A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms—addressing a critical issue that can affect diagnostic accuracy and treatment decisions. The findings were published in the September 4 online issue of the Journal of Medical Internet Research [DOI: 10.2196/71757]. To tackle the problem, the investigators developed AEquity, a tool that helps detect and correct bias in health care datasets before they are used to train artificial intelligence (AI) and machine-learning models. The investigators tested AEquity on different types of health data, including medical images, patient records, and a major public health survey, the National Health and Nutrition Examination Survey, using a variety of machine-learning models. The tool was able to spot both well-known and previously overlooked biases across these datasets.

Korea University College of Medicine hosted the K-CLUB (Korea Club for Leading-edge University Biomedical-science) International Symposium at the SK Future Hall on the university’s Seoul campus in Seongbuk District, bringing together distinguished global scholars for an in-depth examination of “Health for Humanity.”

Ultra-flat, featherlight, and compact – these are the hallmarks of the next-generation cooling units being developed by Professor Paul Motzki at Saarland University. Backed by a prestigious ERC Starting Grant from the European Research Council, Motzki is pushing the boundaries of elastocaloric technology – a cutting-edge, climate-friendly method of cooling and heating – by combining two breakthrough smart material systems. This marks the third major success for Paul Motzki in just two years in the EU’s Horizon Europe research and innovation programme. He has already secured an EIC Pathfinder grant for visionary technologies and is also involved in a multimillion-euro EU cluster project.

Scientists at UCL, Google DeepMind and Intrinsic have developed a powerful new AI algorithm that enables large sets of robotic arms to work together faster and smarter in busy industrial settings, potentially saving manufacturers hundreds of hours of planning time and unlocking new levels of flexibility and efficiency.

The University of Bonn has yet another good reason to celebrate as three of its researchers have been awarded an ERC Starting Grant worth €1.5 million each. This European Research Council (ERC) grant program is designed to support early-career researchers. The economist Assistant Professor Amelie Schiprowski, the computer scientist Professor Lucie Flek and the evolutionary biologist Dr. Moritz Lürig will use the funding to progress their own research projects over the next five years.

Sweat-based enzyme sensors offer a convenient way to measure lactic acid levels in the body, but face challenges due to the loss of lactate oxidase (LOx) activity in sweat. Now, researchers from Japan have improved LOx stability by adding sucrose monolaurate, a sugar-based surfactant, that when added to the electrode forms protective nanostructures around the enzyme. Their approach could enable more durable and accurate sweat lactate sensors for sports training management and continuous health monitoring.