Articles tagged with Artificial Intelligence
The American College of Radiology has issued a joint statement with four other radiology societies to address the development and use of AI tools in radiology. The statement emphasizes the need for increased monitoring of AI utility and safety, advocating for collaboration among developers, clinicians, purchasers, and regulators.
Researchers at Universiteit van Amsterdam developed an autonomous chemical synthesis robot with integrated AI, outperforming human chemists in terms of speed and accuracy. The 'RoboChem' system can perform various reactions while producing minimal waste and delivering results quickly.
The TRAILS AI Institute has awarded eight seed grants totaling $1.5 million to advance AI design, development and governance. The funded projects include developing AI chatbots for smoking cessation and designing animal-like robots for autism support.
A study by Lancaster University forecasts exponential growth in Artificial Intelligence over the next 15 years, with experts warning of corners being cut in safe AI development. The experts also predict that advances in technology will make it harder to distinguish truth from fiction, with potential ramifications for democracies.
Researchers at City of Hope and TGen developed a machine-learning tool that can identify half of the cancers in 11 studied types with high accuracy. The innovative 'fragmentomics' approach allows for smaller blood draws, making it more practical for clinical applications.
Researchers from Cleveland Clinic and IBM have developed an AI strategy to identify new targets for immunotherapy treatments. The study, published in Briefings in Bioinformatics, reveals how artificial intelligence can be designed to accurately depict how immune systems recognize target antigens.
Researchers predict an increase in bad-actor AI attacks on mainstream communities by mid-2024, with AI tools being used to spread toxic content daily.
A new study by George Washington University researchers predicts an escalation of daily bad-actor AI activity globally by mid-2024, posing a significant threat to election results. The study provides the first quantitative analysis of the misuse of AI for disinformation during elections.
Researchers at Stanford University have developed a new phase-change memory that could help computers process large amounts of data faster and more efficiently. The technology improves several metrics simultaneously, including speed, endurance, and stability, while operating below 1 volt.
By 2050, at least 34% of Alpine ice volume will be lost even if global warming stops. This is based on a new study predicting near-term ice loss due to climate inertia.
A groundbreaking study uses machine learning to predict treatment resistance in cervical cancer by analyzing genetic mutations. The algorithm identified molecular assemblies driving treatment resistance and pinpointed tumors most susceptible to therapy, resulting in improved patient outcomes.
Scientists at Kyushu University use machine learning to identify promising green energy materials, accelerating the search for hydrogen fuel cell efficiency and expanding material discovery capabilities. Two new candidate materials with unique crystal structures have been successfully synthesized.
Researchers developed an AI-driven algorithm that accurately predicts death and complications after percutaneous coronary intervention (PCI). The tool uses patient feedback to provide a patient-centered, individualized risk prediction score.
A new technique using optical orbital angular momentum lattice (OAML) multiplexed holography boosts information storage capacity and offers novel approaches for implementing high-capacity holographic systems. The research unlocks supplementary encrypted dimensions, enhancing storage capacity and overcoming limitations of traditional me...
Researchers from Osaka University have developed a small sensor-based data logger that automatically detects and records video of infrequent behaviors in wild seabirds. The bio-logger uses low-power sensors and artificial intelligence to capture rare behaviors, such as head-shaking and foraging habits, without needing human supervision.
A study published in Arthroplasty Today found that robotic-assisted knee revision surgery significantly influences the function of the knee replacement. The computer system can help predict implant size and balance the knee for stability, leading to improved patient outcomes.
A unique framework measures individual perceptions of common sense and collective beliefs across groups, finding that larger groups have fewer common beliefs. Demographic factors like age or education do not influence common sense, but social perceptiveness does correlate with higher levels.
A nurse practitioner at The Hospital for Sick Children reduced invasive scans by 58% after using an AI model to analyze ultrasounds. She developed a new type of bias called induced belief revision through repeated exposure to the model.
The CACHE Challenge series has identified seven promising molecules with potential for new, more effective drugs for familial Parkinson's disease. The open science competition, funded by The Michael J. Fox Foundation and Conscience, used AI to predict hits and validated experimental results.
Researchers have developed an AI-enabled bio-logger that captures rare bird behaviors, including vigorous head shaking before flight and deep-sea mating rituals. The system uses outlier detection to identify unusual behaviors in real-time, providing valuable insights into animal biology and ecology.
