Assessing deep learning artificial intelligence support for detecting elbow fractures in the pediatric emergency department.

Multi-Parameter Comprehensive Diagnosis Technology for Electrical Faults based on Artificial Intelligence Algorithms

Musculoskeletal disorders (MSDs) are among the most prevalent occupational health issues affecting industrial workforces, often leading to decreased productivity, increased absenteeism, and long-term disability. In recent years, the integration of machine learning (ML) and artificial intelligence (AI) has become a transformative approach to proactively prevent and manage MSDs in industrial settings. By leveraging real-time data from wearable sensors, cameras, and biomechanical monitoring systems, AI-driven solutions can identify hazardous postures, repetitive strain movements, and fatigue indicators before injuries occur. ML algorithms can analyse vast datasets to detect early warning signs, predict injury risks, and recommend ergonomic interventions tailored to individual workers. AI technologies also enhance workplace training through simulation-based learning and virtual reality environments, enabling workers to adopt safe practices more effectively. In addition, AI-powered exoskeletons and robotics are being developed to support manual labour, reducing physical strain on the musculoskeletal system. Predictive analytics models are increasingly being used by occupational health and safety professionals to design safer workspaces and optimise workload distribution. Furthermore, the integration of natural language processing (NLP) with incident reporting systems helps analyse unstructured data to uncover trends and causes of MSD-related issues, facilitating quicker response and prevention strategies. Despite the promising potential, challenges remain, including data privacy concerns, the need for large, high-quality datasets, and resistance to technological adoption in traditional industries. ML has become a powerful tool in predicting, preventing, and managing these disorders by analysing large datasets and providing actionable insights. This paper explores the ML and AI algorithms to monitor worker health in real-time, detect early signs of MSDs, and suggest corrective measures. AI and ML have demonstrated immense potential in revolutionising health care by providing advanced tools for predicting and managing health issues. AI and ML algorithms can analyse large datasets, such as medical records, genetic information, and patient demographics, to identify patterns and correlations that may not be immediately obvious to healthcare professionals. These technologies enable early detection of diseases, personalised treatment plans, and improved diagnosis accuracy. The paper discusses the challenges and future potential of AI/ML in transforming industrial health and safety management, thereby improving worker productivity and reducing health care costs.

Artificial intelligence revolutionize food detection? Vision, olfaction and taste integrated with machine learning/deep learning in food detection.

The need for better quality studies: A systematic scoping review of current utility of artificial intelligence in orthopaedics and research gaps in the knee joint.

Rabbit monoclonal antibodies: Synergistic innovation and breakthrough based on B-cell development mechanism and single B-cell technology.

Artificial intelligence-assisted selective modified natural frozen embryo transfer.

Image encryption using artificial intelligence algorithms for secure communication

Artificial intelligence classification of pediatric middle ear effusion using consumer-grade otoscopes.

AI-driven strategies for enhancing Mpox surveillance and response in Africa.

Clinical Grade Interpretable Artificial Intelligence Tool for Automated Detection of Lymph Node Metastasis in Prostate Cancer.

Nuclear medicine differs from other specialties of radiology by employing unsealed radionuclides. Moreover, it may heighten the risks of incidents for nuclear medicine healthcare professionals (NMHP). On the other hand, artificial intelligence (AI) methods improve their ability to assess, understand, and prevent these incidents. This systematic review examines the critical incidents affecting NMHP and reviews the potential of AI in improving, controlling, and evaluating the occupational exposure, to predict and prevent these accidents. A systematic search of PubMed, Science Direct, Scopus, and the NLM was conducted using the keywords and Mesh terms, with no language restrictions. A protocol based on PRISMA guidelines was developed. To streamline both the search strategy and the study selection process, EndNote X7.8 was employed. 49 studies were reviewed. The primary causes of incidents in nuclear medicine are due to inadequate handling of radionuclides, malfunctioning equipment, and the loss or theft of radioactive sources. Furthermore, our research highlights the potential of AI algorithms to facilitate better identification of radioactive sources, radiation dose optimization, and strengthen thedecision-making processes during potentially hazardous incidents. Our systematic study intervenes to improve the role of AI in the surveillance and improvement of the occupational exposure situation for NMHP. In addition, AI tools can contribute to better decision-making in real time during nuclear medicine emergency situations. Such advancements underscore the crucial need for ongoing development and implementation of AI technologies in nuclear medicine to enhance radiation protection for NMHP.

