Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care. Utilizing population models to address this challenge is a potential solution, but collecting patient data for training population models in a privacy-conscious manner is challenging, especially given that such data is often stored on personal devices. Considering the privacy protection and addressing the "cold start" problem in diabetes care, we propose "GluADFL", blood Glucose prediction by Asynchronous Decentralized Federated Learning. We compared GluADFL with eight baseline methods using four distinct T1D datasets, comprising 298 participants, which demonstrated its superior performance in accurately predicting BG levels for cross-patient analysis. Furthermore, patients' data might be stored and shared across various communication networks in GluADFL, ranging from highly interconnected (e.g., random, performs the best among others) to more structured topologies (e.g., cluster and ring), suitable for various social networks. The asynchronous training framework supports flexible participation. By adjusting the ratios of inactive participants, we found it remains stable if less than 70% are inactive. Our results confirm that GluADFL offers a practical, privacy-preserved solution for BG prediction in T1D, significantly enhancing the quality of diabetes management.

Augmenting traditional genome-wide association studies (GWAS) with advanced machine learning algorithms can allow the detection of novel signals in available cohorts. We introduce "genome-wide association neural networks (GWANN)" a novel approach that uses neural networks (NNs) to perform a gene-level association study with family history of Alzheimer's disease (AD). In UK Biobank, we defined cases (n = 42 110) as those with AD or family history of AD and sampled an equal number of controls. The data was split into an 80:20 ratio of training and testing samples, and GWANN was trained on the former followed by identifying associated genes using its performance on the latter. Our method identified 18 genes to be associated with family history of AD. APOE, BIN1, SORL1, ADAM10, APH1B, and SPI1 have been identified by previous AD GWAS. Among the 12 new genes, PCDH9, NRG3, ROR1, LINGO2, SMYD3, and LRRC7 have been associated with neurofibrillary tangles or phosphorylated tau in previous studies. Furthermore, there is evidence for differential transcriptomic or proteomic expression between AD and healthy brains for 10 of the 12 new genes. A series of post hoc analyses resulted in a significantly enriched protein-protein interaction network (P-value < 1 × 10-16), and enrichment of relevant disease and biological pathways such as focal adhesion (P-value = 1 × 10-4), extracellular matrix organization (P-value = 1 × 10-4), Hippo signaling (P-value = 7 × 10-4), Alzheimer's disease (P-value = 3 × 10-4), and impaired cognition (P-value = 4 × 10-3). Applying NNs for GWAS illustrates their potential to complement existing algorithms and methods and enable the discovery of new associations without the need to expand existing cohorts.

Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with type 1 or 2 diabetes, thereby reducing complications and improving quality of life. The state of the art of BG prediction has been achieved by leveraging advanced deep learning methods to model multimodal data, i.e., sensor data and self-reported event data, organized as multi-variate time series (MTS). However, these methods are mostly regarded as "black boxes" and not entirely trusted by clinicians and patients. In this paper, we propose interpretable graph attentive recurrent neural networks (GARNNs) to model MTS, explaining variable contributions via summarizing variable importance and generating feature maps by graph attention mechanisms instead of post-hoc analysis. We evaluate GARNNs on four datasets, representing diverse clinical scenarios. Upon comparison with fifteen well-established baseline methods, GARNNs not only achieve the best prediction accuracy but also provide high-quality temporal interpretability, in particular for postprandial glucose levels as a result of corresponding meal intake and insulin injection. These findings underline the potential of GARNN as a robust tool for improving diabetes care, bridging the gap between deep learning technology and real-world healthcare solutions.

