Type 1 Diabetes (T1D) is a chronic metabolic disease characterized by elevated blood glucose (BG) concentrations, resulting from the immune-mediated destruction of insulin-producing $\beta$-cells in the pancreas. Effective management of T1D greatly benefits from constant monitoring of BG levels, achievable in real-time using minimally invasive continuous glucose monitoring (CGM) devices. These devices provide data streams that can be leveraged by forecasting algorithms to predict BG levels minutes in advance, enabling timely therapeutic interventions to prevent adverse events, such as hypo/hyperglycemia. With the increasing availability of data, deep learning (DL) algorithms have emerged as the state-of-the-art for BG forecasting, owing to their ability to autonomously learn complex nonlinear relationships, such as those underlying the glucoregulatory system. Despite a growing body of research, a comprehensive review specifically focusing on DL applications for BG prediction is still lacking. To address this gap, a systematic review was conducted following the PRISMA guidelines, involving extensive searches across PubMed, Scopus, and Web of Science databases. A total of 26 studies satisfied the inclusion criteria and were evaluated based on dataset characteristics, model inputs, training paradigm, prediction horizon, model architecture, evaluation metrics, performance, and baseline comparators. While DL models show great promise, several challenges persist-particularly in ensuring physiological fidelity and interpretability, both essential for clinical adoption. To overcome these barriers, future research should prioritize the integration of explainable AI (XAI) techniques to improve model reliability and safety, ultimately supporting the effective deployment of DL models in real-time T1D management.

Type 1 diabetes (T1D) management in pediatric patients presents unique challenges due to the evolving physiology and the need for close monitoring and intervention. This article presents the system architecture of TWIN, a novel personalized Decision Support System (DSS) for managing multiple daily injections (MDI) therapy in pediatric T1D patients. TWIN incorporates advanced technologies such as continuous glucose monitoring (CGM) devices, smart insulin pens, and wearable physical activity trackers to collect large amounts of user-generated data. At its core, the system leverages an open-source digital twinning methodology called ReplayBG to create virtual clones of patients, representing their unique physiological characteristics. These virtual clones are then utilized in multiple simulation iterations to personalize and optimize therapy parameters. To promote the transparency of the generated results, TWIN employs a large-scale linguistic model based on a Generative Pre-trained Transformer (GPT). This model provides clear explanations and contextual information regarding the recommended therapy parameters. Finally, the proposed TWIN system architecture integrates these algorithms within a state-of-the-art digital platform. This platform offers a user-friendly interface for patients and healthcare providers, enabling effective management and tuning of MDI therapy. Future work will focus on testing and validating TWIN to assess its efficacy and usability in pediatric T1D management.

Type 1 diabetes (T1D) is a chronic condition characterized by elevated blood glucose (BG) levels resulting from the pancreas’ inability to secrete insulin. To keep their BG levels within the safe range of [70−180] mg/dL, individuals affected by T1D must adhere to a lifelong therapy, which involves multiple daily actions and may negatively impact patients’ quality of life.To address these challenges, decision support systems (DSSs) utilizing continuous glucose monitoring sensors have become vital in managing T1D. These tools assist individuals suggesting therapeutic actions like carbohydrate intake and insulin injections. In this context, accurate algorithms predicting future BG levels are essential for proactive interventions, improving glucose control and enhancing patient well-being.This paper presents a new algorithm for DSSs that recommends corrective insulin boluses (CIBs). The core of the proposed DSS is a BG predictive algorithm based on a long short-term memory (LSTM) neural network which has been trained on 12 patients with T1D monitored for 10 weeks. The proposed algorithm, named LSTM-CIB, has been retrospectively evaluated on an external test set composed by 30 T1D patients monitored in free-living conditions. Compared to a state-of-art heuristic-based strategy for hyperglycemia correction, LSTM-CIB significantly reduces time spent in hyperglycemia (33.26% vs. 39.42%) and increases time spent in euglycemia (65.29% vs. 59.16%), also improving patient safety.

Abstract The presented platform architecture and deployed implementation in real-life clinical and home care settings on four Amyotrophic Lateral Sclerosis (ALS) and Multiple Sclerosis (MS) study sites, integrates the novel working tools for improved disease management with the initial releases of the AI models for disease monitoring. The described robust industry-standard scalable platform is to be a referent example of the integration approach based on loose coupling APIs and industry open standard human-readable and language-independent interface specifications, and its successful baseline implementation for further upcoming releases of additional and more advanced AI models and supporting pipelines (such as for ALS and MS progression prediction, patient stratification, and ambiental exposure modelling) in the following development.

Mealtime insulin dosing is a major challenge for people living with type 1 diabetes (T1D). This task is typically performed using a standard formula that, despite containing some patient-specific parameters, often leads to sub-optimal glucose control due to lack of personalization and adaptation. To overcome the previous limitations here we propose an individualized and adaptive mealtime insulin bolus calculator based on double deep Q-learning (DDQ), which is tailored to the patient thanks to a personalization procedure relying on a two-step learning framework. The DDQ-learning bolus calculator was developed and tested using the UVA/Padova T1D simulator modified to reliably mimic real-world scenarios by introducing multiple variability sources impacting glucose metabolism and technology. The learning phase included a long-term training of eight sub-population models, one for each representative subject, selected thanks to a clustering procedure applied to the training set. Then, for each subject of the testing set, a personalization procedure was performed, by initializing the models based on the cluster to which the patient belongs. We evaluated the effectiveness of the proposed bolus calculator on a 60-day simulation, using several metrics representing the goodness of glycemic control, and comparing the results with the standard guidelines for mealtime insulin dosing. The proposed method improved the time in target range from 68.35% to 70.08% and significantly reduced the time in hypoglycemia (from 8.78% to 4.17%). The overall glycemic risk index decreased from 8.2 to 7.3, indicating the benefit of our method when applied for insulin dosing compared to standard guidelines.

In type 1 diabetes management, maintaining nocturnal blood glucose within target range can be challenging. Although semi-automatic systems to modulate insulin pump delivery, such as low-glucose insulin suspension and the artificial pancreas, are starting to become a reality, their elevated cost and performance below user expectations is hindering their adoption. Hence, a decision support system that helps people with type 1 diabetes, on multiple daily injections or insulin pump therapy, to avoid undesirable overnight blood glucose fluctuations (hyper- or hypoglycaemic) is an attractive alternative. In this paper, we introduce a novel data-driven approach to predict the quality of overnight glycaemic control in people with type 1 diabetes by analyzing commonly gathered data during the day-time period (continuous glucose monitoring data, meal intake and insulin boluses). The proposed approach is able to predict whether overnight blood glucose concentrations are going to remain within or outside the target range, and therefore allows the user to take the appropriate preventive action (snack or change in basal insulin). For this purpose, a number of popular established machine learning algorithms for binary classification were evaluated and compared on a publicly available clinical dataset (i.e., OhioT1DM). Although there is no clearly superior classification algorithm, this study indicates that, by using commonly gathered data in type 1 diabetes management, it is possible to predict the quality of overnight glycaemic control with reasonable accuracy (AUC-ROC = 0.7).