Articles tagged with Artificial Intelligence
The collaboration aims to advance research on brain health with a focus on Alzheimer's disease. Initial projects will use CAS Content Collection and advanced technologies, including AI models and quantum computing to build and train disease-specific models.
A new artificial intelligence-based method detects genetic markers of antibiotic resistance in bacteria, potentially leading to faster and more effective treatments. The method, called Group Association Model, uses machine learning to identify key mutations linked to drug resistance, reducing false positives and misdiagnoses.
A Cedars-Sinai study finds AI treatment recommendations were graded higher than physician decisions in virtual urgent care settings. AI excelled at identifying critical red flags and suggesting antibiotic treatments, but physicians better assessed patient histories and adapted recommendations.
A study found that AI recommendations were rated as superior to physicians' decisions in real-life clinical settings, with lower risk for potential harm. The AI system uses modeling to calculate probabilities and derives treatment plans based on medical guidelines, complementing human physician discernment.
Researchers developed a machine learning-powered fluid simulation model that significantly reduces computation time without compromising accuracy. The new surrogate model maintains the same level of accuracy as traditional particle-based simulations while reducing computation time from approximately 45 minutes to just three minutes.
Researchers at George Mason University have developed AI models that can predict cancer risk with accuracy rates of up to 90% for certain types of cancer. These models can enable risk-based screening recommendations, increasing access to life-saving cancer detection for high-risk patients.
Researchers develop AI model to predict lightning-induced wildfires with over 90% accuracy, integrating data from satellites, weather systems, and environmental factors. The model has the potential to transform emergency response and disaster management worldwide, saving lives and preserving ecosystems.
A new framework helps clinicians choose phrases that more accurately reflect the likelihood of certain pathologies in X-rays, improving the reliability of critical clinical information. The approach treats certainty phrases as probability distributions, capturing nuances of what each word means.
The conference gathered international researchers to discuss AI's role in drug discovery and development, including generative AI strategies for designing chemical compounds. The speakers emphasized the significance of personalized medicine, where therapies will be tailored to each patient's unique molecular profile.
A team of researchers discovered that a robotic hand can learn to grasp and rotate objects even with incomplete or absent tactile sensation. The study highlights the importance of the sequence of learning experiences, also known as the curriculum, in facilitating learning.
The US power system lacks capacity to handle rising demand, meeting participants agreed. Six big ideas for federal and state energy policymakers consider expanding the grid, optimizing current capabilities, and controlling costs and system reliability.
A clinical trial shows that AI screening for opioid use disorder is as effective as healthcare providers in generating referrals to addiction specialists. The study found a 47% reduction in hospital readmissions among patients who received AI screening, resulting in estimated healthcare savings of nearly $109,000.
A new study developed an AI model that can predict whether bacteria will become antibiotic-resistant by analyzing their genetic data. The model shows that antibiotic resistance is more easily transmitted between genetically similar bacteria and mainly occurs in wastewater treatment plants and inside the human body.
The study explores AI-driven innovations across multiple scales, from material design to industrial park optimization, highlighting its potential for simplifying complex chemical processes. However, data reliability remains a major challenge, and full-scale industrial implementation faces technical, economic, social, and ethical hurdles.
The device uses AI technology to detect potential heart problems and provides real-time health insights. It has multiple points touching the skin near the heart, allowing for more accurate tracking even during movement.
A new study suggests AI-driven smart devices can revolutionize healthcare by detecting cardiac issues early, triggering emergency responses. The Internet of Medical Things (IoMT) technology enables real-time patient monitoring and analysis, improving efficiency and reducing costs.
Researchers developed an AI system, Plant Doctor, to monitor urban plant health at the individual leaf level using machine vision techniques. The system can automatically diagnose diseased areas on leaves and provide accurate diagnoses across various urban flora.
A study explores how large language models (LLMs) can transform teaching by generating customized educational materials, assessing student progress, and providing targeted feedback. LLMs excel at automating routine tasks, reducing teachers' workload and enabling them to focus on mentoring students.
The NCCN 2025 Annual Conference showcased the critical impact of cancer research on improving lives. The conference featured new research, discussions on AI in oncology care, and strategies for ensuring high-quality, person-centered cancer care.
A new framework developed by MIT researchers allows large language models (LLMs) to break down complex planning problems into manageable parts and find optimal solutions using software optimization tools. The framework achieves an 85% success rate on nine complex challenges, outperforming the best baseline.
