Research on making sense of scientific and medical data. Covers AI error-correction, single-cell search engines, optical computing, and measurement reliability.
Studies show that patients with advanced ovarian and metastatic breast cancer dedicate approximately 7 hours per week to cancer-related tasks. Most participants report performing these tasks daily, impacting their time burden. The use of a mobile app facilitated the collection of detailed time-use data.
Researchers have launched a new multimodal medical dataset, Observer, capturing anonymized, real-time interactions between patients and clinicians. The dataset links video, audio, transcripts, and electronic health records to study subtleties like body language and environmental factors affecting care.
Researchers at UT Health Sciences Center have developed an AI-enhanced platform called ENRICH, which leverages advanced analytics with community-based human support to reduce treatment interruptions and improve cancer outcomes. The program identifies patients at highest risk for interruption and deploys targeted support resources.
A study analyzed large-scale human ChIP-seq data to identify unmeasured transcription factor-tissue/cell type pairs, revealing significant gaps in current knowledge. These findings indicate that essential regulatory mechanisms may have been overlooked, emphasizing the need for strategic prioritization of measurement targets.
A new study reveals that Normalized Mutual Information (NMI), a widely used metric for algorithm performance, can produce biased results. The researchers developed an asymmetric, reduced version of the mutual information metric to eliminate biases and improve comparison across fields.
A new study found that highly educated, Western European millennials have the most digital concerns, with individuals having higher levels of digital literacy being the most affected. The research also found that people's perceptions of digital harm are heightened by their level of digital exposure and knowledge.
A new study maps three decades of income inequality data globally, revealing worsening trends for half the world's population but 'bright spots' in regions with effective policies. Regional efforts such as investments in public health and education in India and cash transfer programs in Brazil show promise in reducing inequality.
A comprehensive analysis of 383 US cities found common patterns of isolation and segregation, with wealthy suburban areas and poorer downtown zones often having limited interactions between residents. Researchers recommend zoning incentives and strategic development to encourage greater diversity and social mixing.
Exposure to single and mixtures of perfluoroalkyl substances (PFAS) was associated with higher odds of endocrine disruption (ED) among women. Certain PFAS compounds, particularly n-PFOS, were found to disrupt endocrine function and harm health.
Researchers at Tokyo University of Science propose approximate domain unlearning (ADU) algorithm, which differentiates between domains while preserving generalization capability. This approach enables flexible AI configuration suited to individual practical scenarios.
University of Missouri researchers are combining in-home sensor technology with artificial intelligence to monitor daily changes in ALS patients' health. The system uses machine learning to estimate a patient's score on the ALS Functional Rating Scale Revised, predicting potential problems before they occur.
Researchers explore ways to understand and control multiple errors affecting machine tool accuracy, combining traditional models with data-driven approaches and digital twin technology. This enables more integrated systems that can monitor themselves, predict changes, and adjust behavior automatically.
A team of researchers has developed a detailed open map of emerging technologies, grouping 23,000 plus technologies into a multi-level map. The Cosmos 1.0 framework uses machine learning to analyze Wikipedia pages, books, and patents.
Withdrawal of tirzepatide after 36-week treatment led to 25% or greater weight regain in most participants within a year, reversing initial cardiometabolic parameter improvements. Continued obesity treatment is crucial for sustained benefits.
A cross-sectional study found that US population faces significant challenges with nervous system disorders, impacting 180.3 million people, mainly due to stroke, Alzheimer's disease, diabetic neuropathy, and migraine conditions.
Researchers identified a targeted drug that blocks a specific genetic pathway to reverse tumor-driving cellular interactions, potentially restoring DNA function and benefiting patients with synovial sarcoma. The study's findings endorse a promising strategy to improve outcomes for this rare but deadly cancer.
Approximately 1 in 30 clinical trials were disrupted due to grant funding terminations, disproportionately affecting infectious disease and prevention studies. The study emphasizes the need for sustainable financial support to ensure trial operations and participant safety.
Rapid rise in early measles vaccination observed in February 2025, ahead of CDC guidelines. The study suggests clinician and parental concern drove increased vaccination rates.
