The study, published in Communications Medicine, combines magnetic resonance imaging and simulation-based artificial intelligence to speed up brain analysis while maintaining a high level of accuracy.

The method avoids the use of real patient data for training, reduces bias, and could facilitate the implementation of these advanced techniques in hospitals, helping to shorten waiting lists and improve diagnosis.

Researchers are increasingly using EEG (electroencephalography) to investigate how caffeine affects the brain during sleep — and findings suggest the issue goes beyond simply “falling asleep.” According to Prof. Donata Kurpas of Wroclaw Medical University, caffeine may reduce slow-wave activity, a key marker of deep, restorative sleep, even when sleep duration appears normal. EEG analyses reveal that the brain can remain in a more “wakeful” state overnight, potentially impairing recovery despite the subjective feeling of good sleep. Scientists also emphasize strong individual differences in caffeine sensitivity linked to genetics, metabolism, age, stress, and fatigue. The findings suggest that caffeine’s stimulating effects may contribute to a cycle of daytime fatigue and poorer nighttime recovery, highlighting the importance of sleep quality — not only sleep length — in understanding caffeine’s impact on health.

A new viewpoint article published in JMIR Mental Health argues that AI systems should evaluate the reliability of human training and feedback data to improve safety in mental health applications.

Artificial intelligence is rapidly changing how biomedical materials are discovered and designed. In a new review published in Science Bulletin, researchers summarize how machine learning and generative AI are helping scientists predict material behaviors such as drug release, biocompatibility, and catalytic activity, and even propose entirely new inorganic materials for biomedical applications. The review highlights emerging applications in drug delivery, cancer therapy, anti-inflammatory treatment, and tissue engineering, while also discussing the challenges that still limit clinical translation.

Researchers have proposed a new conceptual framework called “Health Elements” that positions digital technologies and AI as core structural drivers of health alongside biological, behavioral, social, and environmental factors. Published in Health Data Science, the framework argues that health outcomes emerge from dynamic interactions across multiple domains rather than from isolated risk factors alone. The study reflects growing recognition that digital systems—including algorithms, wearable devices, AI-enabled diagnostics, and health data infrastructures—are increasingly shaping health behaviors, access to care, and population-level outcomes.

The authors also discuss how multimodal health data integration, complex systems science, and AI-based analytical methods could support more adaptive public health and clinical decision-making. At the same time, they warn that algorithmic bias, digital inequity, and governance challenges may reinforce existing health disparities if ethical safeguards are not built into future digital health systems. An accompanying editorial describes the framework as a significant extension of traditional Social Determinants of Health models for the digital era.