A novel AI-based method called scNET combines gene expression data with networks of possible gene interactions to identify biological patterns in response to drug treatments. The system reveals complex mechanisms underlying cellular behavior, providing insights for new therapeutic approaches.
RAZO Energy's intelligent charging management enables noticeable cost savings for electric vehicle users, reducing costs per hundred kilometers from six euros to two. The system helps keep the power grid stable by balancing consumption and generation of energy in an optimum way.
A new study offers a fresh perspective on how education systems can adapt to the challenges and opportunities of artificial intelligence. The study proposes several innovative strategies, including reducing prescribed curriculum time, transforming pedagogy, and personalizing assessments.
Dr. Agnes Szmolenszky has been appointed Executive Director of the Heidelberg Laureate Forum Foundation, effective April 1, 2025. She brings extensive experience in science management, education, outreach, and international cooperation to the role.
A study reveals that AI-powered content on a Russian-backed outlet increased publication rate by over 100% and broadened topics, while maintaining persuasive power. The research warns of the urgent need to mitigate AI-assisted propaganda campaigns.
A groundbreaking study reveals that autistic children exhibit social attention patterns similar to their typically developing peers during play, with a primary focus on toys rather than faces. This challenges the longstanding assumption that reduced eye contact is a definitive marker of autism.
A research team at Oxford is developing a machine learning-based filtering tool to accurately distinguish between genuine wildlife references and unrelated content. The project aims to reduce misclassification, misinformation, and misinterpretation of wildlife data, enhancing media-based conservation research.
Researchers developed an AI-powered breath test to detect silicosis, a lung disease caused by inhaling silicon dioxide particles. The test shows high accuracy in differentiating between affected and unaffected individuals, with results provided in minutes.
PolyU's EmoFriends interactive toy and Transparent Knee Guard wearable device have won the prestigious iF Design Awards 2025 for their cutting-edge sensing technology and emotional support capabilities. The devices demonstrate innovative design solutions for healthcare and technology, showcasing PolyU's commitment to research excellence.
Researchers from UC Berkeley and UCSF developed a streaming method that synthesizes brain signals into audible speech in near-real time, solving the latency challenge. The technology represents a critical step toward enabling communication for people who have lost the ability to speak, with high decoding accuracy and naturalistic fluency.
Researchers developed new AI models, InstaNovo and InstaNovo+, to vastly improve accuracy and discovery in protein science. These models excel in tasks such as de novo peptide sequencing, identifying microorganisms, and discovering novel peptides, with implications for personalized medicine, cancer immunology, and beyond.
A deep learning model has been developed to identify tooth and sinus structures in dental X-rays with an accuracy of 98.2%, outperforming traditional detection methods. The system minimizes patient exposure to radiation and provides a cost-effective screening tool for early diagnosis and prompt intervention.
Researchers developed a new viscoelastic model of enzymes, elucidating the intertwined effects of elastic forces and friction forces on enzyme function. This breakthrough allows proteins to be perceived as soft robots or programmable active matter, revolutionizing our understanding of enzymatic catalysis.
Researchers developed an AI algorithm to help surgeons position knee components in a way that better matches each patient's natural anatomy. Patients with naturally bowed legs responded well to the 'functionally aligned' knee surgery, reporting better outcomes.
An AI model has been developed to detect blocked coronary arteries based on ECG readings, achieving high accuracy and outperforming expert clinicians. The model could help physicians quickly identify patients who require urgent treatment for a heart attack.
A new study shows that AI-assisted 20-week pregnancy scans are accurate and reliable, taking only over 40% less time than standard scans. This allows sonographers to focus on other aspects of the scan, such as communicating with parents.
The study found significant improvements in symptoms for participants with major depressive disorder, generalized anxiety disorder, and eating disorders. Participants reported trusting and communicating with Therabot comparable to working with a therapist.
A new study by Reichman University explores the emotional consequences of using artificial intelligence, finding a U-shaped relationship between anxiety and AI usage. The research highlights the psychological motivations and barriers associated with adopting smart technologies.
Researchers developed a new liquid-crystal-based platform to handle hundreds of optical modes in compact two-dimensional setups, overcoming optical losses. This breakthrough enables the scalability of quantum simulations and all-optical AI systems.
Researchers used a large language model to analyze clinical reports of autism patients and found that repetitive behaviors and special interests are most indicative of an autism diagnosis. The study aims to improve diagnostic guidelines by reducing the focus on social factors.
