CoChat
Sign Up
Cited by 113Diabetes Management and ResearchArtificial Intelligence in HealthcareMachine Learning in Healthcare

Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities

Open access
Jacobs, Peter G., Herrero, Pau, Facchinetti, Andrea, Vehi, Josep, Kovatchev, Boris, Breton, Marc D., Cinar, Ali, Nikita, Konstantina S. +7 more·2024·IEEE Reviews in Biomedical Engineering
DOI 10.1109/rbme.2023.3331297
Open this paper in CoChat — free accountOpen PDF

Abstract

OBJECTIVE: Artificial intelligence and machine learning are transforming many fields including medicine. In diabetes, robust biosensing technologies and automated insulin delivery therapies have created a substantial opportunity to improve health. While the number of manuscripts addressing the topic of applying machine learning to diabetes has grown in recent years, there has been a lack of consistency in the methods, metrics, and data used to train and evaluate these algorithms. This manuscript provides consensus guidelines for machine learning practitioners in the field of diabetes, including best practice recommended approaches and warnings about pitfalls to avoid. METHODS: Algorithmic approaches are reviewed and benefits of different algorithms are discussed including importance of clinical accuracy, explainability, interpretability, and personalization. We review the most common features used in machine learning applications in diabetes glucose control and provide an open-source library of functions for calculating features, as well as a framework for specifying data sets using data sheets. A review of current data sets available for training algorithms is provided as well as an online repository of data sources. SIGNIFICANCE: These consensus guidelines are designed to improve performance and translatability of new machine learning algorithms developed in the field of diabetes for engineers and data scientists.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/rbme.2023.3331297

Cites

28 of 28 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Conventional risk prediction models for DKD, such as linear regression, face significant limitations in capturing complex nonlinear relationships and interactions among multidimensional risk factors.

    “Conventional risk prediction models for DKD, such as linear regression, estimate risk by calculating a weighted sum of known risk factors (8–10). While these models are effective when a limited number of variables or predictors are involved, they face significant limitations in capturing the complex nonlinear relationships and interactions among multidimensional risk factors (11, 12).”

    From Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis (2025) · cites this paper as [12]

    In the Best practice 14 passage (page unavailable), the review says a simple linear regression predictor works well when glucose changes at a constant rate, supporting a limited point about when that model is useful. It does not address DKD risk prediction or say that conventional models fail to capture nonlinear interactions among multidimensional risk factors. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 160

  1. A. Katsarou et al., "Type 1 diabetes mellitus," Nature Rev. Dis. Primers, vol. 3, Mar. 2017, Art. no. 17016.
  2. K. K. Dhatariya et al., "Diabetic ketoacidosis," Nature Rev. Dis. Primers, vol. 6, May 2020, Art. no. 40.
  3. J. L. Chiang et al., "Type 1 diabetes through the life span: A position statement of the American Diabetes Association," Diabetes Care, vol. 37, pp. 2034-2054, Jul. 2014.
  4. "Gestational diabetes mellitus," Diabetes Care, vol. 27, pp. S88-S90, Jan. 2004.
  5. R. Hovorka, "Closed-loop insulin delivery: From bench to clinical prac- tice," Nature Rev. Endocrinol., vol. 7, pp. 385-395, Jul. 2011.
  6. L. M. Wilson et al., "Opportunities and challenges in closed-loop sys- tems in type 1 diabetes," Lancet Diabetes Endocrinol., vol. 10, pp. 6-8, Jan. 2022.
  7. O. Moser et al., "Glucose management for exercise using continuous glucose monitoring (CGM) and intermittently scanned CGM (isCGM) systems in type 1 diabetes: Position statement of the European associ- ation for the study of diabetes (EASD) and of the international society for pediatric and adolescent diabetes (ISPAD) endorsed by JDRF and supported by the American diabetes association (ADA)," Diabetologia, vol. 63, no. 12, pp. 2501-2520, Oct. 2020.
  8. B. P. Kovatchev et al., "Evening and overnight closed-loop control versus 24/7 continuous closed-loop control for type 1 diabetes: A randomised crossover trial," Lancet Digit. Health, vol. 2, pp. e64-e73, Feb. 2020.
  9. B. Lobo et al., "A data-driven approach to classifying daily continuous glucose monitoring (CGM) time series," IEEE Trans. Biomed. Eng., vol. 69, no. 2, pp. 654-665, Feb. 2022.
  10. M. K. Bothe et al., "The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas," Expert Rev. Med. Devices, vol. 10, pp. 661-673, Sep. 2013.
  11. T. Zhu et al., "Basal glucose control in type 1 diabetes using deep reinforcement learning: An in silico validation," IEEE J. Biomed. Health Inform., vol. 25, no. 4, pp. 1223-1232, Apr. 2021.
