GLYFE: review and benchmark of personalized glucose predictive models in type 1 diabetes.

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.

Adversarial multi-source transfer learning in healthcare: Application to glucose prediction for diabetic people.

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.

Systematic variation of the stellar initial mass function in early-type galaxies.

Much of our knowledge of galaxies comes from analysing the radiation emitted by their stars, which depends on the present number of each type of star in the galaxy. The present number depends on the stellar initial mass function (IMF), which describes the distribution of stellar masses when the population formed, and knowledge of it is critical to almost every aspect of galaxy evolution. More than 50 years after the first IMF determination, no consensus has emerged on whether it is universal among different types of galaxies. Previous studies indicated that the IMF and the dark matter fraction in galaxy centres cannot both be universal, but they could not convincingly discriminate between the two possibilities. Only recently were indications found that massive elliptical galaxies may not have the same IMF as the Milky Way. Here we report a study of the two-dimensional stellar kinematics for the large representative ATLAS(3D) sample of nearby early-type galaxies spanning two orders of magnitude in stellar mass, using detailed dynamical models. We find a strong systematic variation in IMF in early-type galaxies as a function of their stellar mass-to-light ratios, producing differences of a factor of up to three in galactic stellar mass. This implies that a galaxy's IMF depends intimately on the galaxy's formation history.