Kawasaki disease (KD) is one of the most common forms of vasculitis in childhood and may cause acquired heart disease in children.^1,2 Most morbidity and mortality associated with KD occur among patients with giant aneurysms.³ The incidence of coronary artery aneurysms decreased from 25% to about 4% if patients with KD were treated with intravenous immunoglobulin (IVIG) within the first 10 days of illness; as a result, the associated mortality was reduced.² Therefore, early awareness of KD is vital for initiating IVIG therapy in time to minimize severe complications and prevent related mortality among children.

Background: The use of focused assessment with sonography in trauma (FAST) enables clinicians to rapidly screen for injury at the bedsides of patients. Pre-hospital FAST improves diagnostic accuracy and streamlines patient care, leading to dispositions to appropriate treatment centers. In this study, we determine the accuracy of artificial intelligence model-assisted free-fluid detection in FAST examinations, and subsequently establish an automated feedback system, which can help inexperienced sonographers improve their interpretation ability and image acquisition skills.Methods: This is a single-center study of patients admitted to the emergency room from January 2020 to March 2021. We collected 324 patient records for the training model, 36 patient records for validation, and another 36 patient records for testing. We balanced positive and negative Morison's pouch free-fluid detection groups in a 1:1 ratio. The deep learning (DL) model Residual Networks 50-Version 2 (ResNet50-V2) was used for training and validation.Results: The accuracy, sensitivity, and specificity of the model performance for ascites prediction were 0.961, 0.976, and 0.947, respectively, in the validation set and 0.967, 0.985, and 0.913, respectively, in the test set. Regarding feedback prediction, the model correctly classified qualified and non-qualified images with an accuracy of 0.941 in both the validation and test sets.Conclusions: The DL algorithm in ResNet50-V2 is able to detect free fluid in Morison's pouch with high accuracy. The automated feedback and instruction system could help inexperienced sonographers improve their interpretation ability and image acquisition skills.

Future wireless networks promise immense increases on data rate and energy efficiency while overcoming the difficulties of charging the wireless stations or devices in the Internet of Things (IoT) with the capability of simultaneous wireless information and power transfer (SWIPT). For such networks, jointly optimizing beamforming, power control, and energy harvesting to enhance the communication performance from the base stations (BSs) (or access points (APs)) to the mobile nodes (MNs) served would be a real challenge. In this work, we formulate the joint optimization as a mixed integer nonlinear programming (MINLP) problem, which can be also realized as a complex multiple resource allocation (MRA) optimization problem subject to different allocation constraints. By means of deep reinforcement learning to estimate future rewards of actions based on the reported information from the users served by the networks, we introduce single-layer MRA algorithms based on deep Q-learning (DQN) and deep deterministic policy gradient (DDPG), respectively, as the basis for the downlink wireless transmissions. Moreover, by incorporating the capability of data-driven DQN technique and the strength of noncooperative game theory model, we propose a two-layer iterative approach to resolve the NP-hard MRA problem, which can further improve the communication performance in terms of data rate, energy harvesting, and power consumption. For the two-layer approach, we also introduce a pricing strategy for BSs or APs to determine their power costs on the basis of social utility maximization to control the transmit power. Finally, with the simulated environment based on realistic wireless networks, our numerical results show that the two-layer MRA algorithm proposed can achieve up to 2.3 times higher value than the single-layer counterparts which represent the data-driven deep reinforcement learning-based algorithms extended to resolve the problem, in terms of the utilities designed to reflect the trade-off among the performance metrics considered.