Researchers at UB have developed a new deepfake detection algorithm that reduces biases in facial recognition, with one method classifying videos based on demographics and the other relying on features not visible to the human eye. The algorithms improved fairness metrics and reduced disparities in accuracy across races and genders.
The study introduced a silver-dispersive chalcogenide thin film for use in memristive devices, addressing data retention and endurance challenges. The device demonstrated reliable state retention and endurance, even at high temperatures, and achieved a recognition rate of ~92% in the MNIST database.
Researchers developed a platform combining automated experiments with AI to predict chemical reactivity, greatly accelerating the design process for new drugs. A machine learning model predicts where molecules will react and how reaction sites vary under different conditions, enabling precise tweaks to complex molecules.
AI models predict patient outcomes with high accuracy within their training data, but their performance deteriorates when used outside the original trial or in different clinical settings. Researchers aim to improve accuracy by examining large patient groups and exploring new data modalities.
A new study suggests that using artificial intelligence to scan surgery patients' medical records can identify those with risky drinking habits who may benefit from education or treatment. The AI system analyzed over 53,000 patient records and found three times more patients with high-risk alcohol use than diagnosis codes alone.
A new European research project, SMARTS, aims to improve air travel efficiency by redesigning flexible airspace sectors using artificial intelligence. The €2million project will create accurate predictive models and develop innovative sector configuration plans to reduce passenger delays, increase productivity, and lower emissions.
Researchers developed AI models that can extract information on social determinants of health from clinicians' notes, identifying 93.8% of patients with adverse social factors. The models were less prone to bias than generalist models, offering a potential solution to address health disparities.
Researchers at UMass Amherst have received an NIH grant to create predictive models for Alzheimer's disease using brain MRIs and clinical data. The goal is to enable earlier detection of the condition, ideally two years before onset of symptoms.
Researchers have developed a thermal management technique for photonic packages using glass substrates and thermoelectric vias, enabling precise temperature control. The technology, termed SimTEC, combines through glass vias partially filled with copper and thermoelectric materials to reduce thermal resistance between chips.
Researchers built a new AI that challenges traditional fingerprint comparison methods, revealing similarities between fingerprints from different fingers of the same person. The system achieved high accuracy in detecting intra-person fingerprint matches, potentially increasing forensic efficiency by tenfold.
The partnership aims to leverage AI and cloud computing to accelerate scientific discovery in chemistry and materials science, two key fields for global energy challenges. PNNL researchers are testing Microsoft's Azure Quantum Elements platform to identify promising new materials for energy applications.
Researchers aim to create robots that can change tasks autonomously and explore settings to optimize performance. The project will focus on battery recycling and energy efficiency, with the goal of reducing industrial waste.
Researchers developed a machine learning-based method to estimate chemical attributes of spice extracts by measuring fluorescence emitted by polyphenols and flavonoids. The approach integrated data from multiple dilution levels, achieving highly accurate results.
A study redevelops a framework for teaching artificial intelligence and robotics to preschool children, providing five big ideas that can be grasped by young kids. The framework aims to prepare children to understand and use AI tools effectively, promoting healthy and responsible learning in the rapidly developing digital society.
A recent study published by the Mayo Clinic found that an AI-enabled digital stethoscope can detect peripartum cardiomyopathy, a potentially life-threatening condition, more accurately than regular care. The researchers identified twice as many cases using the AI-powered tool.
Researchers developed mathematical models based on real events data from the Swedish Trauma Registry, showing that AI models outperformed clinical outcomes. The study highlights the potential of AI-powered decision support to improve ambulance staff's ability to assess injury severity and potentially save more lives.
Researchers harness AI power to predict right ventricle issues from electrocardiograms, promising more innovative tools and improved patient outcomes. The study departs from traditional methods, predicting something not easily quantifiable by other common tests.
A new study uses machine learning and satellite imagery to create the first global map of large vessel traffic and offshore infrastructure, finding a remarkable amount of activity previously unknown. The analysis reveals that industrial fishing and transport activities are concentrated around Africa and south Asia.
Recent advancements in AI, particularly deep learning and neural networks, offer significant potential for improving HCC diagnosis. Early detection of HCC is crucial, as curative treatments like surgery and liver transplant are only possible in the early stages.
A recent study suggests that AI can provide real-time analysis of foods and support nutritionists in their work with patients. The study evaluates the consistency and accuracy of AI in providing energy and macronutrient information, showing promising results.
