Researchers at Pennington Biomedical developed GVC-Calc to analyze continuous glucose monitoring data, providing a scalable and transparent approach. The platform supports batch processing, integrates individual-level data with cohort-level results, and offers consensus clinical metrics alongside exploratory measures.
Two iSchool faculty members receive IMLS grants for projects focused on public library services, children's literature, and AI literacy. The grants aim to strengthen library services, develop new models, and create interactive toolkits for librarians.
Jiaqi Ma's $660,307 grant aims to develop tools for understanding how individual components of training data affect large AI systems. This project will improve the performance and reliability of widely used technologies like language models and recommendation systems.
A White House announcement on treating autism with leucovorin and against acetaminophen during pregnancy led to significant increases in internet searches for these topics. Nearly 1 million additional searches for leucovorin were recorded, alongside over 4 million searches for acetaminophen.
A 20-year study in the UK, Australia, and US reveals a significant increase in menopause-related search patterns focused on commercial products and services. This shift indicates a growing need for non-clinical guidance and support beyond traditional clinical encounters.
The Journal of Medical Internet Research publishes a theme issue on digital inclusion in the Global South, examining access, agency, and impact. The focus areas include measuring digital access, gendered digital realities, and digital innovations across health and livelihoods.
Researchers introduce the capabilities approach-contextual integrity (CA-CI) framework to address privacy and dignity risks in AI systems. The framework evaluates normative appropriateness of AI systems beyond narrow tasks and stable contexts, securing social life and human dignity.
Researchers from ISTA developed an algorithm that can extract and analyze information from the world’s most extensive biobank with unprecedented accuracy and speed. The method, dubbed gVAMP, enhances the framework's ability to extract complex information from the dataset at hand, providing a detailed overview of the effects on a trait ...
The Stowers Institute has appointed its first AI Fellow, Sumner Magruder, to harness the potential of artificial intelligence in biological research. He will collaborate with researchers to design new algorithms and unlock insights from large datasets.
A University of Cambridge report argues that menstrual tracking app data is a valuable resource for advertisers but poses significant privacy and safety risks to users. The report calls for better governance of the industry to protect user data and urges public health bodies to launch alternative apps.
University of Missouri researchers create digital sentiment map using AI to analyze public Instagram posts, linking emotional tone to real-life features. The tool aims to improve city services, identify areas of concern, and inform emergency response decisions.
GigaScience Press has won the first-ever Crossref Metadata Award, recognizing its efforts in providing high-quality metadata for its journal GigaByte. The award highlights the press's commitment to making research more discoverable and accessible through rich metadata standards.
A novel framework for retrieving concise entailing legal articles has been proposed, achieving state-of-the-art results across two datasets. The Retrieve–Revise–Refine framework combines small and large language models to improve precision while limiting recall loss.
A recent study by UCL researchers reveals that people with poorer mental health are more prone to browsing negative content online, which further exacerbates their symptoms. The study found that adding 'content labels' to webpages can help users make healthier and more informed decisions about the content they consume.
A new four-year, $459,000 grant will develop software and hardware tools to increase accessibility in STEM fields for persons with disabilities. The project aims to enhance data technologies for blind and low-vision users, making it easier for them to participate in STEM research and education.
Researchers at TU Wien have developed a theory to extract information from waves, allowing for precise measurements of objects in space. The theory reveals that the information content of a wave depends on its interaction with the object's properties, enabling customised waves to be generated for optimal information transfer.
A new study in Health Data Science leverages keywords from Google Trends alongside research abstracts from the WHO COVID-19 database to dissect the pandemic's discourse dynamics. Academics respond faster and provide more detailed insights than GT, enriching policy formulation.
Researchers at University of Missouri are developing software that allows drones to fly independently, perceiving and interacting with their environment while achieving specific goals. This technology has the potential to assist in mapping and monitoring applications, such as 3D or 4D advanced imagery for disaster response.
Researchers found that green spaces alleviate extreme heat's negative impacts on human health, while densely packed buildings increase mortality risk. Urban design strategies incorporating different types of greenery are recommended to mitigate heatwave-associated mortality.
A new project by JooYoung Seo at the University of Illinois School of Information Sciences aims to make data curation more accessible for everyone, regardless of abilities. The three-year grant will connect multimodal data representation with day-to-day reproducible workflows, enriching understanding and offering multiple perspectives.
Researchers found AI chatbot responses to top cancer queries are generally accurate but lack actionable information. These limitations suggest relying on chatbots for supplementary purposes rather than primary medical information.
Researchers identified 7 key symptoms of long COVID, including heart issues and joint pain, in a study of 52,461 patients. The findings could help healthcare providers diagnose and treat the condition more effectively.
A randomized clinical trial found that adding sugar warnings and prohibitions on front-of-package claims reduced parents' purchases of high-sugar beverages. However, percentage juice disclosures had no effect on behavior.
Following the leaked SCOTUS draft ruling, internet searches for abortion medication increased by 350,000 during the first week of May. These searches were more prevalent in states with restrictive reproductive rights.
A randomized clinical trial found that expanding common medical abbreviations increased overall comprehension, suggesting automated expansion can enhance patient understanding of their health information. Researchers observed significant improvements in patient comprehension after the expansion of 10 common medical abbreviations.
The HTRC will create a framework for researchers to build and implement their own tools to access the HathiTrust data more directly. The project aims to enable users to interact with the rich data extracted from the HathiTrust Digital Library's collection of over 17.5 million digitized volumes.
Omri Weinstein, assistant professor at Columbia University, has won a National Science Foundation CAREER Award to explore data structures and information retrieval. His research aims to develop new mathematical tools for proving lower bounds on data structure efficiency and scalable storage applications.
Research suggests that forgetting can increase long-term retention and information retrieval, ultimately enhancing learning. By changing context, forgetting can also enrich how information is encoded and retrieved.
A study of 150 U2 fan-made videos uncovered various visual and musical methods used to convey emotions, creating a sense of community among fans. The research may inform commercial music service providers on how to include emotional factors in recommendations and playlists.
Researchers at USC created an AI system called ASSA that can generate harmonious musical accompaniment in the style of a chosen artist. The system uses machine learning techniques to analyze melodic and harmonic patterns, allowing users to input their desired melody and receive an accompanying chord progression.