A study found that higher consumption of ultraprocessed foods is associated with an increased risk of developing early-onset colorectal cancer precursors. The research highlights the importance of improving dietary quality to mitigate the rising burden of early-onset colorectal cancer.
A recent FAU Engineering study leverages quantum computing to enhance the accuracy of chronic kidney disease (CKD) diagnosis. The research team developed and compared two automated systems: Classical Support Vector Machine (CSVM) and Quantum Support Vector Machine (QSVM). CSVM achieved remarkable 98.75% accuracy, while QSVM reached 87....
A recent study finds that artificial intelligence has a negligible effect on global greenhouse gas emissions. The researchers' analysis of US energy consumption and AI use across industries revealed that the energy usage from AI in the US equals the energy consumption for all of Iceland, but not noticeable on a global scale.
Researchers developed CellWhisperer, an AI method and software tool that links gene expression with descriptive text across millions of biological samples. It provides a virtual AI-based colleague to support biologists in their research, making biomedical data exploration easier and more exciting.
Researchers developed a novel topology-aware multiscale feature fusion network to enhance EEG-based motor imagery decoding. The TA-MFF network achieves excellent classification performance, outperforming state-of-the-art methods by leveraging spectral-topological data analysis-processing and inter-spectral recursive attention.
The FAU College of Engineering and Computer Science has established the 'Ubicquia Innovation Center for Intelligent Infrastructure' to develop transformative technologies. The center will empower students and faculty to create AI-First solutions for a smarter, more connected world.
Researchers from The University of Osaka developed MicroAdapt, a groundbreaking self-evolving edge AI technology that enables real-time learning and forecasting capabilities within compact devices. It achieves up to 100,000 times faster processing and 60% higher accuracy compared to state-of-the-art deep learning methods.
A new study by the University of Ottawa exposes how video game studios are violating children's privacy rights. Researchers analyzed 139 privacy policies and found none fully comply with existing legal frameworks.
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.
Optical computing harnesses light to accelerate feature extraction in AI applications. The new system, OFE2, achieves a 12.5 GHz operating rate and 250.5 ps latency, outperforming traditional digital processors.
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.
A new study by Mass General Brigham researchers found that daily step counts of 4,000 or more are associated with a 26% lower mortality risk and 27% lower cardiovascular disease risk in older women. The study suggests that even sporadic high-intensity exercise can have significant health benefits.
A low-cost smartphone imaging system called mDOC combines autofluorescence and white light imaging with machine learning to accurately identify oral lesions requiring specialist referral. The system achieved an area under the ROC curve of 0.778, outperforming dental providers in sensitivity and specificity.
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.
A study published in JAMA found that both low and high increases in social media use during early adolescence are negatively associated with cognitive function. Specifically, adolescents with higher or lower social media use tend to perform poorly in certain aspects of cognition.
A new study found that COVID-19 work absences have become a year-round phenomenon in the US labor market, similar to pre-pandemic influenza season conditions. Nationally representative data can help monitor public health crises and inform policy decisions.
The research team's Cord-Approx strategy coordinates drivers to assign different street parking spots using statistical predictions and an optimal matching algorithm. This approach significantly reduces parking search time, with drivers finding a spot in 6.7 minutes on average.
Researchers found that the addition of new hierarchical layers occurred neither at the start nor end of growth periods, but rather smoothly as firms expanded. Smaller firms tend to add layers soon after growth begins, while larger firms have lower levels of managerial resources at the end of growth periods.
A prospective cohort study found that young adults experiencing unfavorable patterns of cardiovascular health are at a marked increased risk for incident cardiovascular disease. Achieving and maintaining high cardiovascular health throughout young adulthood is crucial for preventing later-life cardiovascular disease.
Researchers developed a novel spectroscopic approach to precisely analyze molecular interfaces at material surfaces. The technique uses gap-controlled infrared absorption spectroscopy, combining conventional ATR-IR with advanced data analysis, allowing for the isolation of interfacial molecular signals.
