CoChat

Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations

Duckworth, Christopher, Guy, Matthew J., Kumaran, Anitha, O’Kane, Aisling Ann, Ayobi, Amid, Chapman, Adriane, Marshall, Paul, Boniface, Michael · 2024 · Journal of Diabetes Science and Technology

Published version of a preprint

Cited by 75

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.

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

Integrity signals

Registry

Crossref · 10.1177/19322968221103561

Cites

23 of 23 references verified0 citation errors · 0 not checkable

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.

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?

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

Show all 23 references

Research works printed but not linked: 33

  1. 10.1111/dom.12142 · DOI
  2. 10.2337/dc08-0607 · DOI · Paper page
  3. 10.1038/tp.2016.296 · DOI · Paper page
  4. 10.1097/MOP.0b013e32833a46a7 · DOI · Paper page
  5. 10.1007/s11892-015-0621-6 · DOI · Paper page
  6. 10.1515/JPEM.1998.11.S1.189 · DOI · Paper page
  7. 10.1007/s10880-008-9123-x · DOI · Paper page
  8. 10.1089/dia.2015.0417 · DOI · Paper page
  9. Langendam M, 2012, Cochrane Database of Syst Rev, 1
  10. 10.1177/193229681300700227 · DOI · Paper page
  11. 10.1089/dia.2016.0319 · DOI · Paper page
  12. 10.1371/journal.pone.0253125 · DOI · Paper page
  13. 10.1177/1932296820922622 · DOI · Paper page
  14. 10.1177/1932296819868727 · DOI · Paper page
  15. 10.1089/dia.2009.0076 · DOI · Paper page
  16. 10.1177/1932296815583507 · DOI
  17. 10.1109/TITB.2009.2034141 · DOI · Paper page
  18. Pedregosa F, 2011, J Mach Learn Res, 12, 2825
  19. Chen T, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 785
  20. Breiman L., 1996, Bias, variance, and arcing classifiers
  21. Lundberg SM, 2017, Proceedings of the 31st International Conference on Neural Information Processing Systems
  22. Shapley LS. 17, 2016, Contributions to the Theory of Games (AM-28)
  23. 10.1145/2939672.2939778 · DOI · Paper page
  24. 10.2196/26909 · DOI
  25. 10.1089/dia.2019.0011 · DOI · Paper page
  26. 10.1089/dia.2016.0349 · DOI · Paper page
  27. Vu L, 2019, AMIA Annu Symp Proc, 2019, 874
  28. 10.2196/22458 · DOI · Paper page
  29. 10.1177/1932296820978423 · DOI
  30. 10.1089/dia.2012.0298 · DOI · Paper page
  31. 10.2337/dc06-1085 · DOI · Paper page
  32. 10.2337/diacare.20.11.1655 · DOI · Paper page
  33. 10.2337/diacare.21.11.1870 · DOI · Paper page

Cited by

See all 75

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
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.