  12. L. M. Wilson et al., "Dual-hormone closed-loop system using a liquid stable glucagon formulation versus insulin-only closed-loop system com- pared with a predictive low glucose suspend system: An open-label, out- patient, single-center, crossover, randomized controlled trial," Diabetes Care, vol. 43, pp. 2721-2729, Sep. 2020.
  13. T. Zhu et al., "A deep learning algorithm for personalized blood glucose prediction," in Proc. KHD@IJCAI, 2018, pp. 64-78.
  14. K. Turksoy et al., "Multivariable artificial pancreas for various exer- cise types and intensities," Diabetes Technol. Therapeutics, vol. 20, pp. 662-671, Oct. 2018.
  15. N. S. Tyler and P. G. Jacobs, "Artificial intelligence in deci- sion support systems for type 1 diabetes," Sensors, vol. 20, 2020, Art. no. 3214.
  16. N. S. Tyler et al., "An artificial intelligence decision support system for the management of type 1 diabetes," Nature Metab., vol. 2, no. 7, pp. 612-619, 2020.
  17. P. Pesl et al., "Case-based reasoning for insulin bolus advice," J. Diabetes Sci. Technol., vol. 11, pp. 37-42, Jan. 2017.
  18. V. Gulshan et al., "Development and validation of a deep learning algo- rithm for detection of diabetic retinopathy in retinal fundus photographs," J. Amer. Med. Assoc., vol. 316, pp. 2402-2410, 2016.
  19. F. Arcadu et al., "Deep learning algorithm predicts diabetic retinopathy progression in individual patients," NPJ Digit. Med., vol. 2, Sep. 2019, Art. no. 92.
  20. M. R. Askari et al., "Detection of meals and physical activity events from free-living data of people with diabetes," J. Diabetes Sci. Technol., vol. 17, no. 6, pp. 1482-1492, 2023.
  21. C. Mosquera-Lopez and P. G. Jacobs, "Incorporating glucose variability into glucose forecasting accuracy assessment using the new glucose variability impact index and the prediction consistency index: An LSTM case example," J. Diabetes Sci. Technol., vol. 16, no. 1, pp. 7-18, 2022.
  22. R. Reddy et al., "Prediction of hypoglycemia during aerobic exercise in adults with type 1 diabetes," J. Diabetes Sci. Technol., vol. 13, pp. 919-927, Sep. 2019.
  23. J. Daniels et al., "A deep learning framework for automatic meal detection and estimation in artificial pancreas systems," Sensors, vol. 22, 2022, Art. no. 466.
  24. K. Turksoy et al., "Multivariable adaptive closed-loop control of an artificial pancreas without meal and activity announcement," Diabetes Technol. Therapeutics, vol. 15, pp. 386-400, May 2013.
  25. K. Turksoy et al., "Use of wearable sensors and biometric variables in an artificial pancreas system," Sensors, vol. 17, no. 3, Mar. 2017, Art. no. 532.
  26. F. Cameron et al., "Probabilistic evolving meal detection and estimation of meal total glucose appearance," J. Diabetes Sci. Technol., vol. 3, pp. 1022-1030, Sep. 2009.
  27. F. M. Cameron et al., "Closed-loop control without meal announcement in type 1 diabetes," Diabetes Technol. Therapeutics, vol. 19, pp. 527-532, Sep. 2017.
  28. E. Dassau et al., "Detection of a meal using continuous glucose monitor- ing," Implic. Artif. B-Cell, vol. 31, pp. 295-300, 2008.
  29. A. Haidar et al., "A novel dual-hormone insulin-and-pramlintide artificial pancreas for type 1 diabetes: A randomized controlled crossover trial," Diabetes Care, vol. 43, no. 3, pp. 597-606, 2020.
  30. E. Palisaitis et al., "A meal detection algorithm for the artificial pan- creas: A randomized controlled clinical trial in adolescents with type 1 diabetes," Diabetes Care, vol. 44, pp. 604-606, Feb. 2021.
  31. M. Zheng et al., "Automated meal detection from continuous glucose monitor data through simulation and explanation," J. Amer. Med. Inform. Assoc., vol. 26, pp. 1592-1599, 2019.
  32. J. Garcia-Tirado et al., "Advanced closed-loop control system im- proves postprandial glycemic control compared with a hybrid closed- loop system following unannounced meal," Diabetes Care, vol. 44, pp. 2379-2387, 2021.
  33. A. Z. Woldaregay et al., "Data-driven blood glucose pattern clas- sification and anomalies detection: Machine-learning applications in type 1 diabetes," J. Med. Internet Res., vol. 21, May 2019, Art. no. e11030.
