After a heart attack, a scar-forming activity can persist for months and contribute to heart fibrosis and later heart failure. Treatment with mesenchymal stromal cell-derived extracellular vesicles (MSC-EVs) reduced this process and limited harmful fibrosis beyond the damaged area. The study shows that MSC-EVs both reduce the scarring process and preserve heart function over time in a small-animal model, and that they have an acute cardioprotective effect in pig trials when administered directly into the coronary arteries.

α-linolenic acid (ALA), an essential omega-3 acid, is known to have anti-inflammatory and antioxidant properties and could help support cardiovascular health. Although perilla oil, which is widely consumed in South Korea, is composed of up to 70% ALA, its positive cardiovascular effects are underexplored. In a new study, researchers evaluate the effects of perilla oil supplementation on blood coagulation and inflammatory markers through a randomized double-blind, placebo-controlled, parallel group trial.

A recent study published in National Science Review has revealed global inequalities in lake water quality through the development of GlakeWQ, the first satellite–machine learning framework enabling consistent assessment across countries. Mapping 16,409 lakes in 145 countries, the framework shows that only about two-thirds of lakes meet sustainable water quality standards, leaving approximately 1.15 billion people exposed to potential water quality-related health risks and highlighting the urgent need for equitable freshwater management.

A research team from The Hong Kong University of Science and Technology (HKUST) has developed a novel AI framework, the Generalist–Specialist Collaboration (GSCo), which enables a generalist foundation model and specialist models to collaborate on disease diagnosis. GSCo outperforms both standalone models in tasks such as medical imaging, visual question answering, and radiology report generation, while significantly reducing development costs of medical models to adapt to new clinical tasks. This marks a meaningful step toward bringing AI medical models into everyday clinical workflows. The study, titled "Towards generalizable AI in medicine via Generalist–Specialist Collaboration," was published in the prestigious academic journal Nature Biomedical Engineering.

A new Perspective in Science Bulletin argues that AI tools for intracranial aneurysm detection should be evaluated beyond test-set accuracy. The authors propose a four-stage pathway covering lesion-level validation, reader performance, prospective implementation and post-deployment surveillance to assess whether AI can deliver real clinical benefit.