{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T02:03:41Z","timestamp":1794967421147,"version":"4.9.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T00:00:00Z","timestamp":1696550400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T00:00:00Z","timestamp":1696550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Ministero dell\u2019Universit\u00e0 e della Ricerca,Italy","award":["PRIN: Progetti di Rilevante Interesse Nazionale, call 2020, project ID: 2020X7XX2P"],"award-info":[{"award-number":["PRIN: Progetti di Rilevante Interesse Nazionale, call 2020, project ID: 2020X7XX2P"]}],"id":[{"id":"https:\/\/ror.org\/0341vw408","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning has become a popular tool for learning models of complex dynamics from biomedical data. In Type 1 Diabetes (T1D) management, these models are increasingly been integrated in decision support systems (DSS) to forecast glucose levels and provide preventive therapeutic suggestions, like corrective insulin boluses (CIB), accordingly. Typically, models are chosen based on their prediction accuracy. However, since patient safety is a concern in this application, the algorithm should also be physiologically sound and its outcome should be explainable. This paper aims to discuss the importance of using tools to interpret the output of black-box models in T1D management by presenting a case-of-study on the selection of the best prediction algorithm to integrate in a DSS for CIB suggestion. By retrospectively \u201creplaying\u201d real patient data, we show that two long-short term memory neural networks (LSTM) (named p-LSTM and np-LSTM) with similar prediction accuracy could lead to different therapeutic decisions. An analysis with SHAP\u2014a tool for explaining black-box models\u2019 output\u2014unambiguously shows that only p-LSTM learnt the physiological relationship between inputs and glucose prediction, and should therefore be preferred. This is verified by showing that, when embedded in the DSS, only p-LSTM can improve patients\u2019 glycemic control.<\/jats:p>","DOI":"10.1038\/s41598-023-44155-x","type":"journal-article","created":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T09:02:14Z","timestamp":1696582934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":176,"title":["The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP"],"prefix":"10.1038","volume":"13","author":[{"given":"Francesco","family":"Prendin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacopo","family":"Pavan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Cappon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Del Favero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Sparacino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Facchinetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,6]]},"reference":[{"key":"44155_CR1","doi-asserted-by":"publisher","first-page":"S83","DOI":"10.2337\/dc22-S006","volume":"45","author":"ADAPP Committee","year":"2021","unstructured":"ADAPP Committee. Glycemic targets: Standards of medical care in diabetes-2022. Diabetes Care 45, S83\u2013S96. https:\/\/doi.org\/10.2337\/dc22-S006 (2021).","journal-title":"Diabetes Care"},{"key":"44155_CR2","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/S0140-6736(06)68341-4","volume":"367","author":"D Daneman","year":"2006","unstructured":"Daneman, D. Type 1 diabetes. Lancet 367, 847\u2013858 (2006).","journal-title":"Lancet"},{"key":"44155_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/nrdp.2017.16","volume":"3","author":"A Katsarou","year":"2017","unstructured":"Katsarou, A. et al. Type 1 diabetes mellitus. Nat. Rev. Dis. Primers 3, 1\u201317 (2017).","journal-title":"Nat. Rev. Dis. Primers"},{"key":"44155_CR4","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/j.ecl.2010.05.009","volume":"39","author":"LY Melendez-Ramirez","year":"2010","unstructured":"Melendez-Ramirez, L. Y., Richards, R. J. & Cefalu, W. T. Complications of type 1 diabetes. Endocrinol. Metab. Clin. 39, 625\u2013640 (2010).","journal-title":"Endocrinol. Metab. Clin."},{"key":"44155_CR5","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.2337\/db10-0103","volume":"59","author":"RJ McCrimmon","year":"2010","unstructured":"McCrimmon, R. J. & Sherwin, R. S. Hypoglycemia in type 1 diabetes. Diabetes 59, 2333\u20132339 (2010).","journal-title":"Diabetes"},{"key":"44155_CR6","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.1089\/dia.2015.0417","volume":"18","author":"D Rodbard","year":"2016","unstructured":"Rodbard, D. Continuous glucose monitoring: A review of successes, challenges, and opportunities. Diabetes Technol. Ther. 18, S2-3 (2016).","journal-title":"Diabetes Technol. Ther."