  34. M. R. Askari et al., "Adaptive-learning model predictive control for complex physiological systems: Automated insulin delivery in diabetes," Annu. Rev. Control, vol. 50, pp. 1-12, Jan. 2020.
  35. "Good to know: Factors affecting blood glucose," Clin. Diabetes, vol. 36, pp. 202-202, 2018.
  36. I. Kavakiotis et al., "Machine learning and data mining methods in diabetes research," Comput. Struct. Biotechnol. J., vol. 15, pp. 104-116, Jan. 2017.
  37. T. Sharma and M. Shah, "A comprehensive review of machine learning techniques on diabetes detection," Vis. Comput. Ind., Biomed., Art, vol. 4, pp. 1-16, Dec. 2021.
  38. T. Zhu et al., "Deep learning for diabetes: A systematic review," IEEE J. Biomed. Health Inform., vol. 25, no. 7, pp. 2744-2757, Jul. 2021.
  39. M. Niederberger and J. Spranger, "Delphi technique in health sciences: A map," Front. Public Health, vol. 8, 2020, Art. no. 457.
  40. S. Basu et al., "Use of machine learning approaches in clinical epidemi- ological research of diabetes," Curr. Diabetes Rep., vol. 20, pp. 1-19, Dec. 2020.
  41. I. Contreras and J. Vehi, "Artificial Intelligence for diabetes management and decision support: Literature review," J. Med. Internet Res., vol. 20, May 2018, Art. no. e10775.
  42. S. Larabi-Marie-Sainte et al., "Current techniques for diabetes prediction: Review and case study," Appl. Sci., vol. 9, 2019, Art. no. 4604.
  43. J. Li et al., "Application of Artificial Intelligence in diabetes education and management: Present status and promising prospect," Front. Public Health, vol. 8, 2020, Art. no. 173.
  44. M. Phillip et al., "The digital/virtual diabetes clinic: The future is now-recommendations from an international panel on diabetes digital technologies introduction," Diabetes Technol. Therapeutics, vol. 23, pp. 146-154, Feb. 2021.
  45. M. A. Makroum et al., "Machine learning and smart devices for di- abetes management: Systematic review," Sensors, vol. 22, Feb. 2022, Art. no. 1843.
  46. B. P. Kovatchev, "Metrics for glycaemic control-From HbA1c to contin- uous glucose monitoring," Nature Rev. Endocrinol., vol. 13, pp. 425-436, Jul. 2017.
  47. A. Z. Woldaregay et al., "Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes," Artif. Intell. Med., vol. 98, pp. 109-134, Jul. 2019.
  48. C. Marling and R. Bunescu, "The OhioT1DM dataset for blood glu- cose level prediction: Update 2020," CEUR Workshop Proc., vol. 2675, pp. 71-74, Sep. 2020.
  49. C. Mosquera-Lopez et al., "Predicting and preventing nocturnal hypo- glycemia in type 1 diabetes using big data analytics and decision theoretic analysis," Diabetes Technol. Therapeutics, vol. 22, no. 11, pp. 801-811, May 2020.
  50. M. R. Askari et al., "Meal and physical activity detection from free-living data for discovering disturbance patterns of glucose levels in people with diabetes," BioMedInformatics, vol. 2, pp. 297-317, 2022.
  51. M. Riddell et al., "The type 1 diabetes EXercise initiative (T1DEXI): Examining the acute glycemic effects of different types of structured exercise sessions in type 1 diabetes in a real-world settting," Diabetes Care, vol. 46, no. 4, pp. 704-713, 2023.
  52. M. Gillingham et al., "Assessing mealtime macronutrient content: Patient perceptions versus expert analyses via a novel phone app," Diabetes Technol. Therapeutics, vol. 23, no. 2, pp. 85-94, 2021.
  53. C. Cobelli and E. Carson, Introduction to Modeling in Physiology and Medicine, vol. 2. Amsterdam, The Netherlands: Elsevier, 2019.
  54. A. Haidar et al., "Glucose-responsive insulin and glucagon delivery (dual- hormone artificial pancreas) in adults with type 1 diabetes: A randomized crossover controlled trial," Can. Med. Assoc. J., vol. 185, pp. 297-305, Mar. 2013.
  55. A. Haidar et al., "Comparison of dual-hormone artificial pancreas, single- hormone artificial pancreas, and conventional insulin pump therapy for glycaemic control in patients with type 1 diabetes: An open-label ran- domised controlled crossover trial," Lancet Diabetes Endocrinol., vol. 3, pp. 17-26, 2015.
  56. P. G. Jacobs et al., "Randomized trial of a dual-hormone artificial pancreas with dosing adjustment during exercise compared with no adjustment and sensor-augmented pump therapy," Diabetes, Obesity Metab., vol. 18, pp. 1110-1119, Nov. 2016.
