Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia,Hypoglycemia,and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring
Restricted accessResearch articleFirst published online May, 2026
Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia,Hypoglycemia,and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring
The aim of this study was to develop and validate explainable prediction models based on continuous glucose monitoring (CGM) and baseline data to identify a week-to-week risk of CGM key metrics (hyperglycemia, hypoglycemia, glycemic variability). By having a weekly prediction of CGM key metrics, it is possible for the patient or health care personnel to take immediate preemptive action.
Methods:
We analyzed, trained, and internally tested three prediction models (Logistic regression, XGBoost, and TabNet) using CGM data from 187 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach combined with feature engineering deployed on the CGM signals was used to predict hyperglycemia, hypoglycemia, and glycemic variability based on consensus targets (time above range ≥5%, time below range ≥4%, coefficient of variation ≥36%). The models were validated in two independent cohorts with a total of 223 additional patients of varying ages.
Results:
A total of 46 593 weeks of CGM data were included in the analysis. For the best model (XGBoost), the area under the receiver operating characteristic curve (ROC-AUC) was 0.9 [95% confidence interval (CI) = 0.89-0.91], 0.89 [95% CI = 0.88-0.9], and 0.8 [95% CI = 0.79-0.81] for predicting hyperglycemia, hypoglycemia, and glycemic variability in the interval validation, respectively. The validation test showed good generalizability of the models with ROC-AUC of 0.88 to 0.95, 0.84 to 0.89, and 0.80 to 0.82 for predicting the glycemic outcomes.
Conclusion:
Prediction models based on real-world CGM data can be used to predict the risk of unstable glycemic control in the forthcoming week. The models showed good performance in both internal and external validation cohorts.
KatsarouAGudbjörnsdottirSRawshaniA, et al. Type 1 diabetes mellitus. Nat Rev Dis Primers. 2017;3:1-17.
2.
AtkinsonMAEisenbarthGS. Type 1 diabetes: new perspectives on disease pathogenesis and treatment. Lancet. 2001;358:221-229.
3.
LindMSvenssonAMKosiborodM, et al. Glycemic control and excess mortality in type 1 diabetes. N Engl J Med. 2014;371:1972-1982.
4.
CraneMALamAEkanayakeE, et al. Mortality due to hyperglycemic crises in the US, 1999-2022. JAMA. 2024;331:440-442.
5.
ElsayedNAAleppoGArodaVR, et al. 6. Glycemic targets: standards of care in diabetes—2023. Diabetes Care. 2023;46:S97.
6.
CerielloAMonnierLOwensD. Glycaemic variability in diabetes: clinical and therapeutic implications. Lancet Diabetes Endocrinol. 2019;7:221-230.
7.
PoolsupNSuksomboonNKyawAM. Systematic review and meta-analysis of the effectiveness of continuous glucose monitoring (CGM) on glucose control in diabetes. Diabetol Metab Syndr. 2013;5:1-14.
8.
SuhSKimJH. Glycemic variability: how do we measure it and why is it important?Diabetes Metab J. 2015;39:273-282.
9.
CryerPE. Minimizing hypoglycemia in diabetes. Diabetes Care. 2015;38:1583-1591.
10.
FidlerCElmelund ChristensenTGillardS, et al. Hypoglycemia: an overview of fear of hypoglycemia, quality-of-life, and impact on costs. J Med Econ. 2011;14:646-655. doi:103111/136969982011610852.
11.
LaaksoM. Hyperglycemia and cardiovascular disease in type 2 diabetes. Diabetes. 1999;48:937-942.
12.
RoloAPPalmeiraCM. Diabetes and mitochondrial function: role of hyperglycemia and oxidative stress. Toxicol Appl Pharmacol. 2006;212:167-178.
Juvenile Diabetes Research Foundation Continuous Glucose Monitoring Study Group; TamborlaneWVBeckRWBodeBW, et al. Continuous glucose monitoring and intensive treatment of type 1 diabetes. N Engl J Med. 2008;359:1464-1476.
15.
DanneTNimriRBattelinoT, et al. International consensus on use of continuous glucose monitoring. Diabetes Care. 2017;40:1631-1640.
16.
WoldaregayAZÅrsandEBotsisT, et al. Data-driven blood glucose pattern classification and anomalies detection: machine-learning applications in type 1 diabetes. J Med Internet Res. 2019;21(5):e11030. Accessed September 25, 2024. https://www.jmir.org/2019/5/e11030
17.
Zhu Y. Automatic detection of anomalies in blood glucose using a machine learning approach. Paper presented at the2010 IEEE International Conference on Information Reuse and Integration, IRI; August2010; Las Vegas, NV.
18.
BotweyRHDaskalakiEDiemP, et al. Multi-model data fusion to improve an early warning system for hypo-/hyperglycemic events. Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:4843-4846.
19.
NguyenLLSuSNguyenHT. Neural network approach for non-invasive detection of hyperglycemia using electrocardiographic signals. Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:4475-4478.
20.
CichoszSLFrystykJHejlesenOK, et al. A novel algorithm for prediction and detection of hypoglycemia based on continuous glucose monitoring and heart rate variability in patients with type 1 diabetes. J Diabetes Sci Technol. 2014;8:731-737. doi:101177/1932296814528838.
21.
CichoszSLJensenMHHejlesenO. Short-term prediction of future continuous glucose monitoring readings in type 1 diabetes: development and validation of a neural network regression model. Int J Med Inform. 2021;151:104472.
22.
CichoszSLFrystykJTarnowL, et al. Combining information of autonomic modulation and CGM measurements enables prediction and improves detection of spontaneous hypoglycemic events. J Diabetes Sci Technol. 2015;9:132-137.
23.
