Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations
Published version of a preprint
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Background: The occurrences of acute complications arising from hypoglycemia and hyperglycemia peak as young adults with type 1 diabetes (T1D) take control of their own care. Continuous glucose monitoring (CGM) devices provide real-time glucose readings enabling users to manage their control proactively. Machine learning algorithms can use CGM data to make ahead-of-time risk predictions and provide insight into an individual’s longer term control. Methods: We introduce explainable machine learning to make predictions of hypoglycemia (<70 mg/dL) and hyperglycemia (>270 mg/dL) up to 60 minutes ahead of time. We train our models using CGM data from 153 people living with T1D in the CITY (CGM Intervention in Teens and Young Adults With Type 1 Diabetes)survey totaling more than 28 000 days of usage, which we summarize into (short-term, medium-term, and long-term) glucose control features along with demographic information. We use machine learning explanations (SHAP [SHapley Additive exPlanations]) to identify which features have been most important in predicting risk per user. Results: Machine learning models (XGBoost) show excellent performance at predicting hypoglycemia (area under the receiver operating curve [AUROC]: 0.998, average precision: 0.953) and hyperglycemia (AUROC: 0.989, average precision: 0.931) in comparison with a baseline heuristic and logistic regression model. Conclusions: Maximizing model performance for glucose risk prediction and management is crucial to reduce the burden of alarm fatigue on CGM users. Machine learning enables more precise and timely predictions in comparison with baseline models. SHAP helps identify what about a CGM user’s glucose control has led to predictions of risk which can be used to reduce their long-term risk of complications.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
In the citing paper
“Multiple reviews and methodological studies show that machine‑learning and deep‑learning models improve predictive accuracy for hypoglycemia, hyperglycemia, and overall glycemic variability compared with traditional approaches, laying the groundwork for data‑driven decision support and ultimately, closed‑loop systems in T2D [47–49].”
From Digital Management of Early-Onset Type 2 Diabetes: Empowerment, Challenges, and Future Outlook (2026) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
From local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551
Larian Studios Dev Team (2024) · doi:10.1145/3292500.3330701 · Cited by 8,618 · cited 1×
“33 In Supplemental Table 1, we include the complete set of tuned hyperparameters along with the corresponding search ranges.”
Background17. A Value for n-Person Games
Shapley, L. S. (1953) · Contributions to the Theory of Games (AM-28), Volume II · doi:10.1515/9781400881970-018 · Cited by 6,950
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
The Emerging Risk Factors Collaboration (2010) · The Lancet · doi:10.1016/s0140-6736(10)60484-9 · Cited by 5,125
Zhou, B., Lu, Y., Hajifathalian, K., Bentham, J., Di Cesare, M., Danaei, G., Bixby, H., Cowan, M., Ali, M., Taddei, C., et al. (2016) · The Lancet · doi:10.1016/s0140-6736(16)00618-8 · Cited by 4,311
Battelino, T., Danne, T., Bergenstal, R. M., Amiel, S. A., Beck, R., Biester, T., Bosi, E., Buckingham, B. A., Cefalu, W. T., Close, K. L., et al. (2019) · Diabetes Care · doi:10.2337/dci19-0028 · Cited by 4,237 · cited 1×
“…daily risk range, 50 %coefficient of variation, 51 level 2 hypoglycemia (% of readings or time < 54 mg/dL), level 2 hyperglycemia (% of readings or time > 250 mg/dL), 52 and low/high blood glucose index 53,54 along with our baseline of standard deviation is likely to improve model performance.”
Mechanisms of Diabetic Complications
Forbes, J. M., & Cooper, M. E. (2013) · Physiological Reviews · doi:10.1152/physrev.00045.2011 · Cited by 2,890
Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., Liston, D. E., Low, D. K.-W., Newman, S.-F., Kim, J., et al. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0304-0 · Cited by 1,967
Continuous glucose monitoring and intensive treatment of type 1 diabetes
(2008) · New England Journal of Medicine · doi:10.1056/nejmoa0805017 · Cited by 1,559
Research works printed but not linked: 33
- 10.1111/dom.12142 · DOI
- 10.2337/dc08-0607 · DOI · Paper page
- 10.1038/tp.2016.296 · DOI · Paper page
- 10.1097/MOP.0b013e32833a46a7 · DOI · Paper page
- 10.1007/s11892-015-0621-6 · DOI · Paper page
- 10.1515/JPEM.1998.11.S1.189 · DOI · Paper page
- 10.1007/s10880-008-9123-x · DOI · Paper page
- 10.1089/dia.2015.0417 · DOI · Paper page
- Langendam M, 2012, Cochrane Database of Syst Rev, 1
- 10.1177/193229681300700227 · DOI · Paper page
- 10.1089/dia.2016.0319 · DOI · Paper page
- 10.1371/journal.pone.0253125 · DOI · Paper page
- 10.1177/1932296820922622 · DOI · Paper page
- 10.1177/1932296819868727 · DOI · Paper page
- 10.1089/dia.2009.0076 · DOI · Paper page
- 10.1177/1932296815583507 · DOI
- 10.1109/TITB.2009.2034141 · DOI · Paper page
- Pedregosa F, 2011, J Mach Learn Res, 12, 2825
- Chen T, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 785
- Breiman L., 1996, Bias, variance, and arcing classifiers
- Lundberg SM, 2017, Proceedings of the 31st International Conference on Neural Information Processing Systems
- Shapley LS. 17, 2016, Contributions to the Theory of Games (AM-28)
- 10.1145/2939672.2939778 · DOI · Paper page
- 10.2196/26909 · DOI
- 10.1089/dia.2019.0011 · DOI · Paper page
- 10.1089/dia.2016.0349 · DOI · Paper page
- Vu L, 2019, AMIA Annu Symp Proc, 2019, 874
- 10.2196/22458 · DOI · Paper page
- 10.1177/1932296820978423 · DOI
- 10.1089/dia.2012.0298 · DOI · Paper page
- 10.2337/dc06-1085 · DOI · Paper page
- 10.2337/diacare.20.11.1655 · DOI · Paper page
- 10.2337/diacare.21.11.1870 · DOI · Paper page
Cited by
Hasan, R., Dattana, V., Mahmood, S., & Hussain, S. (2024) · Information · doi:10.3390/info16010007 · Cited by 44
Giza, S., Kotanidou, E. P., Tsinopoulou, V. R., Poukoulidou, T., Ntouma, S., & Galli-Tsinopoulou, A. (2025) · Children · doi:10.3390/children12121668 · Cited by 7
“Maximizing model performance for glucose risk prediction and management is crucial for reducing the burden of alarm fatigue on CGM users [74].”
Digital Management of Early-Onset Type 2 Diabetes: Empowerment, Challenges, and Future Outlook
Guo, L.-J., Low, K.-S., Tae, S.-K., & Lim, L.-L. (2026) · Current Diabetes Reports · doi:10.1007/s11892-026-01633-6
Metadata
- Authors
- Duckworth, C., Guy, M. J., Kumaran, A., O’Kane, A. A., Ayobi, A., Chapman, A., Marshall, P., & Boniface, M.
- Venue
- Journal of Diabetes Science and Technology
- Publisher
- SAGE Publications
- Published
- 2022-06-13
- Volume
- 18
- Issue
- 1
- Pages
- 113-123
- ISSN
- 1932-2968
- Cited by
- 75
- References
- 23
- Language
- en
- Funders
- UKRI Trustworthy Autonomous Systems Hub (RITM0372366)
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations. https://app.cochat.ai/papers/10.1177/19322968221103561
- The paper
- 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. https://doi.org/10.1177/19322968221103561
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.