  57. P. G. Jacobs et al., "Incorporating an exercise detection, grading, and hormone dosing algorithm into the artificial pancreas using accelerometry and heart rate," J. Diabetes Sci. Technol., vol. 9, pp. 1175-1184, 2015.
  58. N. Resalat et al., "Adaptive control of an artificial pancreas using model identification, adaptive postprandial insulin delivery and exercise," J. Diabetes Sci. Technol., vol. 13, pp. 1044-1053, 2019.
  59. N. Resalat et al., "Adaptive tuning of basal and bolus insulin to reduce postprandial hypoglycemia in a hybrid artificial pancreas," J. Process Control, vol. 80, pp. 247-254, Aug. 2019.
  60. N. Tyler et al., "Quantifying the impact of physical activity on future glucose trends using machine learning," IScience, vol. 25, pp. 1-19, 2022.
  61. A. Haidar et al., "Stochastic virtual population of subjects with type 1 diabetes for the assessment of closed-loop glucose con- trollers," IEEE Trans. Biomed. Eng., vol. 60, no. 12, pp. 3524-3533, Dec. 2013.
  62. M. Rashid et al., "Simulation software for assessment of nonlinear and adaptive multivariable control algorithms: Glucose-Insulin dynam- ics in type 1 diabetes," Comput. Chem. Eng., vol. 130, Nov. 2019, Art. no. 106565.
  63. E. Estremera et al., "A simulator with realistic and challenging scenarios for virtual T1D patients undergoing CSII and MDI therapy," J. Biomed. Inform., vol. 132, Aug. 2022, Art. no. 104141.
  64. B. J. Heil et al., "Reproducibility standards for machine learning in the life sciences," Nature Methods, vol. 18, pp. 1132-1135, Oct. 2021.
  65. J. Pineau et al., "Improving reproducibility in machine learning re- search (a report from the NeurIPS 2019 reproducibility program)," 2021, arXiv:2003.12206. · arXiv
  66. P. I. Beato-Víbora et al., "Real-world outcomes with different technology modalities in type 1 diabetes," Nutr., Metab. Cardiovasc. Dis., vol. 31, pp. 1845-1850, Jun. 2021.
  67. K. Weiss et al., "A survey of transfer learning," J. Big Data, vol. 3, May 2016, Art. no. 9.
  68. R. Vilalta and Y. Drissi, "A perspective view and survey of meta- learning," Artif. Intell. Rev., vol. 18, pp. 77-95, Jun. 2002.
  69. V. Naumova et al., "A meta-learning approach to the regularized learning-Case study: Blood glucose prediction," Neural Netw., vol. 33, pp. 181-193, Sep. 2012.
  70. T. Zhu et al., "Dilated recurrent neural networks for glucose forecasting in type 1 diabetes," J. Healthcare Inform. Res., vol. 4, pp. 308-324, Sep. 2020.
  71. T. Zhu et al., "Personalized blood glucose prediction for type 1 diabetes using evidential deep learning and meta-learning," IEEE Trans. Biomed. Eng., vol. 70, no. 1, pp. 193-204, Jan. 2023.
  72. S.-J. Yen and Y.-S. Lee, "Cluster-based under-sampling approaches for imbalanced data distributions," Expert Syst. Appl., vol. 36, pp. 5718-5727, Apr. 2009.
  73. B. W. Bequette, "Fault detection and safety in closed-loop artificial pancreas systems," J. Diabetes Sci. Technol., vol. 8, pp. 1204-1214, 2014.
  74. L. Meneghetti et al., "Machine learning-based anomaly detection algo- rithms to alert patients using sensor augmented pump of infusion site failures," J. Diabetes Sci. Technol., vol. 16, pp. 641-648, May 2022.
  75. H. Zisser et al., "Bolus calculator: A review of four 'smart' in- sulin pumps," Diabetes Technol. Therapeutics, vol. 10, pp. 441-444, Dec. 2008.
  76. W. L. Clarke and B. Kovatchev, "Continuous glucose sensors: Continuing questions about clinical accuracy," J. Diabetes Sci. Technol., vol. 1, pp. 669-675, Sep. 2007.
  77. N. V. Chawla et al., "SMOTE: Synthetic minority over-sampling tech- nique," J. Artif. Intell. Res., vol. 16, pp. 321-357, 2002.
  78. O. Mujahid et al., "Conditional synthesis of blood glucose profiles for T1D patients using deep generative models," Mathematics, vol. 10, 2022, Art. no. 3741.