Artificial intelligence for laser-assisted oral surgery: A narrative review of current trends and future perspectives.

OBJECTIVE: To investigate the degree of agreement between artificial intelligence (AI)-based strabismus measurements obtained from images of nine diagnostic gaze positions and the actual diagnosis and amount of deviation recorded during clinical examination. MATERIALS and METHODS: The study included twenty cases diagnosed with horizontal strabismus. For each patient, nine gaze position photographs taken using the 9gaze application (See Vision LLC, Virginia, USA) under fixation on a near target were used, and horizontal and vertical deviation values were recorded during clinical examination. Data on the amounts of horizontal and vertical deviations, incomitance status, pattern presence, and type of strabismus were reviewed from clinical records. The same photographs were uploaded to ChatGPT-5.0-Plus, and the diagnosis, incomitance, pattern, and deviation amounts generated by the AI algorithm were documented. RESULTS: The average age of the 20 cases included in the study was 21.0±20.9 (1–65) years; 10 (50%) were female and 10 (50%) were male. According to the actual diagnosis, 11 (55%) had esotropia and 9 (45%) had exotropia. The number of cases correctly classified in the clinical diagnosis classification of the YZ was 19/20 (95%), showing excellent agreement with Cohen's kappa = 0.90. Sensitivity for esotropia was 90.9%, specificity was 100%, and overall accuracy was 95%. Clinical and AI analyses showed 75% agreement for incomitance (Kappa=0.38). The AI algorithm was found to be inadequate in detecting pattern shift (%80 agreement, Kappa=-0.05). Strong correlations were observed in horizontal and vertical shift analyses (r=0.87, p<0.001 and r=0.77, p<0.001). No significant relationship was found between age and gender and the absolute error magnitude (p>0.05 for all). CONCLUSION: AI-based analysis of nine diagnostic gaze position photographs shows a high level of agreement with clinical measurements in estimating strabismus type and deviation magnitude. However, agreement is much lower for more subtle diagnostic features such as incommitance and A/V-pattern. The findings suggest that properly trained AI systems can serve as a useful diagnostic support tool in strabismus practice but cannot replace clinical examination, especially in cases of incomitant and patterned strabismus.

As consumer-grade GPUs have rapidly evolved, efforts have emerged to deploy these computational models for training and inference, typically handled by data center hardware. The paper explores optimization of two next-generation graphics computing units, the NVIDIA GeForce RTX 5090 and the AMD Radeon RX 9070, to optimize the new generation of ML and AI applications. We examine the internal compute pipelines, tensor/matrix acceleration capabilities, memory hierarchies, and software ecosystems (CUDA/cuDNN/TensorRT versus ROCm/MIOpen/HIP) that influence ML performance in a two-pronged architectural and empirical study. The convolutional networks, transformer models, diffusion architecture, and graph neural networks share a standard benchmarking model: training, inference latency, power consumption, precision scaling (FP32-INT8), and bottlenecks. The results of the experiment have demonstrated that the performance profiles of the RTX 5090 and the RX 9070 are different, i.e., the acceleration performance of mixed precision and kernel fusion is higher in the RTX 5090 as compared to the throughput performance of the RX 9070 in the BF16/INT8 workloads with the high memory-bandwidth utilization. Strategies for each platform. Platform-specific optimization strategies, such as kernel tuning, compiler optimization, memory prefetching, gradient checkpointing, and scaling to multiple GPUs, are developed and evaluated. Further, two case studies of real-world performance tuning of transformer fine-tuning and diffusion model inference are also presented. The findings highlight that hardware alone does not guarantee the best ML performance; effective optimization can deliver performance gains that are even more significant than raw compute alone. The paper will provide a step-by-step roadmap for practitioners, researchers, and engineers who may want to optimize the application of RTX 5090 and RX 9070 in artificial intelligence algorithms, as well as a future perspective on the standard models of unified programming on GPUs and emergent precision formats.