A large-scale study uncovered a strong connection between osteoporosis and rotator cuff tears, finding that individuals with osteoporosis are 1.56 times more likely to suffer an RCT. The study also identified common genetic variants influencing both conditions, suggesting a possible biological explanation for the link.
A new guide has been launched to help tackle the growing threat of technology-facilitated domestic abuse against older people. The resource highlights practical ways to prevent and respond to digital forms of abuse, including how to secure access to bank accounts and lock smart devices.
A new 'future-guided' AI method developed at the University of California, Santa Cruz, has shown significant improvements in predicting seizures using brain wave data. The technique operates with two deep learning models working together, improving predictions further into the future by transferring knowledge.
Researchers have discovered myeloid cells in children's liver tumors that could be activated for treatment. This discovery provides new avenues for immunotherapy in childhood liver cancer.
A study by University of Arizona researchers found that selecting the right data for flood insurance can significantly improve accuracy, speed, and predictability. The type of data used affects not only payout timing but also confidence in anticipating future payouts, influencing program costs.
A new study suggests that low-dose aspirin can prevent cancer in older adults based on individual characteristics. The analysis found varying treatment effects among participants, highlighting the need for personalized approaches to cancer prevention.
Dr. Andreea Creanga, a leading maternal health expert, joins the University of Maryland School of Medicine as Chair of the Department of Epidemiology and Public Health. She will oversee initiatives in bioinformatics, data science, and maternal health.
A new study challenges conventional assumptions about urban healthcare advantages by revealing that larger cities have proportionally fewer specialists per resident than smaller ones. Smaller cities often serve more patients per specialist, with some specialties like addiction medicine showing significant disparities in availability.
A systematic review and meta-analysis of 18 trials found GLP-1 RAs significantly improved glycemic and weight outcomes in children and adolescents with type 2 diabetes or obesity. However, gastrointestinal adverse effects warrant attention in long-term management.
A retrospective cohort study found that children of racial and ethnic minority groups receiving CPR had higher odds of in-hospital mortality. Additionally, the odds of in-hospital mortality among children receiving CPR were higher at hospitals with the highest proportion of Black patients.
Researchers are decoding animal decision-making using glass knifefish, exploring the trade-off between gathering information and acting on it. The study, funded by the NIH, aims to understand how animals make decisions in uncertain environments and may lead to breakthroughs in robotics and medicine.
Researchers developed a method to identify causal relationships between neurons solely based on spike train data, providing a new tool for understanding brain connectivity. The approach accurately detected bidirectional and unidirectional coupling between neurons, even in the presence of internal noise.
The new STROBE-Equity extension provides a framework for researchers to report health equity data and considerations in observational studies. This improved reporting can help knowledge users better identify and apply evidence relevant to populations experiencing inequities.
The study reveals data visualization primarily facilitates decision-making at the organizational and community levels, particularly for semi-structured problems. Recent trends indicate increasing support for broader types of decision-making, including individual-level and unstructured problems.
ConcreteSC technology achieves significant speed boosts and improved efficiency in next-generation wireless networks. The innovation integrates user tasks into communication processes, reducing computational complexity and increasing semantic meaning.
A new study introduces an optical imaging technique that uses autofluorescence to detect colorectal cancer in real time, offering a promising tool for improving cancer detection during endoscopic procedures. The technique achieved high accuracy rates and the potential to guide doctors during colonoscopy or surgery.
Researchers developed a machine learning model that accounts for biological variability to identify optimal formulations for serum-free culture media. The model achieved approximately 1.6-fold higher cell density compared to commercially available products.
A cohort study found a higher prevalence of eating disorders among adolescents from lower socioeconomic backgrounds. The study suggests that reducing population-level socioeconomic inequalities may aid in preventing eating disorders.
MIST uses a hierarchical, rules-based classification system grounded in verified mineral formulas from the RRUFF mineral database. It accurately identifies hundreds of different mineral species from their chemical composition, even accounting for natural imperfections and vacancies found in real minerals.
Astronomers have developed a protocol to detect supernovae within 24 hours of their explosion, using high-cadence sky surveys. The method involves rapid searches for candidates based on light signal absence and galaxy location, followed by spectroscopic observations to determine the type of supernova.