  79. C. M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics). Berlin, Germany: Springer, 2006.
  80. Y. Bengio, "Learning deep architectures for AI," Found. Trends Mach. Learn., vol. 2, pp. 1-127, 2009.
  81. V. Vapnik, The Nature of Statistical Learning Theory, vol. 2. Berlin, Germany: Springer, 2000.
  82. M. Sevil et al., "Detection and characterization of physical activity and psychological stress from wristband data," Signals, vol. 1, pp. 188-208, 2020.
  83. M. Sevil et al., "Physical activity and psychological stress detection and assessment of their effects on glucose concentration predictions in diabetes management," IEEE Trans. Biomed. Eng., vol. 68, no. 7, pp. 2251-2260, Jul. 2021.
  84. M. Sevil et al., "Determining physical activity characteristics from wrist- band data for use in automated insulin delivery systems," IEEE Sensors J., vol. 20, no. 21, pp. 12859-12870, Nov. 2020.
  85. G. Sparacino et al., "Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series," IEEE Trans. Biomed. Eng., vol. 54, no. 5, pp. 931-937, May 2007.
  86. K. Turksoy et al., "Hypoglycemia detection and carbohydrate sug- gestion in an artificial pancreas," J. Diabetes Sci. Technol., vol. 10, pp. 1236-1244, Nov. 2016.
  87. B. Kovatchev and W. Clarke, "Peculiarities of the continuous glucose monitoring data stream and their impact on developing closed-loop con- trol technology," J. Diabetes Sci. Technol., vol. 2, pp. 158-163, Jan. 2008.
  88. C. Pérez-Gandía et al., "Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring," Diabetes Tech- nol. Therapeutics, vol. 12, pp. 81-88, Jan. 2010.
  89. E. Montaser et al., "Essential continuous glucose monitoring metrics: The principal dimensions of glycemic control in diabetes," Diabetes Technol. Therapeutics, vol. 24, no. 11, pp. 797-804, 2022.
  90. M. R. Askari et al., "Detection and classification of unannounced phys- ical activities and acute psychological stress events for interventions in diabetes treatment," Algorithms, vol. 15, 2022, Art. no. 352.
  91. R. Hovorka et al., "Nonlinear model predictive control of glucose con- centration in subjects with type 1 diabetes," Physiol. Meas., vol. 25, pp. 905-920, Aug. 2004.
  92. S. D. Patek, "Empirical representation of blood glucose variability in a compartmental model," in Introduction to Modeling in Physiology and Medicine, vol. 2, E. Carson and C. Cobelli, Eds. Amsterdam, The Netherlands: Elsevier, 2019, pp. 133-156.
  93. K. L. Swan et al., "Effect of puberty on the pharmacodynamic and pharmacokinetic properties of insulin pump therapy in youth with type 1 diabetes," Diabetes Care, vol. 31, pp. 44-46, 2008.
  94. I. Hajizadeh et al., "Plasma-insulin-cognizant adaptive model predictive control for artificial pancreas systems," J. Process Control, vol. 77, pp. 97-113, May 2019.
  95. I. Hajizadeh et al., "Adaptive and personalized plasma insulin concentra- tion estimation for artificial pancreas systems," J. Diabetes Sci. Technol., vol. 12, pp. 639-649, May 2018.
  96. T.-T. P. Nguyen et al., "Separating insulin-mediated and non-insulin- mediated glucose uptake during aerobic exercise in people with type 1 diabetes," Amer. J. Physiol.-Endocrinol. Metab., vol. 320, no. 3, pp. E425-E437, 2020.
  97. M. C. Riddell et al., "Exercise management in type 1 diabetes: A con- sensus statement," Lancet Diabetes Endocrinol., vol. 5, pp. 377-390, May 2017.
  98. P. G. Jacobs et al., "Integrating metabolic expenditure information from wearable fitness sensors into an AI-augmented automated insulin delivery system: A randomized clinical trial," Lancet Digit. Health, vol. 5, no. 9, pp. e607-e617, 2023.
  99. R. K. Reddy et al., "Accuracy of wrist-worn activity monitors dur- ing common daily physical activities and types of structured ex- ercise: Evaluation study," JMIR mHealth uHealth, vol. 6, 2018, Art. no. e10338.
  100. C. Manohar et al., "Comparison of physical activity sensors and heart rate monitoring for real-time activity detection in type 1 diabetes and control subjects," Diabetes Technol. Therapeutics, vol. 15, pp. 751-757, Sep. 2013.
  101. K. Turksoy et al., "Classification of physical activity: Information to artificial pancreas control systems in real time," J. Diabetes Sci. Technol., vol. 9, pp. 1200-1207, Oct. 2015.
  102. J. Garcia-Tirado et al., "Anticipation of historical exercise patterns by a novel artificial pancreas system reduces hypoglycemia during and after moderate-intensity physical activity in people with type 1 diabetes," Diabetes Technol. Therapeutics, vol. 23, pp. 277-285, Apr. 2021.
