Harvard Medical School Media Immersion: Thursday, May 30, Boston
Harvard Medical School
Researchers at the University of New Hampshire developed a new machine learning model, an application of artificial intelligence, that news services, like social media outlets, could easily use to better screen medical news stories for accuracy.
The Universe is almost inconceivably vast. So is the amount of data astronomers collect when they study it. This is a challenging process for the scientists and engineers at the U.S. National Science Foundation’s National Radio Astronomy Observatory (NRAO). But what if they could do it over 300 times faster?
A new study led by URI scientists Kathleen Melanson and Theodore Walls aims to shed light on real-world eating behaviors, using AI-enabled wearable technology. In collaboration with researchers at the University of Texas and funded by the National Institutes of Health, the team will develop a system to detect detailed information on eating motions.
Researchers at the Beckman Institute developed an artificial intelligence model that can accurately identify tumors and diseases in medical images. The tool draws a map to explain each diagnosis, helping doctors follow its line of reasoning, check for accuracy, and explain the results to patients.
Scientists at the University of Florida have pioneered a method for using semiconductor technology to manufacture processors that significantly enhance the efficiency of transmitting vast amounts of data across the globe.
PNNL scientists have put forth a new approach to protect the electric grid, creating a tool that sorts and prioritizes cyber threats on the fly.
Scientists develop a method for examining what happens when nanoelectronic materials switch between conducting and nonconducting phases. This may accelerate the development of neural-like circuits for use in nanoelectronic devices.
Scientists at Washington University School of Medicine in St. Louis trained a machine-learning algorithm to predict accurately brain metastasis using biopsy samples from early-stage non-small cell lung cancer patients. It was also highly accurate in predicting those patients who do not develop metastatic brain tumors.
Digital Science is delighted to announce the launch of AI-driven summarization in Dimensions, a new feature to support the user in their discovery process for publications, grants, patents and clinical trials.
Recent NCCN Guidelines updates—along with the supporting evidence—will be presented during the NCCN 2024 Annual Conference held in Orlando, Florida April 5-7, and simultaneously online. Visit NCCN.org/conference to learn more and register.
Unlike existing work, which relies on training data from social media examples, a new benchmark, named ToxicChat, is based on examples gathered from real-world interactions between users and an AI-powered chatbot. ToxicChat is able to weed out queries that use seemingly harmless language but are actually harmful, which would pass muster with most current models.
Fengqui "Frank" Li is a computational developer at Oak Ridge National Laboratory who uses his background as an architect to expand the landscape of design for his research into building energy modeling and beyond.
Atomic force microscopy, or AFM, is a widely used technique that can quantitatively map material surfaces in three dimensions, but its accuracy is limited by the size of the microscope’s probe. A new AI technique overcomes this limitation and allows microscopes to resolve material features smaller than the probe’s tip.
Scientists from the National University of Singapore (NUS) have pioneered a new methodology of fabricating carbon-based quantum materials at the atomic scale by integrating scanning probe microscopy techniques and deep neural networks. This breakthrough highlights the potential of implementing artificial intelligence at the sub-angstrom scale for enhanced control over atomic manufacturing, benefiting both fundamental research and future applications.
In a paper in the prestigious journal Science to appear on Feb. 29, 2024, a multi-institutional team led by scientists at Carnegie Mellon University and University of California at Berkeley found parts of the genome, both within genes and outside of them, that evolved and are associated with vocal learning across mammals. These elements have been linked to autism in humans.
A team at UC Davis has developed a machine-learning model that can better predict which patients are at greater risk to develop hepatocellular carcinoma.
UT Southwestern Medical Center researchers have developed an artificial intelligence (AI) method that writes its own algorithms and may one day operate as an "automated scientis" to extract the meaning behind complex datasets.
Digital Science has awarded two new Catalyst Grants of £25,000 each to innovative AI-based technology ideas aimed at advancing global research.
