CoChat
Sign Up
Cited by 31Diabetes Management and ResearchArtificial Intelligence in HealthcareDiabetes Management and Education

Enhancing the Capabilities of Continuous Glucose Monitoring With a Predictive App

Open access
Herrero, Pau, Andorrà, Magí, Babion, Nils, Bos, Hendericus, Koehler, Matthias, Klopfenstein, Yannick, Leppäaho, Eemeli, Lustenberger, Patrick +3 more·2024·Journal of Diabetes Science and Technology
DOI 10.1177/19322968241267818PMC PMC11418465
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Despite abundant evidence demonstrating the benefits of continuous glucose monitoring (CGM) in diabetes management, a significant proportion of people using this technology still struggle to achieve glycemic targets. To address this challenge, we propose the Accu-Chek ® SmartGuide Predict app, an innovative CGM digital companion that incorporates a suite of advanced glucose predictive functionalities aiming to inform users earlier about acute glycemic situations. Methods: The app’s functionalities, powered by three machine learning models, include a two-hour glucose forecast, a 30-minute low glucose detection, and a nighttime low glucose prediction for bedtime interventions. Evaluation of the models’ performance included three data sets, comprising subjects with T1D on MDI (n = 21), subjects with type 2 diabetes (T2D) on MDI (n = 59), and subjects with T1D on insulin pump therapy (n = 226). Results: On an aggregated data set, the two-hour glucose prediction model, at a forecasting horizon of 30, 45, 60, and 120 minutes, achieved a percentage of data points in zones A and B of Consensus Error Grid of: 99.8%, 99.3%, 98.7%, and 96.3%, respectively. The 30-minute low glucose prediction model achieved an accuracy, sensitivity, specificity, mean lead time, and area under the receiver operating characteristic curve (ROC AUC) of: 98.9%, 95.2%, 98.9%, 16.2 minutes, and 0.958, respectively. The nighttime low glucose prediction model achieved an accuracy, sensitivity, specificity, and ROC AUC of: 86.5%, 55.3%, 91.6%, and 0.859, respectively. Conclusions: The consistency of the performance of the three predictive models when evaluated on different cohorts of subjects with T1D and T2D on different insulin therapies, including real-world data, offers reassurance for real-world efficacy.

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 · 10.1177/19322968241267818

Cites

11 of 11 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?

  • Mobile applications like mySugr and Sugar.IQ analyze glucose data and provide tailored feedback on diet, exercise, and medication, helping users optimize glycemic control.

    “Mobile applications like mySugr and Sugar.IQ analyze glucose data and provide users with tailored feedback on diet, exercise, and medication, helping them optimize glycemic control (41).”

    From Generative artificial intelligence in predictive analysis of diabetes and its complications: a narrative review (2025) · cites this paper as [41]

    The Diabetes Self-Management Digital Tools section says mobile platforms offer solutions for nutrition, physical activity, glucose monitoring, and insulin titration. But the paper mentions mySugr only in the Acknowledgements and Sugar.IQ in the References; it does not say that either app gives tailored feedback on diet, exercise, and medication or demonstrate that these apps improve glycemic control. Page numbers are unavailable in our copy. (LLM, conf=0.83)