Real-time continuous glucose monitoring (CGM), augmented with accurate glucose prediction, offers an effective strategy for maintaining blood glucose levels within a therapeutically appropriate range. This is particularly crucial for individuals with type 1 diabetes (T1D) who require long-term self-management. However, with extensive glycemic variability, developing a prediction algorithm applicable across diverse populations remains a significant challenge. Leveraging meta-learning for domain generalization, we propose GPFormer, a Transformer-based zero-shot learning method designed for multi-horizon glucose prediction. We developed GPFormer on the REPLACE-BG dataset, comprising 226 participants with T1D, and proceeded to evaluate its performance using three external clinical datasets with CGM data. These included the OhioT1DM dataset, a publicly available dataset including 12 T1D participants, as well as two proprietary datasets. The first proprietary dataset included 22 participants, while the second contained 45 participants, encompassing a diverse group with T1D, type 2 diabetes, and those without diabetes, including patients admitted to hospitals. These four datasets include both outpatient and inpatient settings, various intervention strategies, and demographic variability, which effectively reflect real-world scenarios of CGM usage. When compared with a group of machine learning baseline methods, GPFormer consistently demonstrated superior performance and achieved the lowest root mean square error for all the evaluated datasets up to a prediction horizon of two hours. These experimental results highlight the effectiveness and generalizability of the proposed model across a variety of populations, demonstrating its substantial potential to enhance glucose management in a wide range of practical clinical settings.

This paper demonstrates a novel framework utilising artificial neural networks (ANNs) to identify electrochemical signals, estimate drift and perform signal extraction for ISFET sensors. We propose a neural network based on the combination of Multi-Layer Perceptrons (MLPs) and Gated Recurrent Units (GRUs), to aid the analysis of chemical reactions for ISFETs by identifying the reaction origin and compensating for drift in real time. The model is trained and tested using Keras on an artificial dataset, achieving a reaction classification accuracy of 89.71 % with an average delay of 15.73s. We have also implemented the proposed model on an FPGA through high-level synthesis (HLS) with a tunable latency of 56254 clock cycles under an 100 MHz clock. This work paves the way for enhancing biosensors with ANNs, where a smart electrochemical imager with integrated edge processing can be implemented for various biomedical applications.

Deep learning models have achieved the state of the art in blood glucose (BG) prediction, which has been shown to improve type 1 diabetes (T1D) management. However, most existing models can only provide single-horizon prediction and face a variety of real-world challenges, such as lacking hardware implementation and interpretability. In this work, we introduce a new deep learning framework, the edge-based temporal fusion Transformer (E-TFT), for multi-horizon BG prediction, and implement the trained model on a customized wristband with a system on a chip (Nordic nRF52832) for edge computing. E-TFT employs a self-attention mechanism to extract long-term temporal dependencies and enables post-hoc explanation for feature selection. On a clinical dataset with 12 T1D subjects, it achieved a mean root mean square error of 19.09 ± 2.47 mg/dL and 32.31 ± 3.79 mg/dL for 30 and 60-minute prediction horizons, respectively, and outperformed all the considered baseline methods, such as N-BEATS and N-HiTS. The proposed model is effective for multi-horizon BG prediction and can be deployed on wearable devices to enhance T1D management in clinical settings.

Blood glucose (BG) prediction is essential to the success of glycemic control in type 1 diabetes (T1D) management. Empowered by the recent development of the Internet of Medical Things (IoMT), continuous glucose monitoring (CGM) and deep learning technologies have been demonstrated to achieve the state of the art in BG prediction. However, it is challenging to implement such algorithms in actual clinical settings to provide persistent decision support due to the high demand for computational resources, while smartphone-based implementations are limited by short battery life and require users to carry the device. In this work, we propose a new deep learning model using an attention-based evidential recurrent neural network and design an IoMT-enabled wearable device to implement the embedded model, which comprises a low-cost and low-power system on a chip to perform Bluetooth connectivity and edge computing for real-time BG prediction and predictive hypoglycemia detection. In addition, we developed a smartphone app to visualize BG trajectories and predictions, and desktop and cloud platforms to backup data and fine-tune models. The embedded model was evaluated on three clinical data sets including 47 T1D subjects. The proposed model achieved superior performance of root mean square error (RMSE), mean absolute error, and glucose-specific RMSE, and obtained the best accuracy for hypoglycemia detection when compared with a group of machine learning baseline methods. Moreover, we performed hardware-in-the-loop in silico trials with ten virtual T1D adults to test the whole IoMT system with predictive low-glucose management, which significantly reduced hypoglycemia and improved BG control.

