Domain generalization for enhanced predictions of hospital readmission on unseen domains among patients with diabetes.

A prediction model to assess the risk of hospital readmission can be valuable to identify patients who may benefit from extra care. Developing hospital-specific readmission risk prediction models using local data is not feasible for many institutions. Models developed on data from one hospital may not generalize well to another hospital.

Deep Learning vs Traditional Models for Predicting Hospital Readmission among Patients with Diabetes.

A hospital readmission risk prediction tool for patients with diabetes based on electronic health record (EHR) data is needed. The optimal modeling approach, however, is unclear. In 2,836,569 encounters of 36,641 diabetes patients, deep learning (DL) long short-term memory (LSTM) models predicting unplanned, all-cause, 30-day readmission were developed and compared to several traditional models.

Plasticity of body axis polarity in Hydra regeneration under constraints.

One of the major events in animal morphogenesis is the emergence of a polar body axis. Here, we combine classic grafting techniques with live imaging to explore the plasticity of polarity determination during whole body regeneration in Hydra. Composite tissues are made by fusing two rings, excised from separate animals, in different configurations that vary in the polarity and original positions of the rings along the body axes of the parent animals.

Simple Majority Consensus in Networks with Unreliable Communication.

In this work, we analyze the performance of a simple majority-rule protocol solving a fundamental coordination problem in distributed systems--in the presence of probabilistic message loss. Using probabilistic analysis for a large-scale, fully-connected, network of 2n agents, we prove that the Simple Majority Protocol (SMP) reaches consensus in only three communication rounds, with probability approaching 1 as grows to infinity. Moreover, if the difference between the numbers of agents that hold different opinions grows at a rate of n, then the SMP with only two communication rounds attains consensus on the majority opinion of the network, and if this difference grows faster than n, then the SMP reaches consensus on the majority opinion of the network in a single round, with probability converging to 1 as exponentially fast as n→∞.

Fabrication and Characterization of Double- and Single-Clamped CuO Nanowire Based Nanoelectromechanical Switches.

Electrostatically actuated nanoelectromechanical (NEM) switches hold promise for operation with sharply defined ON/OFF states, high ON/OFF current ratio, low OFF state power consumption, and a compact design. The present challenge for the development of nanoelectromechanical system (NEMS) technology is fabrication of single nanowire based NEM switches. In this work, we demonstrate the first application of CuO nanowires as NEM switch active elements.