BEYOND THE ALGORITHM: A SYSTEMATIC REVIEW OF AI-DRIVEN DIGITAL TWINS IN GLYCEMIC CONTROL AND DECISION SUPPORT FOR TYPE 1 DIABETES

Authors

DOI:

https://doi.org/10.31435/ijitss.4(52).2026.6584

Keywords:

Type 1 Diabetes, Digital Twin, Artificial Intelligence, Continuous Glucose Monitoring, Machine Learning, Decision Support System

Abstract

Background: Managing type 1 diabetes requires continuous adaptation to metabolic fluctuations. Standard automated systems use static rules rather than dynamic, patient-specific models. AI-driven Digital Twins (DTs) overcome this by pairing continuous multimodal data with virtual patient representations for proactive therapy optimization.

Aim: This systematic review characterizes AI-driven DTs for T1D glycemic control, evaluating their underlying architectures (data-driven, mechanistic, hybrid), multimodal data integration, decision-support translation, and clinical validation levels.

Methods: Following PRISMA guidelines, a PubMed search yielded 443 unique records after duplicate removal. Five independent reviewers screened articles using PICOS criteria. Ultimately, 42 studies (including 11 randomized trials) evaluating AI-driven DTs or predictive models in T1D were included for qualitative synthesis.

Results: Most systems rely on continuous glucose monitoring (97.6%), while 40.5% incorporate the complete "metabolic triad" (CGM, insulin, carbohydrates). Architectures are shifting toward closed-loop paradigms combining patient-state estimation and adaptive feedback. Clinically, DT integration increased Time in Range by 7–26 percentage points (adding 3.0–6.2 hours daily), reduced Time Below Range (<4%), and lowered HbA1c by 0.32%–1.05% without severe adverse events. Capabilities range from short-term forecasting (30–120 minutes) to counterfactual simulation and autonomous closed-loop delivery. Hybrid models combining physiological mechanisms with machine learning represent the emerging standard.

Conclusions: AI-driven DTs advance T1D care by enabling dynamic, personalized decision-making and automated control. However, widespread clinical implementation requires addressing technical complexity, establishing standardized architectures, and conducting robust prospective validation under real-world conditions.

References

Tyler, N. S., & Jacobs, P. G. (2020). Artificial intelligence in decision support systems for type 1 diabetes. Sensors (Basel, Switzerland), 20(11), 3214. https://doi.org/10.3390/s20113214

Thabit, H., Tauschmann, M., Allen, J. M., Leelarathna, L., Hartnell, S., Wilinska, M. E., Acerini, C. L., Dellweg, S., Benesch, C., Heinemann, L., Mader, J. K., Holzer, M., Kojzar, H., Exall, J., Yong, J., Pichierri, J., Barnard, K. D., Kollman, C., Cheng, P., Hindmarsh, P. C., … New Collective Author (2015). Home use of an artificial beta cell in type 1 diabetes. The New England journal of medicine, 373(22), 2129–2140. https://doi.org/10.1056/NEJMoa150935

Brown, S. A., Kovatchev, B. P., Raghinaru, D., Lum, J. W., Buckingham, B. A., Kudva, Y. C., Laffel, L. M., Levy, C. J., Pinsker, J. E., Wadwa, R. P., Dassau, E., Doyle, F. J., 3rd, Anderson, S. M., Church, M. M., Dadlani, V., Ekhlaspour, L., Forlenza, G. P., Isganaitis, E., Lam, D. W., Kollman, C., … iDCL Trial Research Group (2019). Six-month randomized, multicenter trial of closed-loop control in type 1 diabetes. The New England journal of medicine, 381(18), 1707–1717. https://doi.org/10.1056/NEJMoa1907863

Cappon, G., & Facchinetti, A. (2025). Digital twins in type 1 diabetes: A systematic review. Journal of diabetes science and technology, 19(6), 1641–1649. https://doi.org/10.1177/19322968241262112

Young, G., Dodier, R., Youssef, J. E., Castle, J. R., Wilson, L., Riddell, M. C., & Jacobs, P. G. (2024). Design and in silico evaluation of an exercise decision support system using digital twin models. Journal of diabetes science and technology, 18(2), 324–334. https://doi.org/10.1177/19322968231223217