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.

Recent advancements in hybrid closed-loop systems, also known as the artificial pancreas (AP), have been shown to optimize glucose control and reduce the self-management burdens for people living with type 1 diabetes (T1D). AP systems can adjust the basal infusion rates of insulin pumps, facilitated by real-time communication with continuous glucose monitoring. Deep reinforcement learning (DRL) has introduced new paradigms of basal insulin control algorithms. However, all the existing DRL-based AP controllers require extensive random online interactions between the agent and environment. While this can be validated in T1D simulators, it becomes impractical in real-world clinical settings. To this end, we propose an offline DRL framework that can develop and validate models for basal insulin control entirely offline. It comprises a DRL model based on the twin delayed deep deterministic policy gradient and behavior cloning, as well as off-policy evaluation (OPE) using fitted Q evaluation. We evaluated the proposed framework on an in silico dataset generated by the UVA/Padova T1D simulator, and the OhioT1DM dataset, a real clinical dataset. The performance on the in silico dataset shows that the offline DRL algorithm significantly increased time in range while reducing time below range and time above range for both adult and adolescent groups. Then, we used the OPE to estimate model performance on the clinical dataset, where a notable increase in policy values was observed for each subject. The results demonstrate that the proposed framework is a viable and safe method for improving personalized basal insulin control in T1D.

Time series data generated by continuous glucose monitoring sensors offer unparalleled opportunities for developing data-driven approaches, especially deep learning-based models, in diabetes management. Although these approaches have achieved state-of-the-art performance in various fields such as glucose prediction in type 1 diabetes (T1D), challenges remain in the acquisition of large-scale individual data for personalized modeling due to the elevated cost of clinical trials and data privacy regulations. In this work, we introduce GluGAN, a framework specifically designed for generating personalized glucose time series based on generative adversarial networks (GANs). Employing recurrent neural network (RNN) modules, the proposed framework uses a combination of unsupervised and supervised training to learn temporal dynamics in latent spaces. Aiming to assess the quality of synthetic data, we apply clinical metrics, distance scores, and discriminative and predictive scores computed by post-hoc RNNs in evaluation. Across three clinical datasets with 47 T1D subjects (including one publicly available and two proprietary datasets), GluGAN achieved better performance for all the considered metrics when compared with four baseline GAN models. The performance of data augmentation is evaluated by three machine learning-based glucose predictors. Using the training sets augmented by GluGAN significantly reduced the root mean square error for the predictors over 30 and 60-minute horizons. The results suggest that GluGAN is an effective method in generating high-quality synthetic glucose time series and has the potential to be used for evaluating the effectiveness of automated insulin delivery algorithms and as a digital twin to substitute for pre-clinical trials.

Real-time blood glucose (BG) prediction can enhance decision support systems for insulin dosing such as bolus calculators and closed-loop systems for insulin delivery. Deep learning has been proven to achieve state-of-the-art performance in BG prediction. However, it is usually seen as a very computationally expensive approach, hence difficult to implement in wearable medical devices such as transmitters in continuous glucose monitoring (CGM) systems. In this work, we introduce a novel deep learning framework to predict BG levels with the edge inference on a microcontroller unit embedded in a low- power system. By using glucose measurements from a CGM sensor and a recurrent neural network that builds on long-short term memory, the personalized models achieves state-of-the-art performance on a clinical data set obtained from 12 subjects with T1D. In particular, the proposed method achieves an average root mean square error of 19.10 ± 2.04 for a 30-minute prediction horizon (PH) and 32.61 ± 3.45 for a 60-minute PH with high clinical accuracy. Notably, the framework has been optimized to achieve a minimum use of hardware resources (34KB FLASH and 1KB SRAM) as well as an execution time of 22 ms for low power operations (8 μW). The presented system has the potential to be implemented in wearable medical devices for diabetes care (CGM and insulin pumps) and to be integrated within an Internet of Things platform.

