An official website of the United States government
Abstract BackgroundEffective diabetes management requires precise glycemic control to prevent both hypoglycemia and hyperglycemia, yet existing machine learning (ML) and reinforcement learning (RL) approaches often fail to balance competing objectives. Traditional RL-based glucose regulation systems primarily focus on single-objective optimization, overlooking factors such as minimizing insulin overuse, reducing glycemic variability, and ensuring patient safety. Furthermore, these approaches typically rely on centralized data processing, which raises privacy concerns due to the sensitive nature of health care data. There is a critical need for a decentralized, privacy-preserving framework that can personalize blood glucose regulation while addressing the multiobjective nature of diabetes management. ObjectiveThis study aimed to develop and validate PRIMO-FRL (Privacy-Preserving Reinforcement Learning for Individualized Multi-Objective Glycemic Management Using Federated Reinforcement Learning), a novel framework that optimizes clinical objectives—maximizing time in range (TIR), reducing hypoglycemia and hyperglycemia, and minimizing glycemic risk—while preserving patient privacy. MethodsWe developed PRIMO-FRL, integrating multiobjective reward shaping to dynamically balance glucose stability, insulin efficiency, and risk reduction. The model was trained and tested using simulated data from 30 simulated patients (10 children, 10 adolescents, and 10 adults) generated with the Food and Drug Administration (FDA)–approved UVA/Padova simulator. A comparative analysis was conducted against state-of-the-art RL and ML models, evaluating performance using metrics such as TIR, hypoglycemia (<70 mg/dL), hyperglycemia (>180 mg/dL), and glycemic risk scores. ResultsThe PRIMO-FRL model achieved a robust overall TIR of 76.54%, with adults demonstrating the highest TIR at 81.48%, followed by children at 77.78% and adolescents at 70.37%. Importantly, the approach eliminated hypoglycemia, with 0.0% spent below 70 mg/dL across all cohorts, significantly outperforming existing methods. Mild hyperglycemia (180-250 mg/dL) was observed in adolescents (29.63%), children (22.22%), and adults (18.52%), with adults exhibiting the best control. Furthermore, the PRIMO-FRL approach consistently reduced glycemic risk scores, demonstrating improved safety and long-term stability in glucose regulation.. ConclusionsOur findings highlight the potential of PRIMO-FRL as a transformative, privacy-preserving approach to personalized glycemic management. By integrating federated RL, this framework eliminates hypoglycemia, improves TIR, and preserves data privacy by decentralizing model training. Unlike traditional centralized approaches that require sharing sensitive health data, PRIMO-FRL leverages federated learning to keep patient data local, significantly reducing privacy risks while enabling adaptive and personalized glucose control. This multiobjective optimization strategy offers a scalable, secure, and clinically viable solution for real-world diabetes care. The ability to train personalized models across diverse populations without exposing raw data makes PRIMO-FRL well-suited for deployment in privacy-sensitive health care environments. These results pave the way for future clinical adoption, demonstrating the potential of privacy-preserving artificial intelligence in optimizing glycemic regulation while maintaining security, adaptability, and personalization.
more »
« less
This content will become publicly available on March 5, 2026
Predicting Postprandial Glycemic Responses With Limited Data in Type 1 and Type 2 Diabetes
Background:A core challenge in managing diabetes is predicting glycemic responses to meals. Prior work identified significant interindividual variation in responses and developed personalized forecasts. However, intraindividual variation is still not well understood, and the most accurate approaches require invasive microbiome data. We aimed to investigate (1) whether postprandial glycemic responses (PPGRs) can be predicted with limited data and (2) sources of intraindividual variation. Methods:We used data collected from 397 people with Type 1 Diabetes (T1DEXI) and 100 people with Type 2 Diabetes (ShanghaiT2DM) who wore continuous glucose monitors (CGMs) and logged meals. Using dietary, demographic, and temporal features, we predicted 2 hours PPGR, and peak 2 hours postprandial glucose rise (Glumax). We evaluated the contribution of food features (eg, macronutrients, food category) and use of personal training data and investigated intraindividual variability in responses. Results:We achieved comparable accuracy to prior work for PPGR (T1DEXI R = 0.61, ShanghaiT2DM R = 0.72) and Glumax(T1DEXI R = 0.64, ShanghaiT2DM R = 0.73), without using invasive data like microbiome. Including food category features led to higher accuracy than macronutrients alone. Analysis of glycemic responses to duplicate meals identified time of day (PPGR: T1DEXI P < .05 for lunch, ShanghaiT2DM P < .001 for lunch and dinner) and menstrual cycle (Glumax: P < .05 for perimenstrual) as sources of variability. Conclusions:We demonstrate that in individuals with T1D and T2D, glycemic responses to meals can be predicted without personalized training data or invasive physiological data.
