The Home Health Focus dataset provides insights into Medicare home health use from 2016 to 2019, including demographic data and patient function indicators. The analysis shows a rise in home health stays among beneficiaries while a decrease in active agencies during the same period.
The algorithm identifies the minimum set of locations where field studies would guarantee finding the least expensive route, considering problem structure and uncertainty. This method can be applied to broad classes of structured decision-making problems under uncertainty.
Pusan National University researchers develop a novel prompting technique to improve ChatGPT's accuracy in predicting fashion trends. The study reveals that ChatGPT can capture emerging themes and identify new trends not found in existing data.
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.
The Global Pathogen Analysis Platform (GPAP) will enable low- and middle-income countries to conduct research and surveillance of infectious diseases independently. The platform aims to prevent disease outbreaks from developing into pandemics by detecting genetic sequences of potential pathogens.
The African Data Drive is an interactive tool that provides accessible, quality-assured spatial data to empower decision-makers to balance development needs with conservation priorities. The platform enables users to assess potential risks to biodiversity and access the most appropriate information on sustainable development.
A new project aims to enhance workforce readiness in molecular bioscience by creating open-access resources and modules tailored to student needs. The Molecular Data Education Hub will host instructional materials and case studies for instructors to implement into their courses.
The Variant Workbench enables researchers to explore genetic data in a single, integrated workspace, linking genomic information with clinical conditions. By reducing data complexity, the tool facilitates scientific discovery and accelerates pace of research.
Researchers at the University of Missouri have developed an AI-powered method to detect hidden hardware trojans in chip designs, offering a 97% accurate solution. The approach leverages large language models to scan for suspicious code and provides explanations for detected threats.
Frontiers' revolutionary AI-powered FAIR² Data Management service is transforming the way scientific data is shared, enabling researchers to fuel progress and earn credit for their work. The service ensures every dataset is preserved, validated, citable, and reusable.
The BIRDBASE dataset covers 78 ecological traits across 11,589 bird species, revealing that 54% are insectivores, with many tropical forest species under pressure. Fruit-eating birds disperse seeds in tropical forests, and fish-eating seabirds face elevated extinction risk.
A new framework for flexible data collection has been developed by Masumi Hisano, allowing for counts to take place in various settings, including cities and daily routines. This approach can help increase sample size and provide valuable insights into bird species assemblage datasets linked to landscape characteristics.
Researchers developed Vesalius to interpret complex data on cancer cell interactions, leading to potential discoveries in treating hard-to-treat cancers. The tool analyzes whole tissue architecture to identify predictive biomarkers and inform treatment options based on individual disease types.
The Intelligent Data Exploring Assistant (IDEA) framework combines large language models with scientific data to analyze complex geoscience data. Researchers can ask IDEA to retrieve data, run analyses, and generate plots using plain-language questions.
Researchers created a large-scale mouse behavior dataset to study complex behaviors like problem-solving and goal-directed actions. The dataset, featuring over 100 hours of footage and detailed human annotations, provides a benchmark for developing algorithms that analyze animal cognition.
A new dataset has been developed to study climate change in the Arctic Ocean. The dataset spans from 1900 to 2100 with high resolution, offering a more accurate understanding of the region's changing climate. It significantly reduces simulation errors and improves representation of key variables.
Researchers found that billing codes may mistakenly identify diseases in up to 45% of cases, highlighting a significant limitation in using administrative data for clinical research. The study examined records of 1.36 million patients and found discrepancies between coded diagnoses and actual disease presence.
Answer ALS is launching a groundbreaking collaboration with Tulane University and the Pennington Biomedical Research Center to harness AI for ALS treatment discovery. The Louisiana AI Drug Development Infrastructure for ALS (LADDIA) will prioritize therapeutic targets using AI-driven insights from the Answer ALS' Neuromine Data Portal.
A conclave of paleontologists, data scientists, and journal editors will meet in Kansas to improve how data is shared among professionals and beyond. The event aims to align paleontological data with FAIR practices, making it easier for researchers to access and reuse.
Researchers from Sapiens Labs created two ongoing data acquisition programs in India and Tanzania to collect large-scale, high-quality neuroimaging data. The programs have collected data from over 7,900 participants with comparable data quality to lab settings and lower costs.