  103. M. Cescon et al., "Activity detection and classification from wristband accelerometer data collected on people with type 1 diabetes in free-living conditions," Comput. Biol. Med., vol. 135, Aug. 2021, Art. no. 104633.
  104. M. Hernández-Ordoñez and D. U. Campos-Delgado, "An extension to the compartmental model of type 1 diabetic patients to reproduce exercise periods with glycogen depletion and replenishment," J. Biomech., vol. 41, pp. 744-752, 2008.
  105. N. Hobbs et al., "A physical activity-intensity driven glycemic model for type 1 diabetes," Comput. Methods Prog. Biomed., vol. 226, Nov. 2022, Art. no. 107153.
  106. C. D. Man et al., "Physical activity into the meal glucose-Insulin model of type 1 diabetes: In silico studies," J. Diabetes Sci. Technol., vol. 3, pp. 56-67, Jan. 2009.
  107. M. D. Breton, "Physical activity-the major unaccounted impediment to closed loop control," J. Diabetes Sci. Technol., vol. 2, pp. 169-174, Jan. 2008.
  108. B. Ozaslan et al., "Automatically accounting for physical activity in insulin dosing for type 1 diabetes," Comput. Methods Prog. Biomed., vol. 197, Dec. 2020, Art. no. 105757.
  109. M. R. Askari et al., "Artifact removal from data generated by nonlinear systems: Heart rate estimation from blood volume pulse signal," Ind. Eng. Chem. Res., vol. 59, pp. 2318-2327, Dec. 2020.
  110. E. I. Georga et al., "A predictive model of subcutaneous glucose concen- tration in type 1 diabetes based on random forests," in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2012, pp. 2889-2892.
  111. R. Shwartz-Ziv and A. Armon, "Tabular data: Deep learning is not all you need," Inf. Fusion, vol. 81, pp. 84-90, May 2022.
  112. E. I. Georga et al., "Multivariate prediction of subcutaneous glucose con- centration in type 1 diabetes patients based on support vector regression," IEEE J. Biomed. Health Inform., vol. 17, no. 1, pp. 71-81, Jan. 2013.
  113. K. Li et al., "Convolutional recurrent neural networks for glucose pre- diction," IEEE J. Biomed. Health Inform., vol. 24, no. 2, pp. 603-613, Feb. 2020.
  114. S. M. Pappada et al., "Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes," Diabetes Technol. Therapeutics, vol. 13, pp. 135-141, Feb. 2011.
  115. C. Zecchin et al., "Jump neural network for real-time prediction of glucose concentration," Methods Mol. Biol., vol. 1260, pp. 245-259, 2015.
  116. C. Zecchin et al., "Neural network incorporating meal information im- proves accuracy of short-time prediction of glucose concentration," IEEE Trans. Biomed. Eng., vol. 59, no. 6, pp. 1550-1560, Jun. 2012.
  117. T. Zhu et al., "Enhancing self-management in type 1 diabetes with wear- ables and deep learning," NPJ Digit. Med., vol. 5, Jun. 2022, Art. no. 78.
  118. T. Kushner et al., "Multi-hour blood glucose prediction in type 1 diabetes: A patient-specific approach using shallow neural network models," Dia- betes Technol. Therapeutics, vol. 22, pp. 883-891, Dec. 2020.
  119. M. H. Jensen et al., "Prediction of nocturnal hypoglycemia from con- tinuous glucose monitoring data in people with type 1 diabetes: A proof-of-concept study," J. Diabetes Sci. Technol., vol. 14, pp. 250-256, Mar. 2020.
  120. S. D. Favero et al., "A glucose-specific metric to assess predictors and identify models," IEEE Trans. Biomed. Eng., vol. 59, no. 5, pp. 1281-1290, May 2012.
  121. S. Faccioli et al., "Combined use of glucose-specific model identification and alarm strategy based on prediction-funnel to improve online fore- casting of hypoglycemic events," J. Diabetes Sci. Technol., vol. 17, no. 5, pp. 1295-1303, 2023.
  122. F. Cameron et al., "A closed-loop artificial pancreas based on risk management," J. Diabetes Sci. Technol., vol. 5, pp. 368-379, Mar. 2011.
  123. C. Mosquera-Lopez et al., "Enabling fully automated insulin delivery through meal detection and size estimation using artificial intelligence," NPJ Digit. Med., vol. 6, no. 39, pp. 1-7 Mar. 2023.
  124. Z. Mahmoudi et al., "An automated meal detector and bolus calcu- lator in combination with closed-loop blood glucose control," IFAC- PapersOnLine, vol. 51, pp. 168-173, Aug. 2018.