Ahmadasas, M., Inanc, E., Ozkara, E., Siket, M., Rashid, M. M., Bilgic, M., Quinn, L., & Cinar, A. (2025). Cyber-physical-human systems in precision medicine: Advances in artificial pancreas for treatment of diabetes. Annual reviews in control, 60, 101033. https://doi.org/10.1016/j.arcontrol.2025.101033

Herrero, P., Andorrà, M., Breton, M. D., Peak, A., Koehler, M., Klopfenstein, Y., Leppäaho, E., Zanon, M., Ringemann, C., Lustenberger, P., & Glatzer, T. (2026). Glucose predictions improve glycemic control: A digital twin evaluation. Diabetes technology & therapeutics, 15209156261432144. Advance online publication. https://doi.org/10.1177/15209156261432144

Rubin-Falcone, H., Lee, J. M., & Wiens, J. (2024). Learning control-ready forecasters for blood glucose management. Computers in biology and medicine, 180, 108995. https://doi.org/10.1016/j.compbiomed.2024.108995

Nemat, H., Khadem, H., Eissa, M. R., Elliott, J., & Benaissa, M. (2022). Blood glucose level prediction: Advanced deep-ensemble learning approach. IEEE journal of biomedical and health informatics, 26(6), 2758–2769. https://doi.org/10.1109/JBHI.2022.3144870

Zhu, T., Kuang, L., Piao, C., Zeng, J., Li, K., & Georgiou, P. (2024). Population-specific glucose prediction in diabetes care with transformer-based deep learning on the edge. IEEE transactions on biomedical circuits and systems, 18(2), 236–246. https://doi.org/10.1109/TBCAS.2023.3348844

Schmitzer, J., Strobel, C., Blechschmidt, R., Tappe, A., & Peuscher, H. (2022). Efficient closed loop simulation of do-it-yourself artificial pancreas systems. Journal of diabetes science and technology, 16(1), 61–69. https://doi.org/10.1177/19322968211032249

Krishnamoorthy, D., & Doyle Iii, F. J. (2023). Safe and personalized meal bolus calculator for type-1 diabetes using bayesian optimization. IEEE transactions on bio-medical engineering, 70(5), 1481–1492. https://doi.org/10.1109/TBME.2022.3219370

Cappon, G., Noaro, G., Camerlingo, N., Cossu, L., Sparacino, G., & Facchinetti, A. (2021). A new decision support system for type 1 diabetes management. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2021, 1993–1996. https://doi.org/10.1109/EMBC46164.2021.9629797

Daniels, J., Herrero, P., & Georgiou, P. (2022). A multitask learning approach to personalized blood glucose prediction. IEEE journal of biomedical and health informatics, 26(1), 436–445. https://doi.org/10.1109/JBHI.2021.3100558

Zhu, T., Kuang, L., Piao, C., Zeng, J., Li, K., & Georgiou, P. (2024). Population-specific glucose prediction in diabetes care with transformer-based deep learning on the edge. IEEE transactions on biomedical circuits and systems, 18(2), 236–246. https://doi.org/10.1109/TBCAS.2023.3348844

Diamond, T., Cameron, F., & Bequette, B. W. (2022). A new meal absorption model for artificial pancreas systems. Journal of diabetes science and technology, 16(1), 40–51. https://doi.org/10.1177/1932296821990111

Ahmad, S., Beneyto, A., Zhu, T., Contreras, I., Georgiou, P., & Vehi, J. (2024). An automatic deep reinforcement learning bolus calculator for automated insulin delivery systems. Scientific reports, 14(1), 15245. https://doi.org/10.1038/s41598-024-62912-4

Askari, M. R., Ahmadasas, M., Shahidehpour, A., Rashid, M., Quinn, L., Park, M., & Cinar, A. (2023). Multivariable automated insulin delivery system for handling planned and spontaneous physical activities. Journal of diabetes science and technology, 17(6), 1456–1469. https://doi.org/10.1177/19322968231204884

Smaoui, M. R., & Lafi, A. (2022). Leeno: Type 1 diabetes management training environment using smart algorithms. PloS one, 17(9), e0274534. https://doi.org/10.1371/journal.pone.0274534

Batmani, Y., Khodakaramzadeh, S., & Moradi, P. (2022). Automatic artificial pancreas systems using an intelligent multiple-model pid strategy. IEEE journal of biomedical and health informatics, 26(4), 1708–1717. https://doi.org/10.1109/JBHI.2021.3116376

