Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations and discusses potential innovations. We searched five databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from three primary perspectives, including data quality, modeling strategies, and FL frameworks. Out of the 1160 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis. The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

Cross-border violence between Israel and Lebanon, the Saudi ambassador to Yemen meets the Houthis, and Iran's hijab crackdown. Here's your round up of our coverage, written by Abubakr Al-Shamahi, Al Jazeera Digital's Middle East and North Africa editor. First, there were the reports of a single rocket flying across the border from Lebanon into Israel. And then the news that more than 30 had been launched. The majority were intercepted by Israel, but the attack led to the most violent confrontation between Lebanon and Israel since 2006, a sign that the increasing violence in Israel and the occupied Palestinian territories is threatening to spread across the region.

Despite being viewed as a technology of the future, artificial intelligence (AI) has already impacted our daily lives in several ways. Right from the time we wake up, till we go to bed, AI is constantly a part of our lives in forms like voice assistants, online banking, OTT, face IDs among others. Shaping global standards for AI A number of standards covering significant AI issues are now being developed by the ISO/IEC committee for artificial intelligence under the working title ISO/IEC 42001 ISO/IEC DIS 42001 – Information technology -- Artificial intelligence -- Management system. The ISO/IEC 42001 standard, which is being developed by 50 countries, will be essential for improving AI governance and accountability globally. ISO/IEC standardisation brings together the opinions of all relevant stakeholder groups, including SMEs, academia, civil society, and many more.

Warning: Some readers may find some of the scenes described in this article disturbing. Kyiv, Ukraine – Ivan Ukraintsev, a stern-faced insurance broker turned director of a wartime charity providing crucial aid to Ukraine's military forces, is on a mission: to help Ukraine win the drone war. He is a polite but no-nonsense character, and he is here to talk about drones. "If we [Ukraine] had enough drones, we could end this war in two months," he says firmly. Ivan, who heads up the charity Starlife, had recently returned from overseeing a drone delivery to Bakhmut, a city in eastern Ukraine that has become the focal point for months of bloody battles between Ukrainian and Russian forces. Trench warfare, pockmarked and corpse-ridden swathes of no man's land, and constant artillery bombardments have drawn comparisons to battlefield conditions during World War I.

Have you ever wondered why some insects like cockroaches prefer to stay or decrease movement in darkness? Some may tell you it's called photophobia, a habit deeply coded in their genes. A further question would be whether we can correct this habit of cockroaches, that is, moving in the darkness just as they move in bright backgrounds. Scientists from Osaka University may have answered this question by converting a cockroach into a cyborg. They published their research in the journal Cyborg and Bionic Systems.

The performance of text summarization has been greatly boosted by pre-trained language models. A main concern of existing methods is that most generated summaries are not factually inconsistent with their source documents. To alleviate the problem, many efforts have focused on developing effective factuality evaluation metrics based on natural language inference, question answering, and syntactic dependency et al. However, these approaches are limited by either their high computational complexity or the uncertainty introduced by multi-component pipelines, resulting in only partial agreement with human judgement. Most recently, large language models(LLMs) have shown excellent performance in not only text generation but also language comprehension. In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating. Experimental results indicate that ChatGPT generally outperforms previous evaluation metrics across the three tasks, indicating its great potential for factual inconsistency evaluation. However, a closer inspection of ChatGPT's output reveals certain limitations including its preference for more lexically similar candidates, false reasoning, and inadequate understanding of instructions.

While it is well known that population differences from genetics, sex, race, and environmental factors contribute to disease, AI studies in medicine have largely focused on locoregional patient cohorts with less diverse data sources. Such limitation stems from barriers to large-scale data share and ethical concerns over data privacy. Federated learning (FL) is one potential pathway for AI development that enables learning across hospitals without data share. In this study, we show the results of various FL strategies on one of the largest and most diverse COVID-19 chest CT datasets: 21 participating hospitals across five continents that comprise >10,000 patients with >1 million images. We also propose an FL strategy that leverages synthetically generated data to overcome class and size imbalances. We also describe the sources of data heterogeneity in the context of FL, and show how even among the correctly labeled populations, disparities can arise due to these biases.

Multi-objective portfolio optimisation is a critical problem researched across various fields of study as it achieves the objective of maximising the expected return while minimising the risk of a given portfolio at the same time. However, many studies fail to include realistic constraints in the model, which limits practical trading strategies. This study introduces realistic constraints, such as transaction and holding costs, into an optimisation model. Due to the non-convex nature of this problem, metaheuristic algorithms, such as NSGA-II, R-NSGA-II, NSGA-III and U-NSGA-III, will play a vital role in solving the problem. Furthermore, a learnheuristic approach is taken as surrogate models enhance the metaheuristics employed. These algorithms are then compared to the baseline metaheuristic algorithms, which solve a constrained, multi-objective optimisation problem without using learnheuristics. The results of this study show that, despite taking significantly longer to run to completion, the learnheuristic algorithms outperform the baseline algorithms in terms of hypervolume and rate of convergence. Furthermore, the backtesting results indicate that utilising learnheuristics to generate weights for asset allocation leads to a lower risk percentage, higher expected return and higher Sharpe ratio than backtesting without using learnheuristics. This leads us to conclude that using learnheuristics to solve a constrained, multi-objective portfolio optimisation problem produces superior and preferable results than solving the problem without using learnheuristics.

The choice of the most effective treatment may eventually be influenced by breast cancer survival prediction. To predict the chances of a patient surviving, a variety of techniques were employed, such as statistical, machine learning, and deep learning models. In the current study, 1904 patient records from the METABRIC dataset were utilized to predict a 5-year breast cancer survival using a machine learning approach. In this study, we compare the outcomes of seven classification models to evaluate how well they perform using the following metrics: recall, AUC, confusion matrix, accuracy, precision, false positive rate, and true positive rate. The findings demonstrate that the classifiers for Logistic Regression (LR), Support Vector Machines (SVM), Decision Tree (DT), Random Forest (RD), Extremely Randomized Trees (ET), K-Nearest Neighbor (KNN), and Adaptive Boosting (AdaBoost) can accurately predict the survival rate of the tested samples, which is 75,4\%, 74,7\%, 71,5\%, 75,5\%, 70,3\%, and 78 percent.

Bayesian neural networks (BNNs) have received an increased interest in the last years. In BNNs, a complete posterior distribution of the unknown weight and bias parameters of the network is produced during the training stage. This probabilistic estimation offers several advantages with respect to point-wise estimates, in particular, the ability to provide uncertainty quantification when predicting new data. This feature inherent to the Bayesian paradigm, is useful in countless machine learning applications. It is particularly appealing in areas where decision-making has a crucial impact, such as medical healthcare or autonomous driving. The main challenge of BNNs is the computational cost of the training procedure since Bayesian techniques often face a severe curse of dimensionality. Adaptive importance sampling (AIS) is one of the most prominent Monte Carlo methodologies benefiting from sounded convergence guarantees and ease for adaptation. This work aims to show that AIS constitutes a successful approach for designing BNNs. More precisely, we propose a novel algorithm PMCnet that includes an efficient adaptation mechanism, exploiting geometric information on the complex (often multimodal) posterior distribution. Numerical results illustrate the excellent performance and the improved exploration capabilities of the proposed method for both shallow and deep neural networks.