There are various ideas about the role that artificial intelligence (AI), which has become an integral part of individual and social life, will play in the future of humanity. Some see it as a tool offering unique opportunities for civilization-building, while others perceive it as a threat that could bring about its end. While physical and technical aspects are prominent in these discussions of AI’s capabilities, they also touch on topics such as art, aesthetic pleasure, religion, faith, metaphysics, and ethics. In its most concrete form, AI is the digital description of the electrical flow active on hardware designed after human intelligence and thought. The computer codes written in programming languages that represent the software side of AI, and all the algorithms that determine its operating principles, are models developed through the stimulation of human thought processes. In short, AI is a tool that mimics the biological functioning of the human brain in hardware while following the rational thinking patterns of the human mind in software. For pure reasoning that transcends subject and object, the crucial element is completing thought processes in accordance with the principles of logic. In this respect, it is rationally the same whether the correct act of thinking on concrete or abstract values is performed by human intelligence or artificial intelligence. Here, the possibility of determining the logical meaning of the idea of God by artificial intelligence algorithms is discussed. To define the boundaries of the topic, discussions involving marginal claims such as AI addressing religious proposals in the context of its relationship with consciousness or the soul, or its assuming the role of modern religion and God, were deliberately avoided. The study primarily analyzes the methods used by AI in understanding, explaining, and developing attitudes toward the theory of God, within the context of fundamental concepts such as language and logic. In the positivist and rationalist world of the future, it is of great importance to take advantage of the opportunities offered by artificial intelligence in order to preserve both the existence and social reputation of religious and moral values. Indeed, an AI algorithm with a vision for the future should contribute to a healthy conception of God by generating new values rather than being trapped between technology and theology. The purpose of this study is to identify the potential uses of artificial intelligence (AI), an effective tool in daily life and scientific research, and an part of our life due to its speed and accurate computational power, in understanding theological values such as faith, religion, and God. The research uses an inductive analysis of the findings obtained through a literature review to reach a conclusion about the possibilities of AI in thinking about God.

In this study, the prediction performance of different artificial intelligence algorithms was examined using quality of life data from 2016 to 2025. The analysis compared gradient-boosted tree-based XGBoost with LSTM, which has the capacity to model time series and sequential dependencies. In addition, SHAP analysis was applied to ensure the model's explainability and to identify the key factors affecting quality of life. The findings show that both models successfully capture quality of life patterns, with the LSTM model achieving higher out-of-sample accuracy than XGBoost (higher R² and lower MAE, RMSE, and MAPE). SHAP analysis revealed that Purchasing Power and Pollution are the factors with the strongest impact on quality of life. The decisive effect of Purchasing Power indicates that macroeconomic conditions such as real income level, price stability, and Purchasing Power Parity -adjusted welfare indicators directly reflect quality of life. Other factors, such as cost of living, housing price/income ratio, security, healthcare services, climate, and commute time, were found to have varying degrees of importance across countries. These findings emphasize the priority of designing macroeconomic frameworks targeting income/wage policies and price stability alongside policies aimed at improving environmental conditions. The results obtained indicate that policy makers should focus on the efficient allocation of resources. The results obtained provide policymakers with an evidence-based roadmap for the efficient allocation of resources and demonstrate that more detailed analyses can be conducted using different explainable artificial intelligence methods for future research. Additionally, to test the robustness of the model, different training/testing splits, alternative error metrics, and hyperparameter sensitivity analyses were performed; the direction and magnitude of the main findings were found to be consistent across these scenarios. Finally, SHAP-based findings provide a starting framework for policy simulations, enabling the quantitative prediction of potential welfare gains from targeted improvements in specific sub-indices.