CichoszSLKronborgTJensenMH, et al. Penalty weighted glucose prediction models could lead to better clinically usage. Comput Biol Med. 2021;138:104865.
24.
DaveDDeSalvoDJHaridasB, et al. Feature-based machine learning model for real-time hypoglycemia prediction. J Diabetes Sci Technol. 2021;15:842-855.
25.
FleischerJHansenTKCichoszSL. Hypoglycemia event prediction from CGM using ensemble learning. Front Clin Diabetes Healthc. 2022;3:71.
26.
DiouriOCiglerMVettorettiM, et al. Hypoglycaemia detection and prediction techniques: a systematic review on the latest developments. Diabetes Metab Res Rev. 2021;37:e3449.
27.
DuckworthCGuyMJKumaranA, et al. Explainable machine learning for real-time hypoglycemia and hyperglycemia prediction and personalized control recommendations. J Diabetes Sci Technol. 2024;18(1):113-123. doi:10.1177/19322968221103561.
28.
WileyMBunescuRMarlingC, et al. Automatic detection of excessive glycemic variability for diabetes management. Paper presented at the ICMLA’11: Proceedings of the 2011 10th International Conference on Machine Learning and Applications; December 2011; Washington, DC.
29.
PratleyREKanapkaLGRickelsMR, et al. Effect of continuous glucose monitoring on hypoglycemia in older adults with type 1 diabetes: a randomized clinical trial. JAMA. 2020;323:2397.
30.
AleppoGRuedyKJRiddlesworthTD, et al. REPLACE-BG: a randomized trial comparing continuous glucose monitoring with and without routine blood glucose monitoring in adults with well-controlled type 1 diabetes. Diabetes Care. 2017;40:538-545.
31.
LaffelLMKanapkaLGBeckRW, et al. Effect of continuous glucose monitoring on glycemic control in adolescents and young adults with type 1 diabetes: a randomized clinical trial. JAMA. 2020;323:2388-2396.
32.
MonnierLColetteCWojtusciszynA, et al. Toward defining the threshold between low and high glucose variability in diabetes. Diabetes Care. 2017;40:832-838.
33.
BattelinoTDanneTBergenstalRM, et al. Clinical targets for continuous glucose monitoring data interpretation: recommendations from the international consensus on time in range. Diabetes Care. 2019;42:1593-1603.
34.
KlonoffDCWangJRodbardD, et al. A Glycemia Risk Index (GRI) of hypoglycemia and hyperglycemia for continuous glucose monitoring validated by clinician ratings. J Diabetes Sci Technol. 2023;17:1226-1242.
35.
ServiceFJMolnarGDRosevearJW, et al. Mean amplitude of glycemic excursions, a measure of diabetic instability. Diabetes. 1970;19:644-655.
36.
YamashitaRNishioMDoRKG, et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9:611-629.
37.
GeurtsPIrrthumAWehenkelL. Supervised learning with decision tree-based methods in computational and systems biology. Mol Biosyst. 2009;5:1593-1605.
38.
GuisanAEdwardsTCHastieT. Generalized linear and generalized additive models in studies of species distributions: setting the scene. Ecol Modell. 2002;157:89-100.
39.
LermanPM. Fitting segmented regression models by grid search. J R Stat Soc Ser C Appl Stat. 1980;29:77-84.
40.
FushikiT. Estimation of prediction error by using K-fold cross-validation. Stat Comput. 2011;21:137-146.
41.
BursacZGaussCHWilliamsDK, et al. Purposeful selection of variables in logistic regression. Source Code Biol Med. 2008;3:1-8.
42.
SchoberPVetterTR. Logistic regression in medical research. Anesth Analg. 2021;132:365.
43.
StoltzfusJC. Logistic regression: a brief primer. Acad Emerg Med. 2011;18:1099-1104.
44.
ChenTGuestrinC. XGBoost: a scalable tree boosting system. Paper presented at the Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. August 2016; San Francisco, CA.
45.
YadawASLiYBoseS, et al. Clinical features of COVID-19 mortality: development and validation of a clinical prediction model. Lancet Digit Health. 2020;2:e516-e525.
46.
XuYYangXHuangH, et al. Extreme gradient boosting model has a better performance in predicting the risk of 90-day readmissions in patients with ischaemic stroke. J Stroke Cerebrovasc Dis. 2019;28:104441.
47.
OgunleyeAWangQG. XGBoost model for chronic kidney disease diagnosis. IEEE/ACM Trans Comput Biol Bioinform. 2020;17:2131-2140.
MetzCE. Basic principles of ROC analysis. Semin Nucl Med. 1978;8:283-298.
50.
LundbergSMAllenPGLeeSI. A unified approach to interpreting model predictions. Paper presented at the 31st Conference on Neural Information Processing Systems (NIPS 2017). December 2017; Long Beach, CA.
51.
CichoszSLJensenMHSchouS, et al. Development and validation of a machine learning model to predict weekly risk of hypoglycemia in patients with type 1 diabetes based on continuous glucose monitoring. Diabetes Technol Ther. 2024;26(7):457-466. doi:10.1089/DIA.2023.0532. https://www.liebertpub.com/doi/10.1089/dia.2023.0532
52.
CichoszSLJensenMHHejlesenO. Optimal data collection period for continuous glucose monitoring to assess long-term glycemic control: revisited. J Diabetes Sci Technol. 2023;17:690-695.
53.
HouNLiMHeL, et al. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J Transl Med. 2020;18:1-14.
54.
WangRWangLZhangJ, et al. XGBoost machine learning algorism performed better than regression models in predicting mortality of moderate-to-severe traumatic brain injury. World Neurosurg. 2022;163:e617-e622.
55.
Shwartz-ZivRArmonA. Tabular data: deep learning is not all you need. Inf Fusion. 2022;81:84-90.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