    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: 42

  1. Ceriello A, Prattichizzo F, Phillip M, Hirsch IB, Mathieu C, Battelino T. Glycaemic management in diabetes: old and new approaches. Lancet Diabetes Endocrinol. 2022;10(1):75-84.
  2. Forlenza GP, Lal RA. Current status and emerging options for automated insulin delivery systems. Diabetes Technol Ther. 2022;24(5):362-371.
  3. Marigliano M, Mozzillo E, Mancioppi V, et al. Measures of patient-reported expectations, acceptance, and satisfaction using automated insulin delivery systems: a review. J Pers Med. 2023;13(7):1031.
  4. Shan R, Sarkar S, Martin SS. Digital health technology and mobile devices for the management of diabetes mellitus: state of the art. Diabetologia. 2019;62(6):877-887.
  5. Doyle-Delgado K, Chamberlain JJ. Use of diabetes-related applications and digital health tools by people with diabetes and their health care providers. Clin Diabetes. 2020;38(5):449- 461.
  6. Fleming GA, Petrie JR, Bergenstal RM, Holl RW, Peters AL, Heinemann L. Diabetes digital app technology: benefits, challenges, and recommendations. A consensus report by the European Association for the Study of Diabetes (EASD) and the American Diabetes Association (ADA) diabetes technol- ogy working group. Diabetes Care. 2020;43(1):250-260.
  7. Tyler NS, Jacobs PG. Artificial intelligence in decision support systems for type 1 diabetes. Sensors. 2020;20(11):3214.
  8. Vehi J, Mujahid O, Contreras I. Artificial intelligence and machine learning for diabetes decision support. In: Sadasivuni KK, Malik RA, Cabibihan JJ, et al., eds. Advanced Bioscience and Biosystems for Detection and Management of Diabetes. Cham: Springer; 2022:259-272.
  9. Kushner T, Breton MD, Sankaranarayanan S. Multi-hour blood glucose prediction in type 1 diabetes: a patient-specific approach using shallow neural network models. Diabetes Technol Ther. 2020;22(12):883-891.
  10. Seo W, Park SW, Kim N, Jin SM, Park SM. A personalized blood glucose level prediction model with a fine-tuning strat- egy: a proof-of-concept study. Comput Methods Programs Biomed. 2021;211:106424.
  11. Zhu T, Li K, Herrero P, Georgiou P. Personalized blood glucose prediction for type 1 diabetes using evidential deep learning and meta-learning. IEEE Trans Biomed Eng. 2023;70(1):193- 204.
  12. Zhu T, Uduku C, Li K, Herrero P, Oliver N, Georgiou P. Enhancing self-management in type 1 diabetes with wearables and deep learning. NPJ Digit Med. 2022;5(1):78.
  13. Mosquera-Lopez C, Roquemen-Echeverri V, Tyler NS, et al. Combining uncertainty-aware predictive modeling and a bed- time Smart Snack intervention to prevent nocturnal hypoglyce- mia in people with type 1 diabetes on multiple daily injections. J Am Med Inform Assoc. 2024;31(1):109-118.
  14. Tyler NS, Mosquera-Lopez CM, Wilson LM, et al. An artifi- cial intelligence decision support system for the management of type 1 diabetes. Nat Metab. 2020;2(7):612-619.
  15. Fabris C, Nass RM, Pinnata J, et al. The use of a smart bolus calculator informed by real-time insulin sensitivity assessments reduces postprandial hypoglycemia following an aerobic exer- cise session in individuals with type 1 diabetes. Diabetes Care. 2020;43(4):799-805.
  16. Avari P, Leal Y, Herrero P, et al. Safety and feasibility of the PEPPER adaptive bolus advisor and safety system: a random- ized control study. Diabetes Technol Ther. 2021;23(3):175- 186.
  17. Unsworth R, Armiger R, Jugnee N, et al. Safety and efficacy of an adaptive bolus calculator for type 1 diabetes: a ran- domized controlled crossover study. Diabetes Technol Ther. 2023;25(6):414-425.
  18. Heinemann L, Thomas A. Continuous glucose monitoring and bolus calculators: a good combination. J Diabetes Sci Technol. 2024;18(4):761-763. doi:10.1177/19322968231204371. · DOI
  19. Wilson LM, Tyler N, Jacobs PG, et al. Patient input for design of a decision support smartphone application for type 1 diabe- tes. J Diabetes Sci Technol. 2020;14(6):1081-1087.
  20. Goldwater JC. Human factors and usability in mobile health design-factors for sustained patient engagement in diabe- tes care. Proc Int Symp Hum Factors Ergon Health Care. 2014;3(1):63-70.
  21. Martin C, Aldea A, Duce D, Harrison R, Alshaigy B. The role of usability engineering in the development of an intel- ligent decision support system. In: Koch F, ed. International Workshop on Artificial Intelligence in Health. Cham: Springer; 2018:142-161.
  22. Georgsson M, Staggers N, Årsand E, Kushniruk A. Employing a user-centered cognitive walkthrough to evalu- ate a mHealth diabetes self-management application: a case study and beginning method validation. J Biomed Inform. 2019;91:103110.
  23. Woldaregay AZ, Årsand E, Walderhaug S, et al. Data-driven modeling and prediction of blood glucose dynamics: machine learning applications in type 1 diabetes. Artif Intell Med. 2019;98:109-134.
  24. Cappon G, Prendin F, Facchinetti A, Sparacino G, Favero SD. Individualized models for glucose prediction in type 1 diabetes: comparing black-box approaches to a physiological white-box one. IEEE Trans Biomed Eng. 2023;70(11):3105- 3115.
  25. Dave D, Erraguntla M, Lawley M, et al. Improved low- glucose predictive alerts based on sustained hypoglycemia: model development and validation study. JMIR Diabetes. 2021;6(2):e26909.
  26. Georga EI, Príncipe JC, Fotiadis DI. Short-term prediction of glucose in type 1 diabetes using kernel adaptive filters. Med Biol Eng Comput. 2019;57(1):27-46.
  27. Mujahid O, Contreras I, Vehi J. Machine learning techniques for hypoglycemia prediction: trends and challenges. Sensors. 2021;21(2):546.
  28. Jensen MH, Dethlefsen C, Vestergaard P, Hejlesen O. Predic tion of nocturnal hypoglycemia from continuous glucose monitoring data in people with type 1 diabetes: a proof-of-concept study. J Diabetes Sci Technol. 2020;14(2):250-256.
  29. Parcerisas A, Contreras I, Delecourt A, et al. A machine learn- ing approach to minimize nocturnal hypoglycemic events in type 1 diabetic patients under multiple doses of insulin. Sensors. 2022;22(4):1665.
  30. Sevil M, Rashid M, Hajizadeh I, Park M, Quinn L, Cinar A. Physical activity and psychological stress detection and assessment of their effects on glucose concentration predic- tions in diabetes management. IEEE Trans Biomed Eng. 2021;68(7):2251-2260.
  31. Askari MR, Ahmadasas M, Shahidehpour A, et al. Multivariable automated insulin delivery system for handling planned and spontaneous physical activities. J Diabetes Sci Technol. 2023;17(6):1456-1469.
  32. Prendin F, Del Favero S, Vettoretti M, Sparacino G, Facchinetti A. Forecasting of glucose levels and hypoglycemic events: head-to-head comparison of linear and nonlinear data-driven algorithms based on continuous glucose monitoring data only. Sensors. 2021;21(5):1647.
  33. Puhr S, Derdzinski M, Welsh JB, Parker AS, Walker T, Price DA. Real-world hypoglycemia avoidance with a continuous glucose monitoring system's predictive low glucose alert. Diabetes Technol Ther. 2019;21(4):155-158.
  34. Kriventsov S, Lindsey A, Hayeri A. The diabits app for Smartphone-assisted predictive monitoring of glycemia in patients with diabetes: retrospective observational study. JMIR Diabetes. 2020;5(3):e18660.
  35. Evert AB. Treatment of mild hypoglycemia. Diabetes Spectr. 2014;27(1):58-62.
  36. Chen T, Guestrin C. Xgboost: a scalable tree boosting sys- tem. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; August 2016; San Francisco, CA:785-794.
  37. Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; August 2019; Anchorage, AK:2623-2631.
  38. Bergstra J, Bardenet R, Bengio Y, Kégl B. Algorithms for hyper-parameter optimization. Proceedings of the 24th International Conference on Neural Information Processing Systems (NIPS); December 2011; Red Hook, NY.
  39. Parkes JL, Slatin SL, Pardo S, Ginsberg BH. A new consen- sus error grid to evaluate the clinical significance of inaccu- racies in the measurement of blood glucose. Diabetes Care. 2000;23(8):1143-1148.
  40. Jacobs PG, Herrero P, Facchinetti A, et al. Artificial intelli- gence and machine learning for improving glycemic control in diabetes: best practices, pitfalls and opportunities. IEEE Rev Biomed Eng. 2024;17:19-41.
  41. Mohammed NH, Wolever TM. Effect of carbohydrate source on post-prandial blood glucose in subjects with type 1 dia- betes treated with insulin lispro. Diabetes Res Clin Pract. 2004;65(1):29-35.
  42. Marigliano M, Piona C, Mancioppi V, Morotti E, Morandi A, Maffeis C. Glucose sensor with predictive alarm for hypogly- caemia: improved glycaemic control in adolescents with type 1 diabetes. Diabetes Obes Metab. 2024;26(4):1314-1320.

