":"Ongoing debate about models for artificial pancreas systems and in silico studies","volume":"20","author":"Forlenza","year":"2018","journal-title":"Diabetes Technol. Ther."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Matamoros-Alcivar, E., Ascencio-Lino, T., Fonseca, R., Villalba-Meneses, G., Tirado-Esp\u00edn, A., Barona, L., and Almeida-Gal\u00e1rraga, D. (2021, January 16\u201317). Implementation of MPC and PID control algorithms to the artificial pancreas for diabetes mellitus type 1. Proceedings of the 2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), Soyapango, El Salvador.","DOI":"10.1109\/ICMLANT53170.2021.9690529"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.conengprac.2018.05.006","article-title":"Model predictive control with integral action for artificial pancreas","volume":"77","author":"Incremona","year":"2018","journal-title":"Control Eng. Pract."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"\u00c7inar, S., Meng\u00fc\u00e7, E.C., and Acir, N. (2017, January 12\u201314). Automatic removal of ocular artefacts in EEG signal by using independent component analysis and Artificial Neural Network. Proceedings of the 2017 Medical Technologies National Congress (TIPTEKNO), Trabzon, Turkey.","DOI":"10.1109\/TIPTEKNO.2017.8238070"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1097\/MED.0000000000000599","article-title":"Advances in newer basal and bolus insulins: Impact on type 1 diabetes","volume":"28","author":"Vliebergh","year":"2021","journal-title":"Curr. Opin. Endocrinol. Diabetes Obes."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1586\/17434440.2013.827515","article-title":"The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas","volume":"10","author":"Bothe","year":"2013","journal-title":"Expert Rev. Med. Devices"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1111\/dom.13052","article-title":"The challenges of achieving postprandial glucose control using closed-loop systems in patients with type 1 diabetes","volume":"20","author":"Gingras","year":"2018","journal-title":"Diabetes Obes. Metab."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1089\/dia.2019.0502","article-title":"Modeling carbohydrate counting error in type 1 diabetes management","volume":"22","author":"Roversi","year":"2020","journal-title":"Diabetes Technol. Ther."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1111\/dme.13525","article-title":"Optimal prandial timing of bolus insulin in diabetes management: A review","volume":"35","author":"Slattery","year":"2018","journal-title":"Diabet. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s10846-017-0468-y","article-title":"Survey of model-based reinforcement learning: Applications on robotics","volume":"86","author":"Polydoros","year":"2017","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Terven, J. (2025). Deep reinforcement learning: A chronological overview and methods. AI, 6.","DOI":"10.3390\/ai6030046"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101836","DOI":"10.1016\/j.artmed.2020.101836","article-title":"Reinforcement learning application in diabetes blood glucose control: A systematic review","volume":"104","author":"Tejedor","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_29","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":"ref_30","unstructured":"Xie, J. (2024, November 03). Simglucose v0. 2.1 (2018). Available online: https:\/\/github.com\/jxx123\/simglucose."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhu, T., Li, K., and Georgiou, P. (2019). A dual-hormone closed-loop delivery system for type 1 diabetes using deep reinforcement learning. arXiv.","DOI":"10.1007\/978-3-030-53352-6_5"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Myhre, J.N., Launonen, I.K., Wei, S., and Godtliebsen, F. (2018, January 17\u201320). Controlling blood glucose levels in patients with type 1 diabetes using fitted q-iterations and functional features. Proceedings of the 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), Aalborg, Denmark.","DOI":"10.1109\/MLSP.2018.8516946"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4091497","DOI":"10.1155\/2018\/4091497","article-title":"Control of Blood Glucose for Type-1 Diabetes by Using Reinforcement Learning with Feedforward Algorithm","volume":"2018","author":"Ngo","year":"2018","journal-title":"Comput. Math. Methods Med."},{"key":"ref_34","unstructured":"Fox, I., Lee, J., Pop-Busui, R., and Wiens, J. (2020, January 7\u20138). Deep reinforcement learning for closed-loop blood glucose control. Proceedings of the 5th Machine Learning for Healthcare Conference, Virtual."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1109\/JBHI.2020.3002022","article-title":"Toward a fully automated artificial pancreas system using a bioinspired reinforcement learning design: In silico validation","volume":"25","author":"Lee","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Baldisseri, F., Menegatti, D., and Wrona, A. (2024, January 25\u201328). Deep Deterministic Policy Gradient Control of Type 1 Diabetes. Proceedings of the 2024 European Control Conference (ECC), Stockholm, Sweden.","DOI":"10.23919\/ECC64448.2024.10591007"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1109\/TNNLS.2017.2654539","article-title":"Safe exploration algorithms for reinforcement learning controllers","volume":"29","author":"Mannucci","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_38","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 Inform."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TBME.2024.3451712","article-title":"Hybrid control policy for artificial pancreas via ensemble deep reinforcement learning","volume":"72","author":"Lv","year":"2024","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"105756","DOI":"10.1109\/ACCESS.2021.3100007","article-title":"A blood glucose control framework based on reinforcement learning with safety and interpretability: In silico validation","volume":"9","author":"Lim","year":"2021","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"105839","DOI":"10.1016\/j.bspc.2023.105839","article-title":"G2P2C\u2014A modular reinforcement learning algorithm for glucose control by glucose prediction and planning in Type 1 Diabetes","volume":"90","author":"Hettiarachchi","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhao, Y.F., Chaw, J.K., Ang, M.C., Tew, Y., Shi, X.Y., Liu, L., and Cheng, X. (2025). A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0317662"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"104376","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."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Hettiarachchi, C., Malagutti, N., Nolan, C.J., Suominen, H., and Daskalaki, E. (2022, January 5\u20139). Non-linear continuous action spaces for reinforcement learning in type 1 diabetes. AI 2022: Advances in Artificial Intelligence, Proceedings of the Australasian Joint Conference on Artificial Intelligence, Perth, Australia.","DOI":"10.1007\/978-3-031-22695-3_39"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Hettiarachchi, C., Malagutti, N., Nolan, C., Daskalaki, E., and Suominen, H. (2022, January 11\u201315). A reinforcement learning based system for blood glucose control without carbohydrate estimation in type 1 diabetes: In silico validation. Proceedings of the 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, UK.","DOI":"10.1109\/EMBC48229.2022.9871054"},{"key":"ref_46","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_47","first-page":"1143","article-title":"Guidelines for the diagnosis and treatment of type 1 diabetes mellitus in China (2021 edition)","volume":"14","author":"Zhou","year":"2022","journal-title":"Chin. J. Diabetes Mellitus"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1056\/NEJMoa1002853","article-title":"Effectiveness of sensor-augmented insulin-pump therapy in type 1 diabetes","volume":"363","author":"Bergenstal","year":"2010","journal-title":"N. Engl. J. Med."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"American Diabetes Association Professional Practice Committee for Diabetes (2026). 14. Children and Adolescents: Standards of Care in Diabetes-2026. Diabetes Care, 49, S297\u2013S320.","DOI":"10.2337\/dc26-S014"}],"container-title":["Biosensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-6374\/16\/1\/47\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T11:27:22Z","timestamp":1767698842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-6374\/16\/1\/47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["bios16010047"],"URL":"https:\/\/doi.org\/10.3390\/bios16010047","relation":{},"ISSN":["2079-6374"],"issn-type":[{"value":"2079-6374","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}