Ahmad, S., Beneyto, A., Contreras, I., & Vehi, J. (2022). Bolus insulin calculation without meal information. A reinforcement learning approach. Artificial intelligence in medicine, 134, 102436. https://doi.org/10.1016/j.artmed.2022.102436

Xiong, X., Xue, Y., Cai, Y., He, J., & Su, H. (2024). Prediction of personalised postprandial glycaemic response in type 1 diabetes mellitus. Frontiers in endocrinology, 15, 1423303. https://doi.org/10.3389/fendo.2024.1423303

Wilmot, E. G., Moore, P., Sathyapalan, T., Choudhary, P., Lim, J. Z. M., Neupane, S., Crabtree, T. S. J., Iqbal, A., Evans, M. L., Rayman, G., Price, H. C., Ajjan, R. A., Cheah, Y. S., Lumb, A., Mostafa, S., Malik, I., Cranston, I., Min, T., Jude, E. B., Seechurn, S., … FreeDM2 Study Group (2026). Continuous glucose monitoring versus self-monitoring of blood glucose in individuals with type 2 diabetes: A randomised, multicentre, open-label, superiority trial. The lancet. Diabetes & endocrinology, 14(6), 463–474. https://doi.org/10.1016/S2213-8587(26)00076-8

Jacobs, P. G., Resalat, N., Hilts, W., Young, G. M., Leitschuh, J., Pinsonault, J., El Youssef, J., Branigan, D., Gabo, V., Eom, J., Ramsey, K., Dodier, R., Mosquera-Lopez, C., Wilson, L. M., & Castle, J. R. (2023). Integrating metabolic expenditure information from wearable fitness sensors into an AI-augmented automated insulin delivery system: A randomised clinical trial. The Lancet. Digital health, 5(9), e607–e617. https://doi.org/10.1016/S2589-7500(23)00112-7

Ware, J., Boughton, C. K., Allen, J. M., Wilinska, M. E., Tauschmann, M., Denvir, L., Thankamony, A., Campbell, F. M., Wadwa, R. P., Buckingham, B. A., Davis, N., DiMeglio, L. A., Mauras, N., Besser, R. E. J., Ghatak, A., Weinzimer, S. A., Hood, K. K., Fox, D. S., Kanapka, L., Kollman, C., … DAN05 Consortium (2022). Cambridge hybrid closed-loop algorithm in children and adolescents with type 1 diabetes: A multicentre 6-month randomised controlled trial. The Lancet. Digital health, 4(4), e245–e255. https://doi.org/10.1016/S2589-7500(22)00020-6

den Brok, E. J., Svensson, C. H., Olsen, M. T., Dimitropoulou, N. M., van Kuijk, S. M. J., Panagiotou, M., Abdur Rahman, L., Proennecke, S., Mertens, P. R., Athanasopoulos, S., Dingena, C. F., Makrilakis, K., Mougiakakou, S., Pedersen-Bjergaard, U., de Galan, B. E., & MELISSA consortium (2026). Randomised controlled multicentre trial to investigate the effectiveness of a mobile artificial intelligence solution for diabetes adapted care: The melissa trial protocol. Diabetes, obesity & metabolism, 28(8), 6576–6583. https://doi.org/10.1111/dom.70879

Matejko, B., Cyranka, K., Suduł, P., Susuł, K., Krężel, J., Chernovol, J., Maga, P., Malecki, M. T., & Klupa, T. (2026). Metabolic and vascular outcomes after transition to the minimed 780g system in adults ≥65 years with type 1 diabetes: A randomised, single-centre study. Diabetologia, 69(9), 2421–2431. https://doi.org/10.1007/s00125-026-06780-9

Fox, D. S., Ware, J., Boughton, C. K., Allen, J. M., Wilinska, M. E., Tauschmann, M., Denvir, L., Thankamony, A., Campbell, F., Wadwa, R. P., Buckingham, B. A., Davis, N., DiMeglio, L. A., Mauras, N., Besser, R. E. J., Ghatak, A., Weinzimer, S. A., Kanapka, L., Kollman, C., Sibayan, J., … Hovorka, R. (2025). Cost-effectiveness of closed-loop automated insulin delivery using the cambridge hybrid algorithm in children and adolescents with type 1 diabetes: Results from a multicenter 6-month randomized trial. Journal of diabetes science and technology, 19(4), 982–991. https://doi.org/10.1177/19322968241231950