Researchers developed an AI system that analyzed video recordings from therapy sessions with patients with borderline personality pathology. The system accurately detected the emotional states of patients, including fleeting micro-expressions. It also identified a predictor for therapy success: 'social' smiling at the start of a session.
A new study uses reinforcement learning to develop an AI model that can hedge derivative contracts with significantly lower training data requirements. The model's adaptability and accuracy under realistic conditions outperformed benchmark systems.
A study of 100 adults found a significant link between poor sleep quality and higher systolic blood pressure, kidney function impairment, and liver function issues. The research highlights the potential of home-based electroencephalography for assessing sleep quality.
Researchers developed a synaptic transistor capable of higher-level thinking and performing associative learning, categorizing data, and retaining information at room temperature. The device operates fast, consumes low energy, and is ideal for real-world applications.
A study by University of Eastern Finland finds that integrating AI systems into service teams increases demands on middle management, requiring balancing acts and new skills. The study also highlights the need for human managers to focus on innovations and development while AI handles routine tasks.
A new AI system, Coscientist, has demonstrated its ability to autonomously learn about Nobel Prize-winning chemical reactions and design successful laboratory procedures. The system achieved this in just a few minutes, outperforming human chemists in some cases.
The Coscientist AI system has been successfully designed, planned, and executed a chemistry experiment, demonstrating its potential to revolutionize scientific research. By leveraging large language models and cloud lab technology, Coscientist can automate the experimental process, enabling scientists to design and run experiments much...
A new study from the University of Ottawa and Copenhagen Business School finds that removing human bias from organizational processes can lead to autonomous systems that create their own environments. This could limit human ability to recognize automation biases, notice environmental shifts, and take action.
Researchers are leveraging AI/ML to improve health outcomes, but human judgment is still crucial for model selection and data quality. Explainable AI can enhance transparency and acceptance in clinical practice.
The scientific community must create a flexible governance framework to ensure equity, prevent unintended consequences, and maximize positive impact. To achieve this, the authors suggest advancing AI infrastructure, democratizing access to research and outcomes.
A multicenter randomized clinical vignette survey study found that AI models, when systematically biased, reduced diagnostic accuracy. The study involved hospitalist physicians, nurse practitioners, and physician assistants from 13 states.
Researchers at Nagoya University used AI to analyze image data of polycrystalline silicon and discovered staircase-like structures that cause dislocations during crystal growth. The study sheds light on the formation of dislocations in polycrystalline materials, which can affect electrical conduction and overall performance.
A new framework for artificial intelligence (AI) has been outlined to tackle antimicrobial resistance (AMR), a major global health threat. The AI blueprint aims to optimize antimicrobial use and infection care through adaptive implementation and maintenance.
Scientists at the University of Washington School of Medicine developed a novel protein design approach using AI, creating proteins that bind to challenging biomarkers with exceptionally high affinity and specificity. The breakthrough has implications for drug development, disease diagnosis, and environmental monitoring.
A new study published in Frontiers in Artificial Intelligence found that training in Interlingual Respeaking, a new practice combining human collaboration with speech recognition software, can improve language professionals' cognitive abilities. The research, conducted by the University of Surrey, showed significant enhancements in wor...
A team of MIT researchers has created a computational model that can calculate the structures of transition states in chemical reactions much more quickly than traditional methods. The new model uses machine learning and can generate accurate predictions for thousands of reactions, enabling chemists to design new catalysts and fuels.
A NSF-funded project, MABLE, is developing a digital app using crowdsensing, AI, and robotics to empower individuals with responsive maps and turn-by-turn instructions. The app aims to improve accessibility and navigation for persons with visual or mobility impairments, such as those with low vision and wheelchair users.
A technical expert panel provides guiding principles to avoid algorithmic bias in healthcare, aiming to reduce healthcare disparities and promote health equity. The principles aim to identify biases before implementation and mitigate their impact through conscious decisions by developers, users, and regulators.
A diagnostic study of 1,890 eyes supports the use of artificial intelligence in screening for autism spectrum disorder (ASD) and assessing symptom severity. Retinal photographs may improve accessibility to specialized assessments by reducing resource strain.
Klick Applied Sciences unveils LOVENet, an AI framework that rapidly identifies new therapeutic indications for existing drugs. The algorithm integrates large language model and structured knowledge graph technology to offer a fresh perspective on new potential applications.