Category
6,497 papers
ESNN is introduced, an Equivariant Sheaf Neural Network that enriches this interaction by learning directed, matrix-valued transport between neighboring vector features while preserving exact Euclidean equivariance.
This work formalizes resulting Hessian collection as a partially symmetric decomposition to establish conditions for local identifiability and stability to exploit vector-output stencil reuse to reduce the structural query cost by a factor of 16.
KuTIE (Kubernetes Topology Intelligence Engine), which builds a live cluster context from Istio call edges, Trivy KSPM findings, and the service-account bindings a workload reads, and conditions LLM patch generation on it, and improves remediation of topology-dependent findings well beyond scanner-only context.
Anatomy education serves as the cornerstone of medical training across both modern and traditional medicine systems. However, traditional pedagogical approaches—relying heavily on cadaveric dissection and two-dimensional illustrations—face mounting challenges, including cadaver shortages, ethical concerns, and the need to engage technology-oriented Generation Z learners. Artificial Intelligence (AI) has emerged as a transformative force in anatomical education, offering virtual dissection simulations, adaptive learning platforms, intelligent tutoring systems, and generative AI-powered chatbots. In modern medical education, AI tools such as ChatGPT, Anatbuddy, and VR/AR-based platforms have demonstrated significant potential in personalizing learning, generating assessment materials, and enhancing student engagement. Concurrently, in Ayurvedic anatomy education (Sharira Rachana), AI-powered tools like CADAVIZ and AyurSIM are bridging traditional knowledge with contemporary technological methods, enabling three-dimensional visualization of anatomical concepts and addressing resource disparities. This review consolidates existing evidence on AI applications in both streams of anatomy education, evaluates their effectiveness, and identifies key challenges including content accuracy concerns, over-reliance on technology, ethical considerations, and the need for customized knowledge bases. The findings underscore that AI should augment rather than replace traditional teaching methods, with a balanced, ethically guided approach being essential for effective integration. Future directions include developing specialized AI tools for traditional medicine anatomy, integrating real clinical cases, and establishing systematic AI literacy programmes for both educators and students.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Alzheimer's disease (AD), Parkinson's disease (PD) and multiple sclerosis (MS) are complex neurodegenerative diseases that are significant public health problems worldwide. Drug repurposing involves using drugs that are already known to be safe for some purpose for a new purpose. It's more likely to be a success than developing novel drugs. Therefore, drug repositioning could serve as a method to hasten the drug discovery process while also conserving both expenditure and time. Artificial intelligence (AI), machine learning (ML), and network-based pharmacology has transformed drug repositioning with integrated analysis of multi-omics data, knowledge biomedical knowledge graphs and real-world evidence (RWE). An assessment of the contemporary state of AI-powered drug repositioning and network-based pharmacology tactics applied to neurodegenerative illnesses comprising major approaches, candidate drugs, mechanisms, and translation barriers. The topic of this paper is the integration of multi-omics, systems biology, and sex-specific considerations in drug delivery tactics. Finally, it outlines potential paths towards clinical translation for the field – in AI related precision medicine and experimental testing.
Chronic rotator cuff tears are a clinical challenge due to chronic inflammation, progressive tendon degeneration, impairment in regeneration and fatty infiltration. High retear rates, particularly in chronic and large tears, highlight the limitations of mechanical repair alone. These limitations highlight the need for methods that can solve the biomechanical stability and the biological deficits that compromise healing. Orthobiologics utilise allogeneic and autologous substances derived from human cells and tissues to promote pain relief, tissue healing and enhance functioning through anti inflammatory effect. Current strategies include platelet rich plasma injection, bone marrow aspiration injections and mesenchymal stem cell therapy. Biologic augmentation is aimed at improving clinical outcomes and healing rates in rotator cuff repair. Robotics enhances the effectiveness of biologic augmentation by creating a mechanically optimized environment for healing. Robotic and navigation-assisted technologies support improved surgical precision, anchor placement accuracy, footprint restoration, and control of tendon tension. Technologies like three-dimensional imaging and artificial intelligence allow targeted biologic release and customised surgical plans for each individual. Comparing preclinical studies and clinical outcomes remains inconsistent, largely due to variability in biologic preparation, patient related factors such as their chronic condition and tissue quality. In chronic rotator cuff repair, orthobiologics and robotics show an advanced approach in the clinical treatments. Future studies and clinical trials will be critical to confirm and proceed these advanced treatment goals.