Cited by

Sorted by citations

Authors
Herrero, P., Andorrà, M., Babion, N., Bos, H., Koehler, M., Klopfenstein, Y., Leppäaho, E., Lustenberger, P., Peak, A., Ringemann, C., & Glatzer, T.
Affiliations
  • Roche (Spain) (ES)
  • Roche Diabetes Care GmbH (Germany) (DE)
  • IBM (Netherlands) (NL)
  • IBM Switzerland Ltd, Zurich, Switzerland
  • IBM (United States) (US)
  • IBM (Germany) (DE)
Corresponding author
Glatzer, Timor
ORCID
Venue
Journal of Diabetes Science and Technology
Publisher
SAGE Publications
Published
2024-08-19
Volume
18
Issue
5
Pages
1014-1026
ISSN
1932-2968 (ISSN-L)
DOI
10.1177/19322968241267818
PMC
PMC11418465
OpenAlex
W4401694852
Cited by
31
References
11
Citations by year
2026: 14 · 2025: 11 · 2024: 6
Type
conference abstract
Language
en
Open access
Licence
Locations
  • Journal of Diabetes Science and Technology (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
Funders
Roche Diabetes Care
Topics
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Education
Keywords
continuous glucose monitoring, glucose prediction, type 1 diabetes, type 2 diabetes, multiple daily insulin injections, insulin pump therapy, machine learning models
MeSH terms
Machine Learning, Continuous Glucose Monitoring, Adult, Blood Glucose, Diabetes Mellitus, Type 1, Diabetes Mellitus, Type 2, Female, Humans, Insulin Infusion Systems, Male, Middle Aged, Blood Glucose Self-Monitoring, Mobile Applications

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