Recurrent neural networks that learn multi-step visual routines with reinforcement learning.

Many cognitive problems can be decomposed into series of subproblems that are solved sequentially by the brain. When subproblems are solved, relevant intermediate results need to be stored by neurons and propagated to the next subproblem, until the overarching goal has been completed. We will here consider visual tasks, which can be decomposed into sequences of elemental visual operations.

Is HealthPathways viewed as a useful and trustworthy source of information by health professionals?

Objective HealthPathways is a web-based platform designed for use during a consultation to offer health professionals locally agreed information to support clinical and referral decision making. This study aimed to investigate whether access to specific HealthPathways pages in the North Coast New South Wales (NSW) region increased during specific critical events. High pageviews is used as a proxy for platform usefulness, and/or trust as a source of up-to-date information.

Burden of Clostridium (Clostridioides) difficile infection during inpatient stays in the USA between 2012 and 2016.

Background: The healthcare burden of Clostridium (Clostridioides) difficile infection (CDI) is high but not fully characterized.

Aim: To assess hospitalization costs, length of hospital stay (LOS) and in-hospital mortality attributable to CDI in the USA by analysing nationwide hospital discharge records over the 2012-2016 period.

Methods: A retrospective, observational study based on the Truven Health MarketScan Hospital Drug Database was conducted, in which 46,097 inpatient stays with a diagnosis of CDI were analysed.

Model driven optimization of antiangiogenics + cytotoxics combination: application to breast cancer mice treated with bevacizumab + paclitaxel doublet leads to reduced tumor growth and fewer metastasis.

Bevacizumab is the first-in-class antiangiogenic drug and is almost always administrated in combination with cytotoxics. Reports have shown that bevacizumab could induce a transient phase of vascular normalization, thus ensuring a better drug delivery when cytotoxics administration is adjuvant. However, determining the best sequence remains challenging.

In Vivo Bioluminescence Tomography for Monitoring Breast Tumor Growth and Metastatic Spreading: Comparative Study and Mathematical Modeling.

This study aimed at evaluating the reliability and precision of Diffuse Luminescent Imaging Tomography (DLIT) for monitoring primary tumor and metastatic spreading in breast cancer mice, and to develop a biomathematical model to describe the collected data. Using orthotopic mammary fat pad model of breast cancer (MDAMB231-Luc) in mice, we monitored tumor and metastatic spreading by three-dimensional (3D) bioluminescence and cross-validated it with standard bioluminescence imaging, caliper measurement and necropsy examination. DLIT imaging proved to be reproducible and reliable throughout time.