Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management.

Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.

Deep-Learning Based Automated Segmentation and Quantitative Volumetric Analysis of Orbital Muscle and Fat for Diagnosis of Thyroid Eye Disease.

Purpose: Thyroid eye disease (TED) is characterized by proliferation of orbital tissues and complicated by compressive optic neuropathy (CON). This study aims to utilize a deep-learning (DL)-based automated segmentation model to segment orbital muscle and fat volumes on computed tomography (CT) images and provide quantitative volumetric data and a machine learning (ML)-based classifier to distinguish between TED and TED with CON. Methods: Subjects with TED who underwent clinical evaluation and orbital CT imaging were included. Patients with clinical features of CON were classified as having severe TED, and those without were classified as having mild TED. Normal subjects were used for controls. A U-Net DL-model was used for automatic segmentation of orbital muscle and fat volumes from orbital CTs, and ensemble of Random Forest Classifiers were used for volumetric analysis of muscle and fat. Results: Two hundred eighty-one subjects were included in this study. Automatic segmentation of orbital tissues was performed. Dice coefficient was recorded to be 0.902 and 0.921 for muscle and fat volumes, respectively. Muscle volumes among normal, mild, and severe TED were found to be statistically different. A classification model utilizing volume data and limited patient data had an accuracy of 0.838 and an area under the curve (AUC) of 0.929 in predicting normal, mild TED, and severe TED. Conclusions: DL-based automated segmentation of orbital images for patients with TED was found to be accurate and efficient. An ML-based classification model using volumetrics and metadata led to high diagnostic accuracy in distinguishing TED and TED with CON. By enabling rapid and precise volumetric assessment, this may be a useful tool in future clinical studies.

A Probabilistic Approach to Blood Glucose Prediction in Type 1 Diabetes Under Meal Uncertainties.

Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.