Abstract Based on the dual-resonance composite right-/left-handed (CRLH) resonator, a design of dual-band microwave metamaterial filter aided by artificial intelligence (AI) algorithms optimizer is demonstrated in this paper. Specified by dual-mode electromagnetic (EM) resonant behavior, the emphatically illustrated metamaterial resonator is distinguished with characteristics of manipulated modes and couplings. Applied to the design of third-order topology dual-band filter, the circuit architecture consisting of multiple parameters requires efficient and accurate optimization for desired filtering performance. Then, an AI methodology integrating the co-simulator of HFSS-MATLAB with grey wolf algorithm (GWA) optimizer is employed to obtain the pre-set dua-band frequency response. With final filter layout exported, the prototype sample was fabricated. The implemented microwave properties measurement validates a good agreement of device performance between theoretical analysis and practical experiment that reveals the feasibility of described physical concept.

This research paper investigates the multifaceted risks associated with model drift in AI-guided robotic surgery over extended operational periods. As artificial intelligence (AI) increasingly integrates into complex medical procedures, the sustained efficacy and safety of AI models become paramount. Model drift, encompassing both data drift and concept drift, represents a significant challenge wherein the performance of deployed AI algorithms degrades due to shifts in underlying data distributions or changes in the relationships between input variables and target outcomes. In the high-stakes environment of robotic surgery, such degradation can lead to compromised precision, increased error rates, and ultimately, adverse patient outcomes. This paper delineates the various manifestations of model drift within surgical AI, including covariate shifts stemming from evolving patient demographics or surgical techniques, and concept shifts arising from advancements in medical knowledge or procedural modifications. Furthermore, it explores the clinical implications of AI model degradation, ranging from subtle inaccuracies in real- time guidance to critical failures in autonomous or semi-autonomous functions. The paper critically examines current detection and monitoring strategies, such as statistical process control and data distribution monitoring, highlighting their limitations in capturing nuanced or latent forms of drift. Finally, it proposes a comprehensive framework for mitigation and adaptive recalibration, emphasizing continuous retraining, transfer learning, active learning with human-in-the-loop systems, and the development of inherently robust and explainable AI architectures. The objective is to underscore the imperative for proactive management of model drift to ensure the long-term reliability, safety, and clinical utility of AI-guided robotic surgical systems, thereby fostering responsible innovation in medical technology

Automated guided vehicle (AGV) path planning aims to obtain an optimal path from the start point to the target point. Path planning methods are generally divided into classical algorithms and reactive algorithms, and this paper focuses on reactive algorithms. Reactive algorithms are classified into swarm intelligence algorithms and artificial intelligence algorithms, and this paper reviews relevant studies from the past six years (2019–2025). This review involves 123 papers: 81 papers are about reactive algorithms, 44 are based on the swarm intelligence algorithm, and 37 are based on artificial intelligence algorithms. The main categories of swarm intelligence algorithms include particle swarm optimization, ant colony optimization, and genetic algorithms. Neural networks, reinforcement learning, and fuzzy logic represent the main trends in artificial intelligence–based algorithms. Among the cited papers, 45.68% achieve online implementations, and 33.33% address multi-AGV systems. Swarm intelligence algorithms are suitable for static or simplified dynamic environments with a low computational complexity and fast convergence, as 79.55% of papers are based on a static environment and 22.73% achieve online path planning. Artificial intelligence algorithms are effective for dealing with dynamic environments, which contribute 72.97% to online implementation and 54.05% to dynamic environments, while they face the challenge of robustness and the sim-to-real problem.