Continuous, unobtrusive sensors and related monitoring devices are installed in older drivers’ vehicles to detect changes in highly complex activities over time. A driver facing camera, forward facing camera, and telematics unit provide video in real-time to enable researchers to analyze abnormal driving such as getting lost, reaction time and braking patterns as well as travel patterns such as miles driven, miles during the night and daytime, and driving in severe weather. Detecting changes in behavior could generate early warning signs of possible changes in cognition.
A recent study introduce a novel paradigm combining ChatGPT with machine learning (ML) to significantly ease the application of ML in environmental science. This approach promises to bridge knowledge gaps and democratize the use of complex ML models for environmental sustainability.
Digital Science announces two new products – Dimensions Research GPT and Dimensions Research GPT Enterprise – bringing the unmatched, trusted research coverage of Dimensions to the ChatGPT platform.
Researchers at the Icahn School of Medicine at Mount Sinai and others have harnessed the power of machine learning to identify key predictors of mortality in dementia patients. The study, published in the February 28 online issue of Communications Medicine, addresses critical challenges in dementia care by pinpointing patients at high risk of near-term death and uncovers the factors that drive this risk. Unlike previous studies that focused on diagnosing dementia, this research delves into predicting patient prognosis, shedding light on mortality risks and contributing factors in various kinds of dementia.
Dartmouth researchers report they have developed the first smartphone application that uses artificial intelligence paired with facial-image processing software to reliably detect the onset of depression before the user even knows something is wrong.
Bridging precision engineering and precision medicine to create personalized physiology avatars. Pursuing on-demand tissue and organ engineering for human health. Revolutionizing neuroscience by using AI to engineer advanced brain interface systems. Engineering the immune system for health and wellness. Designing and engineering genomes for organism repurposing and genomic perturbations.
Two leading multiple sclerosis (MS) experts—Nancy Sicotte, MD, director of Multiple Sclerosis and Neuroimmunology at Cedars-Sinai, and Pascal Sati, PhD, director of the Neuro Imaging Program in the Department of Neurology—are attending the Americas Committee for Treatment and Research in Multiple Sclerosis Forum 2024 Feb. 29-March 2 in West Palm Beach, Florida.
The Technology Infrastructure for Data Exploration (TIDE) project at SDSU will give CSU researchers access to new high-performance data processing capabilities.
Researchers at the University of Notre Dame conducted a study using AI bots based on large language models and asked human and AI bot participants to engage in political discourse. Fifty-eight percent of the time, the participants could not identify who the AI bots were.
Too often, the first sign of cardiovascular disease may be a major event like a heart attack, stroke or cardiac arrest. Now, researchers and clinicians at Mayo Clinic are using artificial intelligence (AI) technology to flag heart problems earlier, boosting the abilities of a diagnostic test that has been around for over a century — the electrocardiogram (ECG).
As we get older, we may start to notice it takes us longer to find the right words. This can lead to concerns about cognitive decline and dementia.
Liberating Greatness in Every Neurosurgeon, AtlasGPT Delivers the Most Trusted Decision Support for Brain and Spine Care
While the rise of artificial intelligence is proving to be a contentious issue, new research from Edith Cowan University (ECU) has found that the use of social robots in a commercial setting would likely be met with less resistance.
In response to the rapidly evolving landscape of data collection and analysis driven by advances in artificial intelligence, the U.S. National Science Foundation (NSF) and the U.S. Department of Energy (DOE) have established a Research Coordination Network (RCN) dedicated to advancing privacy research and the development, deployment and scaling of privacy enhancing technologies (PETs). Fulfilling a mandate from the "Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence," the initiative advances the recommendations in the National Strategy to Advance Privacy-Preserving Data Sharing and Analytics to move towards a data ecosystem where the beneficial power of data can be unlocked while protecting privacy.
Practice makes perfect, and a new system being tested and perfected that enables surgical trainees to obtain cutting-edge instruction in real-time, all through a new artificial intelligence program. As medical students conduct surgical exercises, the AI software scans a live video feed and provides immediate, personalized feedback.The solution is among the first generation of AI teachers giving real-time feedback and may pioneer the use of similar instructional technology in other industries, including additional areas of healthcare and medicine.
