EurekAlert! News by Subject: Tech & Engineering - News by Subject: Tech & Engineering

Tech & Engineering

Updates every hour. Last Updated: 17-Aug-2025 22:11 ET (18-Aug-2025 02:11 GMT/UTC)

Machine learning can predict which babies will be born with low birth weights

Fundação de Amparo à Pesquisa do Estado de São Paulo
Peer-Reviewed Publication

The evaluation of predictive models for low birth weight cases was based on data from a population study of over 1,500 pregnant women in the city of Araraquara in the state of São Paulo, Brazil. Early identification of the problem is crucial for effective intervention.

Journal: BMC Pregnancy and Childbirth
Funder: Fundação de Amparo à Pesquisa do Estado de São Paulo

AI detects hidden heart disease using existing scans stored in patient records

Mass General Brigham
Peer-Reviewed Publication

Researchers at Mass General Brigham, in collaboration with the U.S. Department of Veterans Affairs (VA), developed an AI tool called AI-CAC that analyzes routine chest CT scans to identify individuals at risk for cardiovascular events by detecting coronary artery calcium (CAC). The tool, shown to be highly accurate and predictive of 10-year mortality, could enable earlier intervention and help repurpose millions of existing CT scans for proactive heart disease prevention.

Journal: NEJM AI
Funder: United States Department of Veterans Affairs (VA)

PFAS-eating bacteria discovered in Veneto soil

Universita Cattolica del Sacro Cuore
Meeting Announcement

A study from Catholic University, Piacenza, on the forever chemicals that threaten the human and planet health

AI could accelerate protein engineering – key for developing new medicines

University of Sheffield
Peer-Reviewed Publication

An AI approach developed by researchers from the University of Sheffield and AstraZeneca, could make it easier to design proteins needed for new treatments.

Journal: Nature Machine Intelligence

New material behavior to improve speed and efficiency of technology

University of Minnesota
Peer-Reviewed Publication

In a new study, researchers at the University of Minnesota Twin Cities discovered surprising magnetic behavior in one of the thinnest metallic oxide materials ever made. This could pave the way for the next generation of faster and smarter spintronic and quantum computing devices.

Journal: Proceedings of the National Academy of Sciences
Funder: DOE/US Department of Energy

ELSI’s challenges in the era of advanced AI

Chuo University
Meeting Announcement

Chuo University ELSI Center and The University of Osaka established the Research Center on Ethical, Legal and Social Issues (The University of Osaka ELSI Center) jointly hosted the "University ELSI Summit", a two-day event held on March 15^th and 16^th, 2025 (Saturday-Sunday) at Chuo University's Korakuen Campus (Bunkyo-ku, Tokyo, Japan).

ELSI (Ethical, Legal and Social Issues) and RRI (Responsible Research and Innovation) are seeing rapid development globally. These approaches are being examined across various fields both domestically and internationally. The ELSI University Summit focused on ELSI and RRI initiatives in academia and industry. These initiatives concentrate on research areas related to advanced AI and social challenges. The summit included reports from multiple stakeholders responsible for development, utilization, and regulation — including the business community, government agencies, educational institutions, science and engineering researchers, and humanities researchers. In addition, through Q&A sessions and panel discussions, the summit engaged in intensive discussions about their respective roles and the importance of collaboration. The event attracted a total of 607 on-site participants and online ones.

MHP-Net: A revolutionary AI model for accurate liver tumor segmentation for diagnosis and therapy

Institute of Science Tokyo
Peer-Reviewed Publication

Signaling a major advance in small-data AI for medical imaging, a research team from Institute of Science Tokyo has developed a novel artificial intelligence model called “MHP-Net,” which delivers cutting-edge performance in liver tumor segmentation with a limited dataset. Unlike conventional models that require thousands of patient cases, this model uses sampling of 3D patches obtained from 7 to 28 tumors. Also, it outperforms the top entry of the MICCAI 2017 (worldwide liver tumor segmentation competition).

Journal: IEEE Access
Funder: JST-Mirai Program