more »
« less
- Award ID(s):
- 1915182
- PAR ID:
- 10575446
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Journal of Diabetes Science and Technology
- ISSN:
- 1932-2968
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Background:Achieving optimal glycemic control for persons with diabetes remains difficult. Real-world continuous glucose monitoring (CGM) data can illuminate previously underrecognized glycemic fluctuations. We aimed to characterize glucose trajectories in individuals with Type 1 and Type 2 diabetes, and to examine how baseline glycemic control, CGM usage frequency, and regional differences shape these patterns. Methods:We linked Dexcom CGM data (2015–2020) with Veterans Health Administration electronic health records, identifying 892 Type 1 and 1716 Type 2 diabetes patients. Analyses focused on the first three years of CGM use, encompassing over 2.1 million glucose readings. We explored temporal trends in average daily glucose and time-in-range values. Results:Both Type 1 and Type 2 cohorts exhibited a gradual rise in mean daily glucose over time, although higher CGM usage frequency was associated with lower overall glucose or attenuated increases. Notable weekly patterns emerged: Sundays consistently showed the highest glucose values, whereas Wednesdays tended to have the lowest. Seasonally, glycemic control deteriorated from October to February and rebounded from April to August, with more pronounced fluctuations in the Northeast compared to the Southwest U.S. Conclusions:Our findings underscore the importance of recognizing day-of-week and seasonal glycemic variations in diabetes management. Tailoring interventions to account for these real-world fluctuations may enhance patient engagement, optimize glycemic control, and ultimately improve health outcomes.more » « less
-
Both long- and short-term glycemic variability have been associated with incident diabetes complications. We evaluated their relative and potential additive effects on incident renal complications in the Action to Control Cardiovascular Risk in Diabetes trial. A marker of short-term glycemic variability, 1,5-anhydroglucitol (1,5-AG), was measured in 4,000 random 12-month postrandomization plasma samples (when hemoglobin A1c [HbA1c] was stable). Visit-to-visit fasting plasma glucose coefficient of variation (CV-FPG) was determined from 4 months postrandomization until the end point of microalbuminuria or macroalbuminuria. Using Cox proportional hazards models, high CV-FPG and low 1,5-AG were independently associated with microalbuminuria after adjusting for clinical risk factors. However, only the CV-FPG association remained after additional adjustment for average HbA1c. Only CV-FPG was a significant risk factor for macroalbuminuria. This post hoc analysis indicates that long-term rather than short-term glycemic variability better predicts the risk of renal disease in type 2 diabetes. Article HighlightsThe relative and potential additive effects of long- and short-term glycemic variability on the development of diabetic complications are unknown. We aimed to assess the individual and combined relationships of long-term visit-to-visit glycemic variability, measured as the coefficient of variation of fasting plasma glucose, and short-term glucose fluctuation, estimated by the biomarker 1,5-anhydroglucitol, with the development of proteinuria. Both estimates of glycemic variability were independently associated with microalbuminuria, but only long-term glycemic variability remained significant after adjusting for average hemoglobin A1c. Our findings suggest that longer-term visit-to-visit glucose variability improves renal disease prediction in type 2 diabetes.more » « less
-
null (Ed.)Diet monitoring is an important component of interventions in type 2 diabetes, but is time intensive and often inaccurate. To address this issue, we describe an approach to monitor diet automatically, by analyzing fluctuations in glucose after a meal is consumed. In particular, we evaluate three standardization techniques (baseline correction, feature normalization, and model personalization) that can be used to compensate for the large individual differences that exist in food metabolism. Then, we build machine learning models to predict the amounts of macronutrients in a meal from the associated glucose responses. We evaluate the approach on a dataset containing glucose responses for 15 participants who consumed 9 meals. Three techniques improve the accuracy of the models: subtracting the baseline glucose, performing z-score normalization, and scaling the amount of macronutrients by each individuals’ body mass index.more » « less
-
Monitoring glucose levels is critical for effective diabetes management. Continuous glucose monitoring devices estimate interstitial glucose levels and provide alerts for glycemic excursions. However, they are expensive and invasive. Therefore, low-cost, noninvasive alternatives are useful for patients with diabetes. In this article, we explore electrocardiogram signals as a potential alternative to detecting glycemic excursions by extracting intrabeat (beat-morphology) and inter-beat (heart rate variability) information. Unlike prior methods that focused only on the standard clinical excursion thresholds (70 mg/dL for hypoglycemia, 180 mg/dL for hyperglycemia), our proposed approach trains independent machine learning models at various excursion thresholds, aggregating their outputs for a final prediction. This allows learning morphological patterns in the neighborhood of the standard excursion thresholds. Our personalized fusion models achieve an AUC of 75 % for hypoglycemia and 78% for hyperglycemia detection across patients, resulting in an average improvement of 4 % compared to the baseline models (trained using only standard clinical thresholds) for detecting glycemic excursions. We also find that combining morphology and HRV information outperforms using them individually (5 % for hypoglycemia and 6 % for hyperglycemia). The data used in this article was collected from 12 patients with type-1 diabetes, each monitored over a 14-day period at Texas Children’s Hospital, Houston. The results indicate that a combination of morphological and HRV features is essential for noninvasive detection of glycemic excursions. Also, morphological changes can happen at varying glucose levels for different patients and capturing these changes provide valuable information that leads to improved prediction performance for detecting glycemic excursions.more » « less