The joint policy brief from four EU projects aims to guide successful implementation of the Green Deal Data Space. It recommends standardised data exchange technologies, inclusive governance frameworks, and metadata management to unlock Europe's full potential in environmental data.
Gene coexpression analysis reveals optimal markers of cell types and states, providing opportunities for developing novel biomarkers and targeted treatment strategies for glioma patients. Dr. Oldham's work tackles the reproducibility crisis in science, emphasizing data metadata standardization.
A research team developed an analytical model to evaluate the performance of grant-free communications schemes in densely populated IoT environments. They found that interference cancellation improved base station throughput but did not resolve the near-far problem, while power control addressed it but led to decreased overall network ...
Researchers have developed an open-access catalog of animal traditions to explore the role of social learning in shaping animal behavior. The Animal Culture Database features vocal communications, mating displays, play, and other social behaviors observed in dozens of species from around the world.
BingoCGN accelerates real-time large-scale graph neural network inference through cross-partition message quantization and a novel training algorithm, achieving up to 65-fold speedup and 107-fold increase in energy efficiency compared to state-of-the-art accelerators.
Researchers found that partial peace agreements play an important role in building trust and strengthening relationships between negotiators. These agreements offer strategic advantages, including consolidating incremental progress, serving as metrics, testing measures, and signaling a larger commitment to the peace process.
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.
Scientists from University of Leicester collaborate with traditional Amazonian communities to monitor biodiversity using artificial intelligence, enabling them to maintain control over their resources and territories. The project aims to reshape conservation approaches in the world's largest tropical rainforest.
Scientists at MIT have identified new potential targets for treating Alzheimer's disease, including a pathway involved in DNA damage repair. The study suggests that a combination of treatments targeting different cellular pathways may be more effective in blocking disease progression.
A new study by University of Cincinnati researcher Edson Chipalo found that children who experienced adverse childhood experiences are at a higher risk of homelessness during their childhood. The study highlights the need for prevention and early support to reduce long-term risks associated with childhood trauma.
A centralized and accessible database aims to integrate molecular simulation data, ensuring findability, accessibility, interoperability, and reusability. This will amplify the impact of these data and avoid duplication.
Researchers developed a new model called React-OT that can predict the transition state of chemical reactions in under a second with high accuracy. The model uses linear interpolation to generate better initial guesses, reducing the number of steps and computation time needed.
A novel method generates binary class labels in highly imbalanced datasets, addressing the challenge of labeling severely imbalanced data. The approach outperformed traditional methods, providing a more efficient way to identify fraud while minimizing false positives.
MIT researchers have found that a computational model of the ventral stream, which processes object recognition, also performs well on spatial tasks such as determining an object's location and orientation. This challenges the dominant perspective that the ventral stream is optimized for object recognition.
Researchers developed a new framework, PAC Privacy, to maintain AI model accuracy and ensure sensitive data remains safe from attackers. The new variant of PAC Privacy estimates anisotropic noise, reducing computational cost and boosting accuracy.
A recent study from UTSA researchers reveals that large language models (LLMs) can pose a serious threat to programmers who use them to help write code. The study found that up to 97% of software developers incorporate generative AI into their workflow, and 30% of code written today is AI-generated.
Researchers found that sleep duration returns to baseline within two days, but changes in sleep timing and structure can take more than a week, with eastward travel causing the most disruption. The study analyzed 1.5 million nights of data from wearables like Oura Ring.
Researchers will use sensors and software to predict AM part lifespan, enabling cost savings and extending part life. The project aims to improve Darwin software to provide detailed insights into manufacturing processes.
The C-Path-led initiative brought together clinical trial sponsors, eCOA technology providers, and regulators to identify and address eCOA implementation issues. Key resources developed during the initiative include guidance on COA data collection and a more open, collaborative environment.
The new DESI results show that the impact of dark energy may be weakening over time, suggesting a fundamental shift in how we think about dark energy. The collaboration's findings are consistent with other measurements, including supernovae and the light left over from the dawn of the universe.
The Euclid data release unlocks a treasure trove of information for scientists to study the universe's cosmic history and invisible forces. With its exceptional field of view, Euclid captures an area 240 times larger than the Hubble Telescope, delivering outstanding image quality in both visible and infrared light spectrum.