  125. S. Samadi et al., "Automatic detection and estimation of unannounced meals for multivariable artificial pancreas system," Diabetes Technol. Therapeutics, vol. 20, pp. 235-246, Mar. 2018.
  126. M. Athanasiou et al., "An LSTM-based approach towards automated meal detection from continuous glucose monitoring in type 1 dia- betes mellitus," in Proc. IEEE 21st Int. Conf. Bioinf. Bioeng., 2021, pp. 1-5.
  127. J. N. Mandrekar, "Receiver operating characteristic curve in diagnostic test assessment," J. Thoracic Oncol., vol. 5, pp. 1315-1316, Sep. 2010.
  128. J. P. Corbett et al., "Using an online disturbance rejection and anticipation system to reduce hyperglycemia in a fully closed-loop artificial pancreas system," J. Diabetes Sci. Technol., vol. 16, pp. 52-60, 2022.
  129. H. M. Romero-Ugalde et al., "ARX model for interstitial glucose pre- diction during and after physical activities," Control Eng. Pract., vol. 90, pp. 321-330, Sep. 2019.
  130. M. Tejedor et al., "Reinforcement learning application in diabetes blood glucose control: A systematic review," Artif. Intell. Med., vol. 104, Apr. 2020, Art. no. 101836.
  131. I. Fox et al., "Deep reinforcement learning for closed-loop blood glucose control," in Proc. 5th Mach. Learn. Healthcare Conf., Proc. Mach. Learn. Res., 2020, pp. 508-536.
  132. P. Herrero et al., "Identifying continuous glucose monitoring data using machine learning," Diabetes Technol. Therapeutics, vol. 24, pp. 403-408, Jun. 2022.
  133. G. Noaro et al., "An ensemble learning algorithm based on dynamic voting for targeting the optimal insulin dosage in type 1 diabetes man- agement," in Proc. 43rd Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2021, pp. 1828-1831.
  134. P. Herrero et al., "Automatic adaptation of basal insulin using sensor-augmented pump therapy," J. Diabetes Sci. Technol., vol. 12, pp. 282-294, Mar. 2018.
  135. C. C. Palerm et al., "A run-to-run control strategy to adjust basal in- sulin infusion rates in type 1 diabetes," J. Process Control, vol. 18, pp. 258-265, 2008.
  136. C. Toffanin et al., "Automatic adaptation of basal therapy for type 1 diabetic patients: A run-to-run approach," IFAC Proc. Volumes, vol. 47, pp. 2070-2075, Jan. 2014.
  137. H. Zisser et al., "Clinical update on optimal prandial insulin dosing using a refined run-to-run control algorithm," J. Diabetes Sci. Technol., vol. 3, pp. 487-491, May 2009.
  138. J. R. Castle et al., "Assessment of a decision support system for adults with type 1 diabetes on multiple daily insulin injections," Diabetes Technol. Therapeutics, vol. 24, no. 12, pp. 892-897, Aug. 2022.
  139. M. Vettoretti et al., "Patient decision-making of CGM sensor driven insulin therapies in type 1 diabetes: In silico assessment," in Proc. 37th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2015, pp. 2363-2366.
  140. R. Nimri et al., "Comparison of insulin dose adjustments made by Artificial Intelligence-based decision support systems and by physicians in people with type 1 diabetes using multiple daily injections therapy," Diabetes Technol. Therapeutics, vol. 24, pp. 564-572, Aug. 2022.
  141. A. Bisio et al., "Impact of a novel diabetes support system on a cohort of individuals with type 1 diabetes treated with multiple daily injections: A multicenter randomized study," Diabetes Care, vol. 45, pp. 186-193, 2021.
  142. P. Herrero et al., "Robust determination of the optimal continuous glucose monitoring length of intervention to evaluate long-term glycemic con- trol," Diabetes Technol. Therapeutics, vol. 23, pp. 314-319, Apr. 2021.
  143. T. Battelino et al., "Continuous glucose monitoring and metrics for clinical trials: An international consensus statement," Lancet Diabetes Endocrinol., vol. 11, pp. 42-57, Jan. 2023.
  144. K. Zarkogianni et al., "A Review of Emerging Technologies for the Management of Diabetes Mellitus," IEEE Trans. Biomed. Eng., vol. 62, no. 12, pp. 2735-2749, Dec. 2015.
  145. B. W. Bequette, "Algorithms for a closed-loop artificial pancreas: The case for model predictive control," J. Diabetes Sci. Technol., vol. 7, pp. 1632-1643, Nov. 2013.
  146. K. Zarkogianni et al., "An insulin infusion advisory system based on autotuning nonlinear model-predictive control," IEEE Trans. Biomed. Eng., vol. 58, no. 9, pp. 2467-2477, Sep. 2011.