},{"key":"44155_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2020.108502","volume":"170","author":"RJ Galindo","year":"2020","unstructured":"Galindo, R. J. & Aleppo, G. Continuous glucose monitoring: The achievement of 100 years of innovation in diabetes technology. Diabetes Res. Clin. Pract. 170, 108502 (2020).","journal-title":"Diabetes Res. Clin. Pract."},{"key":"44155_CR8","doi-asserted-by":"publisher","first-page":"383","DOI":"10.4093\/dmj.2019.0121","volume":"43","author":"G Cappon","year":"2019","unstructured":"Cappon, G., Vettoretti, M., Sparacino, G. & Facchinetti, A. Continuous glucose monitoring sensors for diabetes management: A review of technologies and applications. Diabetes Metab. J. 43, 383\u2013397 (2019).","journal-title":"Diabetes Metab. J."},{"key":"44155_CR9","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1089\/dia.2019.0139","volume":"21","author":"N Camerlingo","year":"2019","unstructured":"Camerlingo, N. et al. A real-time continuous glucose monitoring-based algorithm to trigger hypotreatments to prevent\/mitigate hypoglycemic events. Diabetes Technol. Ther. 21, 644\u2013655. https:\/\/doi.org\/10.1089\/dia.2019.0139 (2019).","journal-title":"Diabetes Technol. Ther."},{"key":"44155_CR10","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/JBHI.2018.2887067","volume":"23","author":"Q Sun","year":"2019","unstructured":"Sun, Q. et al. A dual mode adaptive basal-bolus advisor based on reinforcement learning. IEEE J. Biomed. Health Inform. 23, 2633\u20132641. https:\/\/doi.org\/10.1109\/JBHI.2018.2887067 (2019).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"44155_CR11","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1038\/s41591-020-1045-7","volume":"26","author":"R Nimri","year":"2020","unstructured":"Nimri, R. et al. Insulin dose optimization using an automated artificial intelligence-based decision support system in youths with type 1 diabetes. Nat. Med. 26, 1380\u20131384 (2020).","journal-title":"Nat. Med."},{"key":"44155_CR12","doi-asserted-by":"publisher","DOI":"10.3390\/s20113214","author":"N Tyler","year":"2020","unstructured":"Tyler, N. & Jacobs, P. Artificial intelligence in decision support systems for type 1 diabetes. Sensorshttps:\/\/doi.org\/10.3390\/s20113214 (2020).","journal-title":"Sensors"},{"key":"44155_CR13","doi-asserted-by":"crossref","unstructured":"Cappon, G. et\u00a0al. A new decision support system for type 1 diabetes management. in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 1993\u20131996 (IEEE, 2021).","DOI":"10.1109\/EMBC46164.2021.9629797"},{"key":"44155_CR14","first-page":"1","volume":"361","author":"E Bekiari","year":"2018","unstructured":"Bekiari, E. et al. Artificial pancreas treatment for outpatients with type 1 diabetes: Systematic review and meta-analysis. BJM 361, 1\u201310 (2018).","journal-title":"BJM"},{"key":"44155_CR15","doi-asserted-by":"publisher","first-page":"1795","DOI":"10.1007\/s00125-016-4022-4","volume":"59","author":"H Thabit","year":"2016","unstructured":"Thabit, H. & Hovorka, R. Coming of age: The artificial pancreas for type 1 diabetes. Diabetologia 59, 1795\u20131805 (2016).","journal-title":"Diabetologia"},{"key":"44155_CR16","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1111\/nyas.12431","volume":"1","author":"T Peyser","year":"2014","unstructured":"Peyser, T., Dassau, E., Breton, M. & Skyler, J. S. The artificial pancreas: Current status and future prospects in the management of diabetes. Ann. N. Y. Acad. Sci. 1, 102\u2013123 (2014).","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"44155_CR17","first-page":"07269","volume":"1706","author":"T Miller","year":"2018","unstructured":"Miller, T. Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 1706, 07269 (2018).","journal-title":"Artif. Intell."},{"key":"44155_CR18","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","volume":"2","author":"K Yu","year":"2018","unstructured":"Yu, K., Beam, A. & Kohane, I. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2, 719\u2013731. https:\/\/doi.org\/10.1038\/s41551-018-0305-z (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"44155_CR19","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MC.2018.3620965","volume":"51","author":"H Hagras","year":"2018","unstructured":"Hagras, H. Toward human-understandable, explainable AI. Computer 51, 28\u201336. https:\/\/doi.org\/10.1109\/MC.2018.3620965 (2018).","journal-title":"Computer"},{"key":"44155_CR20","volume-title":"Advances in Neural Information Processing Systems","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M. & Lee, S. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems Vol. 30 (eds Guyon, I. et al.) (Curran Associates, 2017)."},{"key":"44155_CR21","unstructured":"Alvarez-Melis, D. & Jaakkola, T.\u00a0S. On the robustness of interpretability methods. http:\/\/arxiv.org\/abs\/1806.08049 (2018)."},{"key":"44155_CR22","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. in International Conference on Machine Learning, 3145\u20133153 (PMLR, 2017)."},{"key":"44155_CR23","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/TAI.2021.3111138","volume":"2","author":"A Kumar","year":"2021","unstructured":"Kumar, A., Sehgal, K., Garg, P., Kamakshi, V. & Krishnan, N. C. Mace: Model agnostic concept extractor for explaining image classification networks. IEEE Trans. Artif. Intell. 2, 574\u2013583 (2021).","journal-title":"IEEE Trans. Artif. Intell."},{"key":"44155_CR24","first-page":"1","volume":"29","author":"X Chen","year":"2016","unstructured":"Chen, X. et al. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. Adv. Neural Inf. Process. Syst. 29, 1\u201310 (2016).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"44155_CR25","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2833","author":"S Oviedo","year":"2017","unstructured":"Oviedo, S., Veh\u00ed, J., Calm, R. & Armengol, J. A review of personalized blood glucose prediction strategies for t1dm patients. Int. J. Numer. Methods Biomed. Eng.https:\/\/doi.org\/10.1002\/cnm.2833 (2017).","journal-title":"Int. J. Numer. Methods Biomed. Eng."},{"key":"44155_CR26","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.1109\/JBHI.2020.3040225","volume":"25","author":"T Zhu","year":"2020","unstructured":"Zhu, T., Li, K., Herrero, P. & Georgiou, P. Deep learning for diabetes: A systematic review. IEEE J. Biomed. Health Inform. 25, 2744\u20132757 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"44155_CR27","unstructured":"Cappon, G. et\u00a0al. A personalized and interpretable deep learning based approach to predict blood glucose concentration in type 1 diabetes. in KDH@ ECAI, 75\u201379 (2020)."},{"key":"44155_CR28","doi-asserted-by":"crossref","unstructured":"De\u00a0Bois, M., El Yacoubi, M.\u00a0A. & Ammi, M. Interpreting deep glucose predictive models for diabetic people using retain. in International Conference on Pattern Recognition and Artificial Intelligence, 685\u2013694 (Springer, 2020).","DOI":"10.1007\/978-3-030-59830-3_59"},{"key":"44155_CR29","unstructured":"Rubin-Falcone, H., Fox, I. & Wiens, J. Deep residual time-series forecasting: Application to blood glucose prediction. in KDH@ ECAI (2020)."},{"key":"44155_CR30","unstructured":"Xie, J. & Wang, Q. Benchmark machine learning approaches with classical time series approaches on the blood glucose level prediction challenge. in KDH@ ECAI (2018)."},{"key":"44155_CR31","unstructured":"Martinsson, J. et\u00a0al. Automatic blood glucose prediction with confidence using recurrent neural networks. in KDH@ ECAI (2018)."},{"key":"44155_CR32","unstructured":"Zhu, T., Li, K., Herrero, P., Chen, J. & Georgiou, P. A deep learning algorithm for personalized blood glucose prediction. in KDH@ ECAI (2018)."},{"key":"44155_CR33","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/RBME.2009.2036073","volume":"1","author":"C Cobelli","year":"2009","unstructured":"Cobelli, C. et al. Diabetes: Models, signals, and control. IEEE Rev. Biomed. Eng. 1, 54\u201396. https:\/\/doi.org\/10.1109\/RBME.2009.2036073 (2009).","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"44155_CR34","doi-asserted-by":"crossref","unstructured":"Kushner, T., Sankaranarayanan, S. & Breton, M. Conformance verification for neural network models of glucose-insulin dynamics. in Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control, 1\u201312 (2020).","DOI":"10.1145\/3365365.3382210"},{"key":"44155_CR35","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1089\/dia.2020.0061","volume":"22","author":"T Kushner","year":"2020","unstructured":"Kushner, T., Breton, M. D. & Sankaranarayanan, S. Multi-hour blood glucose prediction in type 1 diabetes: A patient-specific approach using shallow neural network models. Diabetes Technol. Ther. 22, 883\u2013891 (2020).","journal-title":"Diabetes Technol. Ther."