Aims: The accurate prediction of blood glucose (BG) levels is critical for managing Type-1 Diabetes (T1D) in pediatric patients, where variability due to factors like physical activity and developmental changes presents significant challenges. Methods: This work explores the application of foundational models, particularly the encoder–decoder model TimeGPT, for BG forecasting in T1D pediatric patients. Methods: The performance of TimeGPT is compared against state-of-the-art models, including ARIMAX and LSTM, and multilayer perceptron (MLP) architectures such as TiDE and TSMixer. The models were evaluated using continuous glucose monitoring (CGM) data and exogenous variables, such as insulin intake. Results: TimeGPT outperforms or achieves comparable accuracy to the state of the art and MLP models in short-term predictions (15 and 30 min), with most predictions falling within the clinically safe zones of the Clarke Error Grid. Conclusions: The findings suggest that foundational models like TimeGPT offer promising generalization capabilities for medical applications and can serve as valuable tools to enhance diabetes management in pediatric T1D patients.

Disease subtyping, which helps to develop personalized treatments, remains a challenge in data analysis because of the many different ways to group patients based upon their data. However, if we can identify subclasses of disease, then it will help to develop better models that are more specific to individuals and should therefore improve prediction and understanding of the underlying characteristics of the disease in question. This paper proposes a new algorithm that integrates consensus clustering methods with classification in order to overcome issues with sample bias. The new algorithm combines K-means with consensus clustering in order build cohort-specific decision trees that improve classification as well as aid the understanding of the underlying differences of the discovered groups. The methods are tested on a real-world freely available breast cancer dataset and data from a London hospital on systemic sclerosis, a rare potentially fatal condition. Results show that “nearest consensus clustering classification” improves the accuracy and the prediction significantly when this algorithm has been compared with competitive similar methods.

Diabetes is a high-prevalence disease that leads to an alteration in the patient’s blood glucose (BG) values. Several factors influence the subject’s BG profile over the day, including meals, physical activity, and sleep. Wearable devices are available for monitoring the patient’s BG value around the clock, while activity trackers can be used to record his/her sleep and physical activity. However, few tools are available to jointly analyze the collected data, and only a minority of them provide functionalities for performing advanced and personalized analyses. In this paper, we present AID-GM, a web application that enables the patient to share with his/her diabetologist both the raw BG data collected by a flash glucose monitoring device, and the information collected by activity trackers, including physical activity, heart rate, and sleep. AID-GM provides several data views for summarizing the subject’s metabolic control over time, and for complementing the BG profile with the information given by the activity tracker. AID-GM also allows the identification of complex temporal patterns in the collected heterogeneous data. In this paper, we also present the results of a real-world pilot study aimed to assess the usability of the proposed system. The study involved 30 pediatric patients receiving care at the Fondazione IRCCS Policlinico San Matteo Hospital in Pavia, Italy.

An interaction between metabolic glucose impairment and coronavirus disease 2019 is reported. The development of a severe multisystem inflammatory syndrome in children (MIS-C) related to SARS-CoV-2 infection has been described. We evaluated the impact of MIS-C on glycemic patterns in pediatric patients. A group of 30 children and adolescents affected by MIS-C were considered; all patients were normal weight. Clinical and biochemical assessments, including surrogate markers of insulin resistance (IR) such as homeostasis model analysis-IR (HOMA-IR) and triglyceride–glucose (TyG) indexes, were recorded. Patients were also invited to undergo an intermittently scanned continuous glucose monitoring (isCGM). HOMA-IR index was calculated in 18 patients (60%), of which 17 (94%) revealed a pathological value. TyG index was computed for all patients and pathological values were detected in all cases. In 15 patients, isCGM data were recorded on average for 9 days (±3 days). Overall, average glucose was 105 mg/dL (±16 mg/dL) and average time spent in the 70–180 mg/dL range (TIR) was 93.76%, with nearly 10% of glucose readings in the 141–180 mg/dL range; glycemic fluctuations over the hyperglycemic threshold were detected in four patients. Regular glucose monitoring may be useful to prevent metabolic imbalance and obtain a better outcome.

Type 1 Diabetes Mellitus (T1DM) is a chronic metabolic disease affecting millions of people worldwide. T1DM requires patients to continuously monitor their blood glucose levels. Due to pancreatic dysfunctions, patients use insulin injections to correct glucose values by synthetic insulin. Continuous Glucose Monitoring (CGM) is a system which includes an algorithm allowing to measure (and in some cases to predict) glucose levels at a frequent sampling time. This enable implementing advanced devices, including automated insulin pump delivery. Nevertheless, CGM still presents some limitations, including (i) the delay (time lag) in detecting change in glucose levels compared to the traditional blood glucose measurement, and (ii) the lack of a sufficient and acceptable time to accurately predict glucose values. We propose a framework based on a Gated Recurrent Unit (GRU) model to forecast both short- and long-term glucose values using heart rate (HR) and interstitial glucose (IG) values. The framework acquires HR and IG data and predicts glucose values with higher precision compared to state-of-the-art models. For training and testing the proposed framework, we used the OhioT1DM Dataset, which includes physiological data such as HR and IG values collected over an 8-week observation period. Additionally, we validated our framework using two other glucose datasets to ensure its generalizability across different HR and IG sampling frequencies. The proposed framework can be used to optimize the CGM system by incorporating patient HR measurements, thereby improving the prediction of short- and long-term glucose levels and reducing risks associated with conditions like hypoglycemia. Experimental tests were conducted using HR and IG data from the OhioT1DM Dataset, as well as from two additional T1DM patient datasets. We analyzed 6 patients from Ohio dataset while we validated the algorithm on 23 patients coming from two different university hospitals (6 from the University of Catanzaro medical hospital and 17 gathered from a validated study at IRCCS San Matteo Hospital in Pavia) for a total number of 29 patients. Our framework demonstrates an improvement in forecasting IG values in terms of RMSE and MAE for different choice of prediction horizons (PH). In the case of a PH of 5, 10, 20, 30, and 60 min, we reach an RMSE of 5.0, 9.38, 15.27, 20.48, and 34.16 respectively. The framework is freely available as an open-source, with an example dataset on a GitHub repository (see https://github.com/rafgia/attention_to_glycemia). Our framework offers a promising solution for improving glucose level prediction and management in T1DM patients. By leveraging a GRU model and incorporating HR and IG values, we achieve more precise glucose level forecasting compared to state-of-the-art models. This approach not only enhances the accuracy of glucose predictions but also mitigates the risks associated with hypoglycemia.