Kobayati, A., El Fathi, A., Garfield, N., Legault, L., Jafar, A., Yale, J. F., Tsoukas, M. A., & Haidar, A. (2025). A bayesian decision support system for automated insulin doses in adults with type 1 diabetes on multiple daily injections: A randomized controlled trial. Nature communications, 16(1), 8593. https://doi.org/10.1038/s41467-025-63671-0

Roy, A., Grosman, B., Benedetti, A., Engheta, B., Miller, D., Laron-Hirsh, M., Cohen, Y., Ré, R., Edd, S. N., Vigersky, R., Cohen, O., & Tirosh, A. (2024). An automated insulin delivery system with automatic meal bolus based on a hand-gesturing algorithm. Diabetes technology & therapeutics, 26(9), 633–643. https://doi.org/10.1089/dia.2023.0529

Pryor, E. C., Moscoso-Vasquez, M., Fulkerson, D., Holmes, V., Prince, S. D., Koravi, C. L. K., El Fathi, A., Brown, S. A., DeBoer, M. D., & Breton, M. D. (2025). Miniaturized neural networks for deploying fully closed loop insulin delivery systems: A pilot study featuring flexible meal announcement options. Journal of diabetes science and technology, 19(6), 1464–1470. https://doi.org/10.1177/19322968251364283

Builes-Montaño, C. E., Lema-Perez, L., Ramírez-Rincón, A., Zuleta-Tobón, J. J., Restrepo-Gutiérrez, J. C., Álvarez-Zapata, H. D., & García-Tirado, J. (2025). A digital twin-enhanced decision support system improves time-in-range in type 1 diabetes: A randomized clinical trial. Scientific reports, 15(1), 39738. https://doi.org/10.1038/s41598-025-23165-x

Piersanti, A., Manes, G. M., Del Giudice, L. L., Burattini, L., Göbl, C., Tura, A., & Morettini, M. (2026). Prediction of nocturnal hypoglycemia following exercise in type 1 diabetes using temporally structured CGM-derived digital biomarkers. Sensors (Basel, Switzerland), 26(12), 3842. https://doi.org/10.3390/s26123842

Alkhateeb, M., AlSaad, R., Brahim Belhaouari, S., Aziz, S., Ahmed, A., Ali, H., Al-Mohanadi, D., Mohamud, K., Al-Naimi, N., Alsaud, A., Al-Sharshani, H., Sheikh, J. I., Baagar, K., & Abd-Alrazaq, A. (2026). Temporal and behaviour-aware multimodal modelling for hour-ahead hypoglycaemia prediction during ramadan fasting in type 1 diabetes. Sensors (Basel, Switzerland), 26(8), 2552. https://doi.org/10.3390/s26082552

Sakane, N., Hirota, Y., Yamamoto, A., Miura, J., Takaike, H., Hoshina, S., Toyoda, M., Saito, N., Hosoda, K., Matsubara, M., Tone, A., Kawashima, S., Sawaki, H., Matsuda, T., Domichi, M., Suganuma, A., Sakane, S., & Murata, T. (2026). A machine learning approach to predicting severe diabetes distress in adults with type 1 diabetes mellitus. Journal of diabetes investigation, 17(4), 689–697. https://doi.org/10.1111/jdi.70229

Hughes, J., Gautier, T., Colmegna, P., Fabris, C., & Breton, M. D. (2021). Replay simulations with personalized metabolic model for treatment design and evaluation in type 1 diabetes. Journal of diabetes science and technology, 15(6), 1326–1336. https://doi.org/10.1177/1932296820973193

Beolet, T., Adenis, A., Huneker, E., & Louis, M. (2024). End-to-end offline reinforcement learning for glycemia control. Artificial intelligence in medicine, 154, 102920. https://doi.org/10.1016/j.artmed.2024.102920

Cinar, B., & Maleshkova, M. (2025). Benchmarking hypoglycemia classification using quality-enhanced DiaData. IEEE journal of biomedical and health informatics, 29(12), 8831–8838. https://doi.org/10.1109/JBHI.2025.3620603