People with Type 1 diabetes (T1D) require regular exogenous infusion of insulin to maintain their blood glucose concentration in a therapeutically adequate target range. Although the artificial pancreas and continuous glucose monitoring have been proven to be effective in achieving closed-loop control, significant challenges still remain due to the high complexity of glucose dynamics and limitations in the technology. In this work, we propose a novel deep reinforcement learning model for single-hormone (insulin) and dual-hormone (insulin and glucagon) delivery. In particular, the delivery strategies are developed by double Q-learning with dilated recurrent neural networks. For designing and testing purposes, the FDA-accepted UVA/Padova Type 1 simulator was employed. First, we performed long-term generalized training to obtain a population model. Then, this model was personalized with a small data-set of subject-specific data. In silico results show that the single and dual-hormone delivery strategies achieve good glucose control when compared to a standard basal-bolus therapy with low-glucose insulin suspension. Specifically, in the adult cohort (n = 10), percentage time in target range 70, 180 mg/dL improved from 77.6% to 80.9% with single-hormone control, and to 85.6% with dual-hormone control. In the adolescent cohort (n = 10), percentage time in target range improved from 55.5% to [Formula: see text] with single-hormone control, and to 78.8% with dual-hormone control. In all scenarios, a significant decrease in hypoglycemia was observed. These results show that the use of deep reinforcement learning is a viable approach for closed-loop glucose control in T1D.

Diabetes is a chronic metabolic disorder that affects an estimated 463 million people worldwide. Aiming to improve the treatment of people with diabetes, digital health has been widely adopted in recent years and generated a huge amount of data that could be used for further management of this chronic disease. Taking advantage of this, approaches that use artificial intelligence and specifically deep learning, an emerging type of machine learning, have been widely adopted with promising results. In this paper, we present a comprehensive review of the applications of deep learning within the field of diabetes. We conducted a systematic literature search and identified three main areas that use this approach: diagnosis of diabetes, glucose management, and diagnosis of diabetes-related complications. The search resulted in the selection of 40 original research articles, of which we have summarized the key information about the employed learning models, development process, main outcomes, and baseline methods for performance evaluation. Among the analyzed literature, it is to be noted that various deep learning techniques and frameworks have achieved state-of-the-art performance in many diabetes-related tasks by outperforming conventional machine learning approaches. Meanwhile, we identify some limitations in the current literature, such as a lack of data availability and model interpretability. The rapid developments in deep learning and the increase in available data offer the possibility to meet these challenges in the near future and allow the widespread deployment of this technology in clinical settings.

For people with Type 1 diabetes (T1D), forecasting of blood glucose (BG) can be used to effectively avoid hyperglycemia, hypoglycemia and associated complications. The latest continuous glucose monitoring (CGM) technology allows people to observe glucose in real-time. However, an accurate glucose forecast remains a challenge. In this work, we introduce GluNet, a framework that leverages on a personalized deep neural network to predict the probabilistic distribution of short-term (30-60 minutes) future CGM measurements for subjects with T1D based on their historical data including glucose measurements, meal information, insulin doses, and other factors. It adopts the latest deep learning techniques consisting of four components: data pre-processing, label transform/recover, multi-layers of dilated convolution neural network (CNN), and post-processing. The method is evaluated in-silico for both adult and adolescent subjects. The results show significant improvements over existing methods in the literature through a comprehensive comparison in terms of root mean square error (RMSE) ([Formula: see text] mg/dL) with short time lag ([Formula: see text] minutes) for prediction horizons (PH) = 30 mins (minutes), and RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 60 mins for virtual adult subjects. In addition, GluNet is also tested on two clinical data sets. Results show that it achieves an RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 30 mins and an RMSE ([Formula: see text] mg/dL) with time lag ([Formula: see text] mins) for PH = 60 mins. These are the best reported results for glucose forecasting when compared with other methods including the neural network for predicting glucose (NNPG), the support vector regression (SVR), the latent variable with exogenous input (LVX), and the auto regression with exogenous input (ARX) algorithm.