Alzheimer's disease (AD), Parkinson's disease (PD) and multiple sclerosis (MS) are complex neurodegenerative diseases that are significant public health problems worldwide. Drug repurposing involves using drugs that are already known to be safe for some purpose for a new purpose. It's more likely to be a success than developing novel drugs. Therefore, drug repositioning could serve as a method to hasten the drug discovery process while also conserving both expenditure and time. Artificial intelligence (AI), machine learning (ML), and network-based pharmacology has transformed drug repositioning with integrated analysis of multi-omics data, knowledge biomedical knowledge graphs and real-world evidence (RWE). An assessment of the contemporary state of AI-powered drug repositioning and network-based pharmacology tactics applied to neurodegenerative illnesses comprising major approaches, candidate drugs, mechanisms, and translation barriers. The topic of this paper is the integration of multi-omics, systems biology, and sex-specific considerations in drug delivery tactics. Finally, it outlines potential paths towards clinical translation for the field – in AI related precision medicine and experimental testing.
Rapid urbanization has significantly increased pressure on transportation systems, healthcare, energy distribution, environmental monitoring, waste management, public safety, and other municipal services. Traditional city management approaches are increasingly unable to process the enormous volume of heterogeneous data generated by modern urban environments. The integration of the Internet of Things (IoT) with cloud computing provides an effective solution for developing scalable smart city platforms capable of supporting real-time monitoring, intelligent decision-making, and efficient resource management. This paper presents a scalable cloud-enabled smart city architecture that integrates IoT sensing devices, edge gateways, cloud infrastructure, big data analytics, and artificial intelligence to support multiple smart city services within a unified platform. The proposed architecture employs a layered framework consisting of perception, communication, edge computing, cloud services, data analytics, application, and security layers to improve scalability, interoperability, reliability, and service availability. The study critically reviews recent advances in IoT cloud integration, identifies major challenges including security, privacy, latency, interoperability, and energy efficiency, and proposes practical strategies for addressing these limitations through containerization, micro services,edge cloud collaboration, and AI-driven resource orchestration. The proposed framework demonstrates how cloud computing can dynamically allocate computational resources to accommodate growing IoT deployments while maintaining quality of service. The paper concludes that scalable IoT-cloud platforms represent the foundation for next-generation smart cities and recommends future integration with digital twins, federated learning, block chain, and 6G communication technologies for improved sustainability and resilience.
Current Good Manufacturing Practice (cGMP) represents a fundamental regulatory and quality framework for ensuring that pharmaceutical products are consistently manufactured and controlled according to predefined standards of quality, safety, efficacy, identity, strength, and purity. With increasing complexity in pharmaceutical manufacturing, globalization of supply chains, adoption of advanced technologies, and growing regulatory expectations, cGMP compliance has evolved from a predominantly inspection-oriented approach to a comprehensive, science- and risk-based pharmaceutical quality system. This review provides an overview of the principles, regulatory framework, and essential components of cGMP applicable to pharmaceutical manufacturing. Major areas discussed include the Pharmaceutical Quality System (PQS), personnel and training, premises and equipment, documentation and data integrity, material management, production and in -process controls, quality control, qualification and validation, deviation management, Corrective and Preventive Action (CAPA), change control, Quality Risk Management (QRM), Product Quality Review (PQR), supplier management, and self-inspection. The review also highlights the roles of major regulatory authorities and guidance frameworks, including the U.S. Food and Drug Administration (FDA), European Medicines Agency (EMA), World Health Organization (WHO), International Council for Harmonisation (ICH), and Central Drugs Standard Control Organization (CDSCO). Particular emphasis is placed on ICH Q9(R1) and ICH Q10 as important frameworks supporting risk-based decision-making, lifecycle management, continual improvement, and effective pharmaceutical quality systems. Emerging trends such as digitalization, continuous manufacturing, Process Analytical Technology (PAT), automation, artificial intelligence, and advanced data analytics are also considered. Effective implementation of cGMP should extend beyond procedural compliance to establish a sustainable quality culture capable of maintaining process control, preventing quality failures, protecting patients, and supporting continuous improvement throughout the pharmaceutical product lifecycle.
Tuberculosis (TB) is a chronic infectious disease caused by Mycobacterium tuberculosis and remains one of the leading causes of morbidity and mortality worldwide. Despite the availability of effective chemotherapy, tuberculosis continues to pose a major public health challenge due to delayed diagnosis, poor treatment adherence, HIV co-infection, and the increasing prevalence of multidrug-resistant (MDR-TB) and extensively drug-resistant tuberculosis (XDR-TB). According to the World Health Organization (WHO), approximately 10.8 million people developed tuberculosis globally in 2023, resulting in nearly 1.25 million deaths. Early diagnosis using rapid molecular diagnostic techniques such as GeneXpert MTB/RIF, along with appropriate chemotherapy, has significantly improved treatment outcomes. The standard treatment regimen for drug-susceptible tuberculosis consists of a six-month multidrug therapy, while newer drugs including bedaquiline, delamanid, and pretomanid have revolutionized the management of drug-resistant tuberculosis. Recent advances in host-directed therapy, nanotechnology-based drug delivery systems, artificial intelligence-assisted diagnosis, and novel vaccine candidates have shown promising results in improving disease control and patient outcomes. This review summarizes the epidemiology, etiology, pathophysiology, clinical manifestations, diagnosis, conventional treatment, drug-resistant tuberculosis, recent therapeutic advances, patient counseling, and future perspectives in tuberculosis management. Continuous research, early detection, effective treatment strategies, and global public health initiatives are essential to achieve the WHO End TB Strategy and reduce the worldwide burden of tuberculosis.
