A research team has mapped how artificial intelligence is beginning to reshape cardiac arrest care, from early warning and emergency response to cardiopulmonary resuscitation and recovery after survival. By reviewing 114 studies involving more than 9.57 million patients, the study shows that artificial intelligence is most often used to predict cardiac arrest, guide resuscitation decisions, and estimate post-arrest outcomes. The findings suggest that artificial intelligence could become a practical tool for identifying high-risk patients earlier, supporting time-critical decisions during resuscitation, and improving post-arrest care, while also highlighting the need for stronger real-world validation before these tools can be widely adopted in emergency medicine.

A research team led by Drs. Byung-Yong Yu and Gwan-Ho Lee at the Advanced Analysis and Data Center of the Korea Institute of Science and Technology (KIST; President Sang-Rok Oh) announced that it has developed a new analytical platform that can precisely measure the accumulation of fine particulate matter in individual organs, overcoming the limitations of existing analytical technologies.

Researchers publishing in Computational Biomedicine have developed a novel artificial intelligence framework that improves epileptic seizure prediction by combining bidirectional long short-term memory networks with a channel attention mechanism. The study highlights how interpretable deep learning models may help identify critical preictal EEG patterns and support the development of more reliable seizure prediction systems.Researchers publishing in Computational Biomedicine have developed a novel artificial intelligence framework that improves epileptic seizure prediction by combining bidirectional long short-term memory networks with a channel attention mechanism. The study highlights how interpretable deep learning models may help identify critical preictal EEG patterns and support the development of more reliable seizure prediction systems.

A study finds that “preparing” biochar through composting can make it far more effective for improving soil fertility and boosting plant growth.

A study has captured, in real time and in three dimensions, how a single piece of biomass changes as it is heated into biochar, offering fresh clues for designing more effective carbon materials for water cleanup, soil improvement, catalysis, and climate-related applications.

Researchers publishing in Computational Biomedicine have developed a novel artificial intelligence framework, MIGDTA, that integrates graph neural networks and multi-source biological information to enhance drug–target affinity prediction. The study highlights how combining molecular structure, biological descriptors, and interaction networks could accelerate drug discovery and repositioning.

A new study outlines a comprehensive framework leveraging AI and big data to combat illegal plant trade, addressing global biodiversity threats with technological innovation.

Numerical simulation is essential for predicting how complex mechanical systems move, from robots and vehicles to deployable aerospace structures.

Microplastics are now found across oceans, soils, food chains, and even human biological samples. Yet scientists still face a major challenge: these tiny particles are difficult to detect, track, and link to health risks using traditional laboratory methods alone. A new perspective article argues that artificial intelligence could help change that.