Search

Due to the sensitive nature of diabetes-related data, preventing them from being easily shared between studies, and the wide discrepancies in their data processing pipeline, progress in the field of glucose prediction is hard to assess. To address this issue, we introduce GLYFE (GLYcemia Forecasting Evaluation), a benchmark of machine learning-based glucose predictive models. We present the accuracy and clinical acceptability of nine different models coming from the literature, from standard autoregressive to more complex neural network-based models. These results are obtained on two different datasets, namely UVA/Padova Type 1 Diabetes Metabolic Simulator (T1DMS) and Ohio Type-1 Diabetes Mellitus (OhioT1DM), featuring artificial and real type 1 diabetic patients respectively. By providing extensive details about the data flow as well as by providing the whole source code of the benchmarking process, we ensure the reproducibility of the results and the usability of the benchmark by the community. Those results serve as a basis of comparison for future studies. In a field where data are hard to obtain, and where the comparison of results from different studies is often irrelevant, GLYFE gives the opportunity of gathering researchers around a standardized common environment.

Despite recent advances of deep neural networks in hand vein identification, the existing solutions assume the availability of a large and rich set of training image samples. These solutions, therefore, still lack the capability to extract robust and discriminative hand-vein features from a single training image sample. To overcome this problem, we propose a single-sample-per-person (SSPP) palm-vein identification approach, where only a single sample per class is enrolled in the gallery set for training. Our approach, named MSMDGAN + CNN, consists of a multi-scale and multi-direction generative adversarial network (MSMDGAN) for data augmentation and a convolutional neural network (CNN) for palm-vein identification. First, a novel data augmentation approach, MSMDGAN, is developed to learn the internal distribution of patches in a single image. The proposed MSMDGAN consists of multiple fully convolutional GANs, each of which is responsible for learning the patch distribution within an image at a different scale and at a different direction. Second, given the resulting augmented data by MSMDGAN, we design a CNN for single sample palm-vein recognition. The experimental results on two public hand-vein databases demonstrate that MSMDGAN is able to generate realistic and diverse samples, which, in turn, improves the stability of the CNN. In terms of accuracy, MSMDGAN + CNN outperforms other representative approaches and achieves state-of-the-art recognition results.

An optoelectronic Reservoir Computer is proposed and implemented numerically and on physical hardware for early-stage Alzheimer’s disease detection for the first time. The approach yields classification accuracy of 85% surpassing state-of-the-art performances.

Background and objectives: Deep learning has yet to revolutionize general practices in healthcare, despite promising results for some specific tasks. This is partly due to data being in insufficient quantities hurting the training of the models. To address this issue, data from multiple health actors or patients could be combined by capitalizing on their heterogeneity through the use of transfer learning. Methods: To improve the quality of the transfer between multiple sources of data, we propose a multi-source adversarial transfer learning framework that enables the learning of a feature representation that is similar across the sources, and thus more general and more easily transferable. We apply this idea to glucose forecasting for diabetic people using a fully convolutional neural network. The evaluation is done by exploring various transfer scenarios with three datasets characterized by their high inter and intra variability. Results: While transferring knowledge is beneficial in general, we show that the statistical and clinical accuracies can be further improved by using of the adversarial training methodology, surpassing the current state-of-the-art results. In particular, it shines when using data from different datasets, or when there is too little data in an intra-dataset situation. To understand the behavior of the models, we analyze the learnt feature representations and propose a new metric in this regard. Contrary to a standard transfer, the adversarial transfer does not discriminate the patients and datasets, helping the learning of a more general feature representation. Conclusion: The adversarial training framework improves the learning of a general feature representation in a multi-source environment, enhancing the knowledge transfer to an unseen target. The proposed method can help improve the efficiency of data shared by different health actors in the training of deep models.

Research in diabetes, especially when it comes to building data-driven models to forecast future glucose values, is hindered by the sensitive nature of the data. Because researchers do not share the same data between studies, progress is hard to assess. This paper aims at comparing the most promising algorithms in the field, namely Feedforward Neural Networks (FFNN), Long Short-Term Memory (LSTM) Recurrent Neural Networks, Extreme Learning Machines (ELM), Support Vector Regression (SVR) and Gaussian Processes (GP). They are personalized and trained on a population of 10 virtual children from the Type 1 Diabetes Metabolic Simulator software to predict future glucose values at a prediction horizon of 30 minutes. The performances of the models are evaluated using the Root Mean Squared Error (RMSE) and the Continuous Glucose-Error Grid Analysis (CG-EGA). While most of the models end up having low RMSE, the GP model with a Dot-Product kernel (GP-DP), a novel usage in the context of glucose prediction, has the lowest. Despite having good RMSE values, we show that the models do not necessarily exhibit a good clinical acceptability, measured by the CG-EGA. Only the LSTM, SVR and GP-DP models have overall acceptable results, each of them performing best in one of the glycemia regions.