Health-professions students are increasingly using artificial intelligence (AI) tools, especially large language model (LLM)-based chatbots like ChatGPT, for academic tasks as well as informal drug information retrieval, symptom checking, and self-medication decision-making.[2,9,3,7] Due to their dual roles as future gatekeepers of safe pharmaceutical use, trainees in sciences connected to medicine, and consumers of health information, pharmacy students hold a special place in this conversation.[2,3,20,33,56] In order to describe what is known about pharmacy (and allied health) students' knowledge of AI, their attitudes toward its use in clinical and self-care contexts, and their actual practices—including the use of AI for drug information, dosing guidance, and self-diagnosis-adjacent tasks—this review synthesizes nine cross-sectional Knowledge, Attitude, and Practice (KAP) studies conducted between 2022 and 2026 across Zambia.[3] Saudi Arabia.[2,6] India.[1,4,8] Syria.[9] Malaysia.[5] and other settings. AI awareness is almost universal (82–100%) in all contexts.[2,3,5,6,8,9] but conceptual understanding of AI subtypes, medical uses, and limitations is generally lower (30–60%).[2,3,5,6,8,9] Concerns concerning data privacy, false information, over-reliance, and professional displacement temper the generally positive attitudes.[1,2,6,7,8] Practice is still limited: formal curricular training is uncommon (7–46%).[2,3,6,7,9] and the majority of self-reported AI use focuses on academic activities (summarizing, presentations, exam preparation) rather than verified clinical decision-support.[3,4,5,7] There is a dearth of direct data on AI-assisted self-diagnosis and self-medication, particularly among pharmacy students. In order to outline the emerging risk landscape and suggest curricular and regulatory responses, this review draws conclusions from related findings, such as the use of ChatGPT for "getting drug information".[2] perceived AI usefulness in "medication management".[1,2] and expressed willingness to trust AI-generated dosing recommendations.[2]
Driven by artificial intelligence, or AI, today's medicinal science has the potential of rapidly transforming a doctor's knowledge of patient reactions to a variety of medications. In clinical practice, one has seen that sometimes a given medication is effective and sometimes ineffective in a patient. This difference could be caused by genetics, lifestyle, disease conditions, environmental exposure or none of the above. With the advent of AI, drug response prediction and optimization are now better supported with many various approaches. Random Forest (RF) and Support Vector Machine (SVM) are some of the common machine learning algorithms employed to predict the activity of a particular drug, identify the biomarkers and classify patients as responders and non-responders. These techniques aid doctors with the informed decisions, particularly regarding chemotherapy. Gradient Boosting models also predict clinical risks and bad drug reactions with lot of precision, such as XGBoost, and LightGBM. The use of complex biological patterns by deep learning models is enhancing the field of pharmacology research further. The use of Artificial neural Networks (ANNs) to explore drug interactions with the target and to simulate Pharmacokinetics – the mechanisms of body uptake, distribution and disposition of drugs. CNNs also are extremely effective when performing image analysis tasks, such as detecting tumors or modeling and assessing the effectiveness of cancer medications with medical images. The Recurrent Neural Networks (RNNs) are designed to see data changing over time and so help doctors stay abreast of patients' progress and predict their long-term outcomes. More sophisticated AI techniques are making a large impact too. Graphical models are used to describe complex molecular and drug–drug network data and graphical networks are used in Graph Neural Networks (GNNs) to understand the relationships between different molecules and drugs. This is really important to identify safe and effective combined therapies. Drug Safety Monitoring and Evidence-Based Decision Making can be enhanced through the use of Natural Language Processing (NLP), as this technology can extract valuable information from clinical notes, research articles, and electronic health records. Using Reinforcement Learning (RL), flexible treatment plans can be developed by optimising the dose of drug administration in real-time. Pro-bayarian networks: Bayes models when a doctor doesn’t know what to do. Combination of clinical with multi-omics data (including genomic, transcriptomic, and proteomic data) is one of the most powerful of AI. Such a combination helps understand disease mechanisms and patient variability better, resulting in improved patient stratification, personalized dosages and therapeutic outcomes.
Machine Intelligence
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
A Blog post by IBM Research on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
