Coronary artery disease (CAD) remains the leading cause of mortality among cardiovascular diseases, responsible for 16% of the world’s total deaths. According to a statistical report published in 2020, the global prevalence of CAD was estimated at 1655 per 100,000 people and is predicted to exceed 1845 by 2030. Annually, in the United States, CAD accounts for approximately 610,000 deaths and costs more than 200 billion dollars for healthcare services. Most patients with CAD need to be treated over long periods with a combination of drugs. Therefore, the inappropriate use of drugs, or drug-related problems (DRPs), can lead to many consequences that affect these patients’ health, including decreased quality of life, increased hospitalization rates, prolonged hospital stays, increased overall health care costs, and even increased risk of morbidity and mortality. DRPs are common in CAD patients, with a prevalence of over 60%. DRPs must therefore be noticed and recognized by healthcare professionals. This chapter describes common types and determinants of DRPs in CAD patients and recommends interventions to limit their prevalence.

No abstract

This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the human foreground. We thus develop crosslink layers from the temporal network (trained on flows) to the spatial network (trained on RGB frames). These crosslink layers guide the spatial-stream to pay more attention to the human foreground areas and be less affected by background clutter. We obtain promising performances with our approach on the UCF101, HMDB51 and Hollywood2 datasets.1 arXiv:1708.09268v1 [cs.CV] 30 Aug 2017Before the deep learning era, there have been works incorporating saliency into action recognition from videos. Several saliency measures have been proposed for actions in [25,17] and they show improvements in the recognition accuracy when focusing attention on the foreground.

We present a novel statistical moments-based method for optical signal-to-noise ratio (OSNR) monitoring in polarization-multiplexed (pol-mux) coherent optical systems. This technique only requires the knowledge of the envelope of the equalized signal before phase correction, which can be achieved by using any two arbitrary statistical moments, and it is suitable for both constant and non-constant modulus modulation formats. The proposed estimation method is experimentally demonstrated for 10-Gbaud pol-mux coherent systems using QPSK and 16-QAM. Additionally, numerical simulations are carried out to demonstrate 20-Gbaud systems using 16-QAM and 64-QAM. The results show that the OSNR can be estimated accurately over a wide range of values for QPSK, 16-QAM or 64-QAM systems up to 1920-km long and with up to 50-ps all-order polarization mode dispersion. By setting a proper reference value for calibration, the proposed algorithm also shows good tolerance when the received signal is not well compensated.