Researchers highlight the underuse of Japanese bird banding data in avian movement research, revealing gaps in our understanding of East Asian migratory birds. The study proposes improving data accessibility and integrating traditional methods with modern tracking technologies to advance conservation efforts.
A new study from Aalto University found that global population datasets may underestimate rural populations by as much as 53% to 84%, revealing a systematic and profound extent of the bias. The findings have far-reaching consequences, suggesting that the needs of people living in rural areas have been under-represented in decision-maki...
A new study shows that climate change affects short-term precipitation events lasting hours by significantly increasing their frequency, while longer-term rainfall events lasting days are influenced by global weather phenomena like El Niéo. This distinction is crucial for assessing the risk of flooding in different regions.
Researchers have developed a novel technique to overcome the spurious correlations problem in AI by eliminating a small portion of the training data that contains hard-to-understand features. This approach improves performance even when conventional techniques are ineffective.
A recent USC study found that Black immigrants in the United States have a 9% higher likelihood of being uninsured compared to U.S.-born white adults, despite having a 70.2% employment rate. The disparity is attributed to wage penalties and systemic barriers related to race and immigration status.
FAIR² Data Management leverages AI-assisted curation to structure research data for publication, enhancing research efficiency and reproducibility. The platform transforms data into a tool for discovery, tackling pressing challenges in global health, sustainability, and scientific innovation.
Researchers at Trinity College Dublin have discovered a biomarker panel that can accurately identify patients at risk of developing pancreatic cancer, offering new hope for early detection and improved treatment. The study uses a combination of blood and fluid analysis to distinguish between low- and high-risk patients.
A new standard dataset defines 16 clinical and patient-reported outcome measures for adults with heart valve disease. The International Consortium for Health Outcomes Measurement (ICHOM) developed the globally inclusive standard dataset.
The release of a unique Type Ia Supernovae dataset has significant implications for cosmologists measuring the universe's expansion history. The dataset, comprising 3628 supernovae, provides unprecedented precision and accuracy in exploring the properties of these events.
Researchers generated a dataset of water flow beneath the entire Antarctic Ice Sheet, improving projections of sea level rise. The model predicts higher degrees of glacier melt and mass loss by the end of the century.
A new method developed by Osaka Metropolitan University accurately predicts housing prices in Osaka City, with neighborhood perception being a key factor. The approach achieves nearly 75% accuracy by combining existing property data with machine-learning-processed street view images.
A new study found that hotter and colder regions on a star's surface can distort our interpretations of planets, particularly when looking at dips in starlight. This distortion can lead to misinterpretation of features such as planet size, temperature, and atmospheric composition.
InsectNet uses machine learning to identify over 2,500 insect species at 96% accuracy, providing critical information for farmers and researchers. The app can be fine-tuned for specific regions, making it useful for agricultural challenges worldwide.
The International Society for Health and Lung Transplantation (ISHLT) has re-launched the Global IMACS Registry to collect data on patients with durable mechanical circulatory support devices. The registry aims to advance MCS therapy and improve patient outcomes globally.
Two comprehensive datasets from the Gabriella Miller Kids First Pediatric Research Program explore childhood cancers and congenital disorders. The new datasets aim to identify genetic causes and links between these diseases in children, ultimately supporting the development of improved treatments.
A new computational tool, PsiPartition, simplifies genetic data analysis for evolutionary biology, allowing researchers to efficiently study species relationships. The novel method improves both computational efficiency and accuracy of phylogenetic trees.
Researchers at University of Birmingham have discovered three new protein biomarkers TFF3, LCN2, and CEACAM5 that show strong predictive potential for colorectal cancer. These biomarkers are linked to cell adhesion and inflammation, processes closely associated with cancer development.
A new 6D pose dataset has been introduced, providing high-quality RGB and depth images with annotated 6D pose data. This dataset achieves state-of-the-art accuracy rates of 97.05% and 98.09% for robotic grasping and automation applications.
A team led by the University of Tokyo has created a nearly 20-year-long dataset of the entire atmosphere, enabling new research on previously difficult-to-study regions. The dataset spans multiple levels of the atmosphere from ground level to the lower edge of space and could improve climate modeling and seasonal weather forecasting.