The aim of 5G wireless networks to provide Mbps and Gbps data rates to end users is expected to be fulfilled by the advanced technologies such as multi-input multi-output (MIMO), carrier aggregation (CA), inter/intra-cell communication, and adaptive modulation and coding techniques, which would be all realized in the Long Term Evolution-Advanced (LTE-A) heterogeneous network constituted by macrocells (MCs) and small cells (SCs) adopting these 5G advanced techniques. Given the potential of significantly increasing the network performance, the resource allocation (RA) problem involved becomes harder than ever especially when MIMO and CA are included in the RA problem involving multiple types of resources to be concurrently determined for the global optimization. Facing this challenge, we develop a framework to jointly optimize energy efficiency (EE), spectrum efficiency (SE), and queue length for downlink transmissions with an overall and comprehensive consideration of dynamically allocating resource blocks (RBs), component carriers (CCs), modulation and coding schemes (MCSs), and deciding user association (UA) with a power control (PC) mechanism on discrete power levels (PLs) in the heterogeneous LTE-based MIMO wireless networks. Specially, for the complex joint RA, UA, and PC problem, we conduct a mixed integer programming model to accommodate the stochastic optimization problem involved with the drift-plus-penalty (DPP) approach for Lyapunov opportunistic optimization. In particular, although it involves a nondeterministic polynomial time (NP) problem, we can still show a reduced problem to be solved easily through linear relaxation when its coefficient matrix is totally unimodular (TUM), and to be solved efficiently as well even when the TUM property is not guaranteed. Based on the reduction, we further develop a distributed or semi-distributed algorithm operated on two levels to approach the optimal results with lower complexity if the UA requirement can be relaxed. Finally, apart from exhibiting its performance on the weighting parameters, the numerical experiments also show our approach to make a good tradeoff among SE, EE, and queue length, and outperform the greedy-based state-of-the-art algorithms.

Background. Out‐of‐hospital cardiac arrest (OHCA) is a major health problem worldwide, and neurologic injury remains the leading cause of morbidity and mortality among survivors of OHCA. The purpose of this study was to investigate whether a machine learning algorithm could detect complex dependencies between clinical variables in emergency departments in OHCA survivors and perform reliable predictions of favorable neurologic outcomes. Methods. This study included adults (≥18 years of age) with a sustained return of spontaneous circulation after successful resuscitation from OHCA between 1 January 2004 and 31 December 2014. We applied three machine learning algorithms, including logistic regression (LR), support vector machine (SVM), and extreme gradient boosting (XGB). The primary outcome was a favorable neurological outcome at hospital discharge, defined as a Glasgow‐Pittsburgh cerebral performance category of 1 to 2. The secondary outcome was a 30‐day survival rate and survival‐to‐discharge rate. Results. The final analysis included 1071 participants from the study period. For neurologic outcome prediction, the area under the receiver operating curve (AUC) was 0.819, 0.771, and 0.956 in LR, SVM, and XGB, respectively. The sensitivity and specificity were 0.875 and 0.751 in LR, 0.687 and 0.793 in SVM, and 0.875 and 0.904 in XGB. The AUC was 0.766 and 0.732 in LR, 0.749 and 0.725 in SVM, and 0.866 and 0.831 in XGB, for survival‐to‐discharge and 30‐day survival, respectively. Conclusions. Prognostic models trained with ML technique showed appropriate calibration and high discrimination for survival and neurologic outcome of OHCA without using prehospital data, with XGB exhibiting the best performance.

In the real world, dynamic changes in air pollutants and meteorological factors coexist simultaneously. Studies identifying the effects of individual pollutants on acute exacerbation (AE) of asthma may overlook the health effects of the overall combination. A comprehensive study examining the influence of air pollution and meteorological factors is required. Asthma AE data from emergency room visits were collected from the Taiwan National Health Insurance Research Database. Complete monitoring data for air pollutants (SO₂; NO₂; O₃; CO; PM_2.5; PM₁₀) and meteorological factors were collected from the Environmental Protection Agency monitoring stations. A bi-directional case-crossover analysis was used to investigate the effects of air pollution and meteorological factors on asthma AE. Among age group divisions, a 1 °C temperature increase was a protective factor for asthma ER visits with OR = 0.981 (95% CI, 0.971–0.991) and 0.985 (95% CI, 0.975–0.994) for pediatric and adult patients, respectively. Children, especially younger females, are more susceptible to asthma AE due to the effects of outdoor air pollution than adults. Meteorological factors are important modulators for asthma AE in both asthmatic children and adults. When studying the effects of air pollution on asthma AE, meteorological factors should be considered.