Researchers developed a new method to include uncertainty in predictive algorithms, ensuring accurate and reliable solutions. The approach uses Markov models to explicitly include uncertainty in specific parameters, allowing for faster predictions and more complete analysis.
Researchers found people in Japan are less likely to exploit cooperative AI agents compared to humans, while Westerners take advantage of robots more often due to guilt over human exploitation. Cultural differences may shape the future of automation.
A new brain-like computer uses analog computing to process and store information in the same location as biological neurons, reducing power consumption by 0.25%. The device, called a memristor network, is more efficient than conventional transistor-based computers and has implications for autonomous vehicles and drones.
The University of Arizona College of Engineering has received a $1 million endowment to support its electrical and computer engineering department. The Thomas R. Brown Family Private Foundation donated the funds to create a leadership chair, which will focus on artificial intelligence and cybersecurity research.
The forum highlights AI's vast potential in optimizing energy production, accelerating new material inventions, improving climate modeling, and supporting green finance applications. It also emphasizes the need for a whole-of-community approach to harnessing AI's transformative power in combating climate change.
DeepSeek achieves performance on par with GPT-4o-mini through cutting-edge NLP techniques, providing intelligent information retrieval and analytical solutions for healthcare. It helps doctors identify potential blind spots, optimizes doctor-patient communication, and enhances medical efficiency.
The emergence of DeepSeek has triggered the 'catfish effect' in the AI domain, prompting rapid technological iteration and innovation. The company's latest model, DeepSeek-R1, demonstrates significant advancements in AI performance and efficiency, particularly in resource-constrained environments.
University of Missouri researchers developed a method using lidar and AI to analyze pedestrian, cyclist, and vehicle interactions at traffic signals. The approach aims to enhance driver awareness, reduce accidents, and improve mobility.
A new brief warns that assistive AI may worsen challenges related to error prevention and physician burnout. The researchers predict that medical liability will depend on who is considered at fault when the technology fails, subjecting physicians to unrealistic expectations.
A new review article identifies major themes in AI application to neurosciences, including a 5-fold increase in AI-related publications. The study also notes a surge of over 13-fold in clinical neurology AI-related publications in the past decade.
The event will feature major announcements in AI-driven networking, 1.6T advancements, quantum technologies, and next-gen optical innovations. Over 13,500 attendees are expected, with nearly 100 California-based companies participating.
The company will use AI translation tools to publish books in multiple languages, making them accessible to a broader audience. This initiative aims to promote better understanding between cultures and accelerate awareness of knowledge required to meet today's challenges.
The AI FORA project analyzed how AI-based social assessment varies across nine countries and four continents, highlighting the need for flexible, dynamic, and adaptive systems that reflect social stakeholders' perspectives. The research aims to improve AI in addressing fairness and discrimination issues in public social services.
Researchers developed a machine learning-based method called Symbolic Modeling to handle financial asset pricing tasks, reducing prediction errors compared to traditional models. The approach uses genetic programming and deep learning to automatically generate nonlinear expressions that adapt to multiple datasets.
A groundbreaking study found that AI-powered interviews with children can improve the accuracy of witness accounts by improving questioning style and efficiency. The study compared the performance of a Large Language Model (LLM) and untrained human interviewers in interviewing children about a mock event.
Researchers have developed a hybrid image-generation tool called HART that combines the strengths of autoregressive and diffusion models. It achieves high reconstruction quality with significantly reduced computational resources, enabling local execution on laptops or smartphones.
Researchers develop a groundbreaking 3D photonic-electronic platform that achieves unprecedented energy efficiency and bandwidth density for AI hardware. The innovation addresses critical challenges in data movement, enabling faster and more efficient AI technologies.
Researchers at Scripps Research uncovered structural hallmarks of long-term memory called an engram, which expands connectivity through specialized axonal terminals and alters synaptic architecture. This discovery could lead to new treatments for memory disorders.
A VCU researcher found that emergency management and homeland security professionals are more hesitant to act when faced with an AI threat, especially a strategic AI-based one. Those who believed AI could replace them acted recklessly.
Researchers created a powerful new computational and artificial intelligence tool that can generate high-resolution 3D maps of the brain in mice, allowing users to zoom in and out and peer into the full set of molecules producing energy for brain functions. This breakthrough brings scientists closer to understanding the role of metabol...