With time scheduled to use a certain beamline at the National Synchrotron Light Source-II (NSLS-II), scientists from NSLS-II and their partner institutions faced a challenge. They planned on researching a special type of region in magnetic materials that could be useful for next-generation computers. Regions in magnetic materials - called magnetic domains - determine a material's magnetic properties. The scientists wanted to study how these magnetic domains changed over time under the influence of an outside magnetic field.
An interdisciplinary team of experts from the University of Notre Dame, in collaboration with the University of Maryland and University of Utah, have found a way to use artificial intelligence to analyze a household’s passive design characteristics and predict its energy expenses with more than 74 percent accuracy. By combining their findings with demographic data including poverty levels, the researchers have created a comprehensive model for predicting energy burden across 1,402 census tracts and nearly 300,000 households in Chicago.
From the invention of the wheel to the advent of the printing press to the splitting of the atom, history is replete with cautionary tales of new technologies emerging before humanity was ready to cope with them.
With national elections looming in the United States, concerns about misinformation are sharper than ever, and advances in artificial intelligence have made distinguishing genuine news sites from fake ones even more challenging. Virginia Tech experts explore three different facets of the AI-fueled spread of fake news sites and the efforts to combat them.
Researchers have paired a deep learning model with experimental data to “decode” mouse neural activity.
Research shows this tool can strongly support clinicians for patient care
ETRI’s researchers have unveiled a technology that combines generative AI and visual intelligence to create images from text inputs in just 2 seconds, propelling the field of ultra-fast generative visual intelligence.
A Princeton-led team composed of engineers, physicists, and data scientists from the University and the Princeton Plasma Physics Laboratory (PPPL) have harnessed the power of artificial intelligence to predict — and then avoid — the formation of a specific plasma problem in real time.
Two teams of engineers led by faculty in the McKelvey School of Engineering at Washington University in St. Louis will work toward developing products to monitor drinking water quality and to detect explosives with an electronic nose with one-year, $650,000 Convergence Accelerator Phase 1 grants from the National Science Foundation (NSF).
The U.S. Department of Energy (DOE) today announced awards totaling $61 million for small businesses in 17 states. The 50 projects funded by DOE’s Office of Science include the development of advanced scientific instruments, advanced materials, and clean energy conversion and storage technologies that will conduct climate research and advance the Biden-Harris Administration’s goal of a net-zero emissions economy.
Researchers at West Virginia University have identified a set of diagnostic metabolic biomarkers that can help them develop artificial intelligence tools to detect Alzheimer’s disease in its early stages, as well as determine risk factors and treatment interventions.
Dustin Tyler, the Kent H. Smith II Professor of Biomedical Engineering at CWRU’s Case School of Engineering, co-founded a company that restores for people the sensation of touch—with help from a set of electrical rings that fit snugly on users’ fingers—from a distance.
ETRI’s researchers have pioneered the development of light source devices that can be utilized in mega/hyper datacenters and 5G/6G mobile communication base stations. The technology innovated by the research team can transmit full HD movies of 5 GB size at a rate of 5.6 per second.
Imageomics, a new field of science, has made stunning progress in the past year and is on the verge of major discoveries about life on Earth, according to one of the founders of the discipline. Tanya Berger-Wolf, faculty director of the Translational Data Analytics Institute at The Ohio State University, outlined the state of imageomics in a presentation at the annual meeting of the American Association for the Advancement of Science.
The random information posted online could be used to generate information about biodiversity and its conservation.
Researchers studying complex phenomena such as the Higgs boson must work with massive experimental data sets. To help, researchers have defined practical FAIR (findable, accessible, interoperable, reusable) principles for data and applied the principles to an open simulated tktk from CERN. FAIR will help humans and computers use large data sets, enable modern computers to process these data sets, and aid the development of artificial intelligence tools.