International audience; Retrieving and indexing historical Arabic documents remain a very significant challenge. The purpose of this paper is to compare the feature representation spaces for word spotting in historical Arabic documents. Our goal is to create embedding spaces using the characteristics of different machine learning methods: i) linear such as principal component analysis and linear discriminant analysis, and ii) non-linear including convolutional neural networks for triplets and Siamese. Subsequently, each word image is represented by a dense vector. Thus, to match feature representations, a Euclidean distance is used. An evaluation of various representation space models is presented. The embedding word models are evaluated on the VML-HD dataset, and the experiments show the effectiveness of non-linear methods compared to linear ones.

The adoption of deep learning in healthcare is hindered by their “black box” nature. In this paper, we explore the RETAIN architecture for the task of glucose forecasting for diabetic people. By using a two-level attention mechanism, the recurrent-neural-network-based RETAIN model is interpretable. We evaluate the RETAIN model on the type-2 IDIAB and the type-1 OhioT1DM datasets by comparing its statistical and clinical performances against two deep models and three models based on decision trees. We show that the RETAIN model offers a very good compromise between accuracy and interpretability, being almost as accurate as the LSTM and FCN models while remaining interpretable. We show the usefulness of its interpretable nature by analyzing the contribution of each variable to the final prediction. It revealed that signal values older than 1[Formula: see text]h are not used by the RETAIN model for 30[Formula: see text]min ahead of time prediction of glucose. Also, we show how the RETAIN model changes its behavior upon the arrival of an event such as carbohydrate intakes or insulin infusions. In particular, it showed that the patient’s state before the event is particularly important for the prediction. Overall the RETAIN model, thanks to its interpretability, seems to be a very promising model for regression or classification tasks in healthcare.

Palm-vein recognition has received increasing researchers’ attention in recent years. However, palm-vein recognition faces various challenges in practical applications, one of which is the lack of robustness against image quality degradation, resulting in reduction of the verification accuracy. To address this problem, this paper proposes an end-to-end convolutional neural network to automatically extract vein network features, thus without resorting to any hand-crafted features. Firstly, we label the palm-vein pixels based on several handcraft-based segmentation methods and reconstruct a training set accordingly. Secondly, an end-to-end vein segmentation model is proposed based on a generative adversarial network. After training, this model outputs a map where each value is the probability that the corresponding pixel belongs to a vein pattern. The resulting map is then subject to binarization by thresholding and stored in a binary image, used subsequently for verification matching. The experimental results on the public CASIA palm-vein dataset demonstrate the effectiveness of our proposed method.

Standard objective functions used during the training of neural-network-based predictive models do not consider clinical criteria, leading to models that are not necessarily clinically acceptable. In this study, we look at this problem from the perspective of the forecasting of future glucose values for diabetic people. In this study, we propose the coherent mean squared glycemic error (gcMSE) loss function. It penalizes the model during its training not only of the prediction errors, but also on the predicted variation errors which is important in glucose prediction. Moreover, it makes possible to adjust the weighting of the different areas in the error space to better focus on dangerous regions. In order to use the loss function in practice, we propose an algorithm that progressively improves the clinical acceptability of the model, so that we can achieve the best tradeoff possible between accuracy and given clinical criteria. We evaluate the approaches using two diabetes datasets, one having type-1 patients and the other type-2 patients. The results show that using the gcMSE loss function, instead of a standard MSE loss function, improves the clinical acceptability of the models. In particular, the improvements are significant in the hypoglycemia region. We also show that this increased clinical acceptability comes at the cost of a decrease in the average accuracy of the model. Finally, we show that this tradeoff between accuracy and clinical acceptability can be successfully addressed with the proposed algorithm. For given clinical criteria, the algorithm can find the optimal solution that maximizes the accuracy while at the same meeting the criteria.

Progress in the biomedical field through the use of deep learning is hindered by the lack of interpretability of the models. In this paper, we study the RETAIN architecture for the forecasting of future glucose values for diabetic people. Thanks to its two-level attention mechanism, the RETAIN model is interpretable while remaining as efficient as standard neural networks.