Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis
Published version of a preprint
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Background: Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. Objective: In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. Methods: PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. Results: In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Conclusions: Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. Trial Registration: PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250
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 [47]
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
QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies
Whiting, P. F., Rutjes, A. W. S., Westwood, M. E., Mallett, S., Deeks, J. J., Reitsma, J. B., Leeflang, M. M. G., Sterne, J. A. C., Bossuyt, P. M. M., & the QUADAS-2 Group* (2011) · Annals of Internal Medicine · doi:10.7326/0003-4819-155-8-201110180-00009 · Cited by 14,199
Saeedi, P., Petersohn, I., Salpea, P., Malanda, B., Karuranga, S., Unwin, N., Colagiuri, S., Guariguata, L., Motala, A. A., Ogurtsova, K., et al. (2019) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2019.107843 · Cited by 10,792
Cochrane Handbook for Systematic Reviews of Interventions
Higgins, J. P. T., Green, S., & Ben Van Den, A. (2020) · International Coaching Psychology Review · doi:10.53841/bpsicpr.2020.15.2.123 · Cited by 5,670
Continuous glucose monitoring: a review of recent studies demonstrating improved glycemic outcomes
Rodbard, D. (2017) · Diabetes Technology & Therapeutics · doi:10.1089/dia.2017.0035 · Cited by 458
Multivariate Random-effects Meta-regression: Updates to Mvmeta
White, I. R. (2011) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x1101100206 · Cited by 400
There is no such thing as a validated prediction model
Van Calster, B., Steyerberg, E. W., Wynants, L., & van Smeden, M. (2023) · BMC Medicine · doi:10.1186/s12916-023-02779-w · Cited by 286
A review of personalized blood glucose prediction strategies for T1DM patients
Oviedo, S., Vehí, J., Calm, R., & Armengol, J. (2017) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.2833 · Cited by 279 · cited 1×
“Diabetes mellitus (DM) has become one of the most serious health problems worldwide [1], with more than 463 million (9.3”
BackgroundInfluentialDeng, Y., Lu, L., Aponte, L., Angelidi, A. M., Novak, V., Karniadakis, G. E., & Mantzoros, C. S. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00480-x · Cited by 152 · cited 1×
“Recently, studies have focused on more novel deep learning models, such as transformers, which have also been proved clinically useful [72].”
BackgroundPrediction of hypoglycemia during aerobic exercise in adults with type 1 diabetes
Reddy, R., Resalat, N., Wilson, L. M., Castle, J. R., El Youssef, J., & Jacobs, P. G. (2019) · Journal of Diabetes Science and Technology · doi:10.1177/1932296818823792 · Cited by 75
Non-invasive hypoglycemia monitoring system using extreme learning machine for Type 1 diabetes
Ling, S. H., San, P. P., & Nguyen, H. T. (2016) · ISA Transactions · doi:10.1016/j.isatra.2016.05.008 · Cited by 62
Research works printed but not linked: 62
- 10.1186/s12916-022-02709-2 · doi:10.1186/s12916-022-02709-2
- 10.1016/j.diabres.2021.109040 · DOI
- 10.1080/0886022X.2020.1866010 · DOI
- 10.4093/dmj.2020.0100 · DOI
- 10.1007/s11892-019-1189-3 · DOI · Paper page
- Jain, AMC, 2012, J Diab Foot Comp, 4, 1
- 10.1111/j.1728-4465.1999.00067.x · DOI
- 10.2196/14340 · DOI
- 10.1001/jamainternmed.2014.1824 · DOI · Paper page
- 10.1080/0886022X.2022.2056053 · DOI · Paper page
- 10.1016/j.artmed.2021.102120 · DOI
- 10.1186/s12911-019-0943-4 · DOI
- 10.1109/EMBC.2013.6610766 · DOI
- 10.3390/app11041742 · DOI
- 10.1089/dia.2013.0104 · DOI · Paper page
- 10.1109/EMBC.2014.6943589 · DOI
- 10.1089/dia.2009.0076 · DOI · Paper page
- 10.3390/s21051647 · DOI · Paper page
- 10.1007/s41666-020-00068-2 · DOI
- 10.1371/journal.pmed.1000097 · DOI · Paper page
- 10.1136/bmj.b2700 · DOI · Paper page
- 10.1136/bmj.327.7414.557 · DOI · Paper page
- 10.3390/s22041665 · DOI
- 10.1111/dme.13409 · DOI
- 10.3390/s20061705 · DOI
- 10.1016/j.diabres.2020.108388 · DOI
- 10.1089/dia.2019.0458 · DOI
- 10.2337/dc19-1743 · DOI · Paper page
- 10.1109/JBHI.2019.2938305 · DOI
- 10.1177/1932296819868727 · DOI · Paper page
- 10.1016/j.ijmedinf.2019.03.008 · DOI
- 10.1177/1932296819880864 · DOI
- 10.1016/j.eswa.2011.02.020 · DOI
- 10.1109/IEMBS.2010.5627233 · DOI
- 10.3390/e22010081 · DOI
- 10.2196/11990 · DOI
- 10.1089/dia.2013.0069 · DOI · Paper page
- 10.1177/193229681000400109 · DOI
- 10.1007/BF02344732 · DOI
- BertachiABiagiLContrerasILuoNVehíJPrediction of blood glucose levels and nocturnal hypoglycemia using physiological models and artificial neural networks20133rd International Workshop on Knowledge Discovery in Healthcare DataJuly 13, 2018Stockholm, Sweden
- Eljil, KAAS, 2014, Predicting Hypoglycemia in Diabetic Patients Using Machine Learning Techniques
- 10.1016/j.knosys.2020.106134 · DOI
- 10.1089/dia.2019.0435 · DOI
- 10.1109/jbhi.2019.2931842 · DOI · Paper page
- 10.1109/TBME.2012.2188893 · DOI · Paper page
- 10.1109/EMBC44109.2020.9176695 · DOI
- 10.1109/JBHI.2021.3100558 · DOI
- 10.1016/j.bbe.2020.10.004 · DOI
- 10.1177/1932296820922622 · DOI · Paper page
- 10.1002/dmrr.3348 · DOI
- 10.1177/1932296816670400 · DOI
- 10.1177/1932296814554260 · DOI · Paper page
- 10.1007/s10439-011-0446-7 · DOI
- 10.1109/TCYB.2013.2283296 · DOI · Paper page
- 10.1016/j.artmed.2012.04.003 · DOI
- 10.1109/EMBC.2012.6346724 · DOI
- 10.1109/JBHI.2019.2931782 · DOI
- 10.1109/EMBC.2018.8513069 · DOI
- 10.1109/ijcnn.2010.5596916 · DOI
- 10.1001/jama.271.9.703 · doi:10.1001/jama.271.9.703 · Paper page
- 10.2196/22458 · DOI · Paper page
- McShinskyRMarshallBComparison of forecasting algorithms for type 1 diabetic glucose prediction on 30 and 60-minute prediction horizons2020KDH@ECAI 2020: 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial IntelligenceAugust 29-30, 2020Santiago de Compostela, Spain, and virtually
Cited by
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
- Liu, K., Li, L., Ma, Y., Jiang, J., Liu, Z., Ye, Z., Liu, S., Pu, C., Chen, C., & Wan, Y.
- Venue
- JMIR Medical Informatics
- Publisher
- JMIR Publications Inc.
- Published
- 2023-11-20
- Volume
- 11
- Pages
- e47833
- ISSN
- 2291-9694
- Cited by
- 67
- References
- 10
- Language
- en
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
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.