  147. W. L. Clarke et al., "Evaluating clinical accuracy of systems for self- monitoring of blood glucose," Diabetes Care, vol. 10, pp. 622-628, Sep./Oct 1987.
  148. J. L. Parkes et al., "A new consensus error grid to evaluate the clinical sig- nificance of inaccuracies in the measurement of blood glucose," Diabetes Care, vol. 23, pp. 1143-1148, 2000.
  149. W. L. Clarke et al., "Evaluating clinical accuracy of continuous glucose monitoring systems: Continuous glucose-error grid analysis (CG-EGA)," Curr. Diabetes Rev., vol. 4, pp. 193-199, Aug. 2008.
  150. D. C. Klonoff et al., "The surveillance error grid," J. Diabetes Sci. Technol., vol. 8, pp. 658-672, Jul. 2014.
  151. M. T. Ribeiro et al., "Why should i trust you¿': Explaining the predictions of any classifier," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2016, pp. 1135-1144.
  152. A. Shrikumar et al., "Learning important features through propagating activation differences," in Proc. 34th Int. Conf. Mach. Learn., 2017, pp. 3145-3153.
  153. A. Karimi et al., "Model-agnostic counterfactual explanations for conse- quential decisions," in Proc. 23rd Int. Conf. Artif. Intell. Statist., 2020, pp. 895-905.
  154. S. Liu et al., "Generative counterfactual introspection for explainable deep learning," in Proc. IEEE Glob. Conf. Signal Inf. Process., 2019, pp. 1-5.
  155. J. Daniels et al., "A multitask learning approach to personalized blood glucose prediction," IEEE J. Biomed. Health Inform., vol. 26, no. 1, pp. 436-445, Jan. 2022.
  156. C. Toffanin, "Adaptive and individualized artificial pancreas for precision management of type 1 diabetes," in Precision Medicine in Diabetes: A Multidisciplinary Approach to an Emerging Paradigm, R. Basu, Ed. Berlin, Germany: Springer, 2022, pp. 305-313.
  157. S. I. Taylor et al., "SGLT2 inhibitors as adjunctive therapy for type 1 diabetes: Balancing benefits and risks," Lancet Diabetes Endocrinol., vol. 7, pp. 949-958, Dec. 2019.
  158. Shaban-Nejad, Ed. Berlin, Germany: Springer, 2021, pp. 45-53.
  159. K. Cao et al., "An overview on edge computing research," IEEE Access, vol. 8, pp. 85714-85728, 2020.
  160. T. Zhu et al., "IoMT-enabled real-time blood glucose prediction with deep learning and edge computing," IEEE Internet Things J., vol. 10, pp. 3706-3719, 2023.

Cited by

Sorted by citations

Authors
Jacobs, P. G., Herrero, P., Facchinetti, A., Vehi, J., Kovatchev, B., Breton, M. D., Cinar, A., Nikita, K. S., Doyle, F. J., Bondia, J., Battelino, T., Castle, J. R., Zarkogianni, K., Narayan, R., & Mosquera-Lopez, C.
Affiliations
  • Oregon Health & Science University (US)
  • Roche (Spain) (ES)
  • University of Padua (IT)
  • University of Girona and CIBERDEM, Instituto de Salud Carlos III, Madrid, Spain
  • University of Virginia (US)
  • Chemical and Biological EngineeringIllinois Institute of Technology, Chicago, IL, USA
  • National Technical University of Athens (GR)
  • Harvard University (US)
  • Universitat Politácnica de València, Valencia, Spain
  • University of Ljubljana (SI)
ORCID
Venue
IEEE Reviews in Biomedical Engineering
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2024
Volume
17
Pages
19-41
ISSN
  • 1937-3333 (ISSN-L)
  • 1941-1189
DOI
10.1109/rbme.2023.3331297
OpenAlex
W4388520297
Cited by
113
References
28
Citations by year
2026: 27 · 2025: 55 · 2024: 31
FWCI
4.08
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Reviews in Biomedical Engineering (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RiuNet (Universitat Politècnica de València) (publishedVersion, cc-by)
  • Padua Research Archive (University of Padova) (submittedVersion, cc-by)
  • Research Publications (Maastricht University) (submittedVersion, cc-by)
Funders
Javna Agencija za Raziskovalno Dejavnost RS (P3-0343)
Topics
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
artificial intelligence, machine learning, diabetes mellitus, glycemic control, artificial pancreas, biosensing, model interpretability, explainability, personalization, clinical accuracy, feature engineering, data sheets, training data, open-source library
MeSH terms
Machine Learning, Glycemic Control, Algorithms, Artificial Intelligence, Diabetes Mellitus, Humans

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review