},{"key":"44155_CR36","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.2337\/dci19-0028","volume":"42","author":"T Battelino","year":"2019","unstructured":"Battelino, T. et al. Clinical targets for continuous glucose monitoring data interpretation: Recommendations from the international consensus on time in range. Diabetes Care 42, 1593\u20131603 (2019).","journal-title":"Diabetes Care"},{"key":"44155_CR37","first-page":"71","volume":"2675","author":"C Marling","year":"2020","unstructured":"Marling, C. & Bunescu, R. The ohiot1dm dataset for blood glucose level prediction: Update 2020. CEUR Workshop Proc. 2675, 71\u201374 (2020).","journal-title":"CEUR Workshop Proc."},{"key":"44155_CR38","doi-asserted-by":"publisher","first-page":"3303","DOI":"10.3390\/s21093303","volume":"21","author":"J Beauchamp","year":"2021","unstructured":"Beauchamp, J., Bunescu, R., Marling, C., Li, Z. & Liu, C. Lstms and deep residual networks for carbohydrate and bolus recommendations in type 1 diabetes management. Sensors 21, 3303 (2021).","journal-title":"Sensors"},{"key":"44155_CR39","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1177\/193229680900300319","volume":"3","author":"C Ellingsen","year":"2009","unstructured":"Ellingsen, C. et al. Safety constraints in an artificial pancreatic $$\\beta$$ cell: An implementation of model predictive control with insulin on board. J. Diabetes Sci. Technol. 3, 536\u2013544 (2009).","journal-title":"J. Diabetes Sci. Technol."},{"key":"44155_CR40","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.2337\/dc13-1120","volume":"37","author":"M Schiavon","year":"2014","unstructured":"Schiavon, M., Dalla Man, C., Kudva, Y. C., Basu, A. & Cobelli, C. Quantitative estimation of insulin sensitivity in type 1 diabetic subjects wearing a sensor-augmented insulin pump. Diabetes Care 37, 1216\u20131223 (2014).","journal-title":"Diabetes Care"},{"key":"44155_CR41","doi-asserted-by":"publisher","first-page":"2986","DOI":"10.1109\/TBME.2012.2192930","volume":"59","author":"SD Patek","year":"2012","unstructured":"Patek, S. D. et al. Modular closed-loop control of diabetes. IEEE Trans. Biomed. Eng. 59, 2986\u20132999 (2012).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"44155_CR42","doi-asserted-by":"crossref","unstructured":"Turksoy, K., Bayrak, E.\u00a0S., Quinn, L., Littlejohn, E. & Cinar, A. Adaptive multivariable closed-loop control of blood glucose concentration in patients with type 1 diabetes. in 2013 American Control Conference, 2905\u20132910 (IEEE, 2013).","DOI":"10.1109\/ACC.2013.6580275"},{"key":"44155_CR43","doi-asserted-by":"publisher","first-page":"2079","DOI":"10.1109\/TBME.2017.2784101","volume":"65","author":"M Schiavon","year":"2017","unstructured":"Schiavon, M., Dalla Man, C. & Cobelli, C. Modeling subcutaneous absorption of fast-acting insulin in type 1 diabetes. IEEE Trans. Biomed. Eng. 65, 2079\u20132086 (2017).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"44155_CR44","unstructured":"Pavan, J. et\u00a0al. Personalized machine learning algorithm based on shallow network and error imputation module for an improved blood glucose prediction. in KDH@ ECAI, 95\u201399 (2020)."},{"key":"44155_CR45","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/TBME.2012.2188893","volume":"59","author":"C Zecchin","year":"2012","unstructured":"Zecchin, C., Facchinetti, A., Sparacino, G., De Nicolao, G. & Cobelli, C. Neural network incorporating meal information improves accuracy of short-time prediction of glucose concentration. IEEE Trans. Biomed. Eng. 59, 1550\u20131560 (2012).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"44155_CR46","doi-asserted-by":"crossref","unstructured":"Mirshekarian, S., Bunescu, R., Marling, C. & Schwartz, F. Using lstms to learn physiological models of blood glucose behavior. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2887\u20132891 (IEEE, 2017).","DOI":"10.1109\/EMBC.2017.8037460"},{"key":"44155_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-021-01462-5","volume":"21","author":"MF Rabby","year":"2021","unstructured":"Rabby, M. F. et al. Stacked lstm based deep recurrent neural network with Kalman smoothing for blood glucose prediction. BMC Med. Inform. Decis. Mak. 21, 1\u201315 (2021).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"44155_CR48","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1177\/193229681300700415","volume":"7","author":"C Toffanin","year":"2013","unstructured":"Toffanin, C., Zisser, H., Doyle, F. J. III. & Dassau, E. Dynamic insulin on board: Incorporation of circadian insulin sensitivity variation. J. Diabetes Sci. Technol. 7, 928\u2013940 (2013).","journal-title":"J. Diabetes Sci. Technol."},{"key":"44155_CR49","first-page":"10464","volume":"1903","author":"K Aas","year":"2020","unstructured":"Aas, K., Jullum, M. & L\u00f8land, A. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artif. Intell. 1903, 10464 (2020).","journal-title":"Artif. Intell."},{"key":"44155_CR50","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2023.3286856","author":"G Cappon","year":"2023","unstructured":"Cappon, G., Vettoretti, M., Sparacino, G., Del Favero, S. & Facchinetti, A. Replaybg: A digital twin-based methodology to identify a personalized model from type 1 diabetes data and simulate glucose concentrations to assess alternative therapies. IEEE Trans. Biomed. Eng.https:\/\/doi.org\/10.1109\/TBME.2023.3286856 (2023).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"44155_CR51","doi-asserted-by":"publisher","first-page":"E667","DOI":"10.1152\/ajpendo.1979.236.6.E667","volume":"236","author":"R Bergman","year":"1979","unstructured":"Bergman, R., Ider, Y., Bowden, C. & Cobelli, C. Quantitative estimation of insulin sensitivity. Am. J. Physiol. 236, E667-77. https:\/\/doi.org\/10.1152\/ajpendo.1979.236.6.E667 (1979).","journal-title":"Am. J. Physiol."},{"key":"44155_CR52","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1089\/dia.2017.0248","volume":"20","author":"M Schiavon","year":"2018","unstructured":"Schiavon, M., Dalla Man, C. & Cobelli, C. Insulin sensitivity index-based optimization of insulin to carbohydrate ratio: In silico study shows efficacious protection against hypoglycemic events caused by suboptimal therapy. Diabetes Technol. Ther. 20, 98\u2013105. https:\/\/doi.org\/10.1089\/dia.2017.0248 (2018).","journal-title":"Diabetes Technol. Ther."},{"key":"44155_CR53","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1109\/TBME.2007.893506","volume":"54","author":"C Dalla Man","year":"2007","unstructured":"Dalla Man, C., Rizza, R. & Cobelli, C. Meal simulation model of the glucose-insulin system. IEEE Trans. Biomed. Eng. 54, 1740\u20131749 (2007).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"44155_CR54","doi-asserted-by":"crossref","unstructured":"Toffanin, C. et\u00a0al. Artificial pancreas: model predictive control design from clinical experience (2013).","DOI":"10.1177\/193229681300700607"},{"key":"44155_CR55","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jprocont.2019.03.009","volume":"77","author":"I Hajizadeh","year":"2019","unstructured":"Hajizadeh, I., Rashid, M. & Cinar, A. Plasma-insulin-cognizant adaptive model predictive control for artificial pancreas systems. J. Process Control 77, 97\u2013113 (2019).","journal-title":"J. Process Control"},{"key":"44155_CR56","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1109\/TCST.2022.3195072","volume":"31","author":"J Pavan","year":"2022","unstructured":"Pavan, J., Salvagnin, D., Facchinetti, A., Sparacino, G. & Del Favero, S. Incorporating sparse and quantized carbohydrates suggestions in model predictive control for artificial pancreas in type 1 diabetes. IEEE Trans. Control Syst. Technol. 31, 570\u2013586 (2022).","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"44155_CR57","doi-asserted-by":"publisher","DOI":"10.2337\/dc12-0660","volume":"35","author":"C Cobelli","year":"2012","unstructured":"Cobelli, C. et al. Pilot studies of wearable outpatient artificial pancreas in type 1 diabetes. Diabetes Care 35, e65 (2012).","journal-title":"Diabetes Care"},{"key":"44155_CR58","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.2337\/dc13-1631","volume":"37","author":"S Del Favero","year":"2014","unstructured":"Del Favero, S. et al. First use of model predictive control in outpatient wearable artificial pancreas. Diabetes Care 37, 1212\u20131215 (2014).","journal-title":"Diabetes Care"},{"key":"44155_CR59","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.2337\/db11-1445","volume":"61","author":"M Breton","year":"2012","unstructured":"Breton, M. et al. Fully integrated artificial pancreas in type 1 diabetes: Modular closed-loop glucose control maintains near normoglycemia. Diabetes 61, 2230\u20132237 (2012).","journal-title":"Diabetes"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-44155-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-44155-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-44155-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T15:31:15Z","timestamp":1700321475000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-44155-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,6]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["44155"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-44155-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,6]]},"assertion":[{"value":"23 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16865"}}