Development of Machine Learning Models to Predict Hypoglycemia and Hyperglycemia on Days of Hemodialysis in Patients with Diabetes based on Continuous Glucose Monitoring

Background/ObjectivesPatients with diabetes undergoing hemodialysis (HD) are at risk of asymptomatic hypo- and hypergly-cemia within 24 hours of dialysis. Continuous glucose monitoring (CGM) can improve glycemic control, and machine learning offers a promising approach to detect and predict glycemic excursions based on CGM data. This study aimed to develop machine learning models to predict substantial hypo- and hyperglycemia on dialysis days using CGM data and baseline characteristics. MethodsUsing data from 21 patients with diabetes receitarving HD, three classification models (Logistic Regression, XGBoost, and TabPFN) were trained and tested. Predictive features included CGM-derived metrics, HbA1c levels, and insulin use. A binary classification approach was used to predict level 2 hyperglycemia and level 1 hypoglycemia based on international consensus targets; CGM derived Time Above Range (TAR) [≥]10% and Time Below Range (TBR) [≥]1%. ResultsA total of 555 dialysis days were included in the analysis. The Logistic Regression model achieved the best performance for predicting hyperglycemia (F1 score: 0.85 [CI95,0.75-0.91]; ROC-AUC: 0.87 [CI95,0.78-0.93]). For hypoglycemia, TabPFN performed best (F1 score: 0.48 [CI95,0.26-0.69]; ROC-AUC: 0.88 [CI95,0.77-0.94]). ConclusionPrediction of substantial hypo- and hyperglycemia in patients with diabetes under-going HD appears feasible using machine learning models. Additional studies are needed to confirm clinical utility and generalizability.