Lv, W., Wu, T., Xiong, L., Wu, L., Zhou, J., Tang, Y., & Qian, F. (2025). Hybrid control policy for artificial pancreas via ensemble deep reinforcement learning. IEEE transactions on bio-medical engineering, 72(1), 309–323. https://doi.org/10.1109/TBME.2024.3451712

Zhu, T., Afentakis, I., Li, K., Armiger, R., Hill, N., Oliver, N., & Georgiou, P. (2025). Multi-horizon glucose prediction across populations with deep domain generalization. IEEE journal of biomedical and health informatics, 29(8), 5424–5437. https://doi.org/10.1109/JBHI.2024.3428921

Duckworth, C., Guy, M. J., Kumaran, A., O'Kane, A. A., Ayobi, A., Chapman, A., Marshall, P., & Boniface, M. (2024). Explainable machine learning for real-time hypoglycemia and hyperglycemia prediction and personalized control recommendations. Journal of diabetes science and technology, 18(1), 113–123. https://doi.org/10.1177/19322968221103561

Yang, H., Chen, Z., Huang, J., & Li, S. (2024). Awd-stacking: An enhanced ensemble learning model for predicting glucose levels. PloS one, 19(2), e0291594. https://doi.org/10.1371/journal.pone.0291594

Marchetti, A., Sasso, D., D'Antoni, F., Morandin, F., Parton, M., Matarrese, M. A. G., & Merone, M. (2025). Deep reinforcement learning for type 1 diabetes: Dual PPO controller for personalized insulin management. Computers in biology and medicine, 191, 110147. https://doi.org/10.1016/j.compbiomed.2025.110147

Kovatchev, B., Castillo, A., Pryor, E., Kollar, L. L., Barnett, C. L., DeBoer, M. D., & Brown, S. A. (2024). Neural-net artificial pancreas: A randomized crossover trial of a first-in-class automated insulin delivery algorithm. Diabetes technology & therapeutics, 26(6), 375–382. https://doi.org/10.1089/dia.2023.0469

Ibrahim, M., Beneyto, A., Contreras, I., & Vehi, J. (2024). An ensemble machine learning approach for the detection of unannounced meals to enhance postprandial glucose control. Computers in biology and medicine, 171, 108154. https://doi.org/10.1016/j.compbiomed.2024.108154

Unsworth, R., Armiger, R., Jugnee, N., Thomas, M., Herrero, P., Georgiou, P., Oliver, N., & Reddy, M. (2023). Safety and efficacy of an adaptive bolus calculator for type 1 diabetes: A randomized controlled crossover study. Diabetes technology & therapeutics, 25(6), 414–425. https://doi.org/10.1089/dia.2022.0504

Harvengt, A., Bastin, M., Toussaint, C., Beckers, M., Helleputte, T., & Lysy, P. (2025). Development of a prediction model for severe hypoglycemia in children and adolescents with type 1 diabetes: The epi-gluredia study. Nutrients, 17(16), 2610. https://doi.org/10.3390/nu17162610

Hettiarachchi, C., Malagutti, N., Nolan, C., Daskalaki, E., & Suominen, H. (2022). A reinforcement learning based system for blood glucose control without carbohydrate estimation in type 1 diabetes: In silico validation. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2022, 950–956. https://doi.org/10.1109/EMBC48229.2022.9871054

Pellizzari, E., Cappon, G., Sparacino, G., Deodati, A., Schiaffini, R., Cianfarani, S., & Facchinetti, A. (2025). Digital-twin based optimization of bolus insulin dosing in pediatric type 1 diabetes: An in silico feasibility study. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2025, 1–5. https://doi.org/10.1109/EMBC58623.2025.11253829

Downloads

Published

2026-10-19

How to Cite

Światlak, K., Trzaskalik, J., Żelazna , W. ., Sokołowski , J., & Leśniak , M. . (2026). BEYOND THE ALGORITHM: A SYSTEMATIC REVIEW OF AI-DRIVEN DIGITAL TWINS IN GLYCEMIC CONTROL AND DECISION SUPPORT FOR TYPE 1 DIABETES. International Journal of Innovative Technologies in Social Science, 1(4(52). https://doi.org/10.31435/ijitss.4(52).2026.6584

Most read articles by the same author(s)