Glucose variations have a bidirectional relationship with the sleep/wake and circadian systems in type 1 diabetes (T1D); however, the mechanisms remain unclear. The aim of this study was to describe the coupling between glucose and unstructured physical activity over 168 h in young adults with T1D. We hypothesized that there would be differences in sleep and wake characteristics and circadian variations. Glucose was measured with a continuous glucose monitoring device every 5 min and activity with a non-dominant wrist-worn actigraph in 30-s epochs over 6–14 days. There was substantial glucose and unstructured physical activity coupling during sleep and wake, along with circadian variation based on the wavelet coherence analysis. The extent to which glucose fluctuations result in disrupted sleep over longer than one week should be examined considering the harmful effects on achieving glycemic targets. Further studies are needed to delineate the respective roles of glucose production and utilization and the potential for improved meal and insulin timing to optimize glucose and sleep in this population reliant on exogenous insulin.

No abstract

No abstract

No abstract

No abstract

No abstract

No abstract

Machine learning models are increasingly used in high-stakes decision-making systems. In such applications, a major concern is that these models sometimes discriminate against certain demographic groups such as individuals with certain race, gender, or age. Another major concern in these applications is the violation of the privacy of users. While fair learning algorithms have been developed to mitigate discrimination issues, these algorithms can still leak sensitive information, such as individuals' health or financial records. Utilizing the notion of differential privacy (DP), prior works aimed at developing learning algorithms that are both private and fair. However, existing algorithms for DP fair learning are either not guaranteed to converge or require full batch of data in each iteration of the algorithm to converge. In this paper, we provide the first stochastic differentially private algorithm for fair learning that is guaranteed to converge. Here, the term "stochastic" refers to the fact that our proposed algorithm converges even when minibatches of data are used at each iteration (i.e. stochastic optimization). Our framework is flexible enough to permit different fairness notions, including demographic parity and equalized odds. In addition, our algorithm can be applied to non-binary classification tasks with multiple (non-binary) sensitive attributes. As a byproduct of our convergence analysis, we provide the first utility guarantee for a DP algorithm for solving nonconvex-strongly concave min-max problems. Our numerical experiments show that the proposed algorithm consistently offers significant performance gains over the state-of-the-art baselines, and can be applied to larger scale problems with non-binary target/sensitive attributes.