Predicting whether a healthy 45-year-old will struggle to climb stairs or walk a decade later has long been a challenge for geriatric medicine. Now, a study published in JMIR Aging, a leading open access journal from JMIR Publications, reveals that early mobility decline can be predicted using a simple set of home-based measurements and artificial intelligence.

A new study published in Big Earth Data develops a stochastic random forest (RF) classifier to predict extreme wind-gust (WG) occurrences along the western Mediterranean coast by integrating instantaneous and trailing 24-hour meteorological variables across multiple height levels, enabling the model to capture both short-term evolution and immediate atmospheric forcing. It demonstrates strong forecasting performance with high precision, low false-alarm rates, and reliable uncertainty estimation, while identifying barometric-pressure tendencies and humidity as key predictors, highlighting the framework’s potential for early-warning systems, climate resilience, and disaster-risk management. UERRA reanalysis data can be downloaded from the Copernicus Climate Data Store platform: https://cds.climate.copernicus.eu/. Supplementary materials supporting the findings of this study are openly accessible at the public GitHub repository: https://github.com/AI4OCEANS/.

A new national study reveals just how deeply AI chatbots are shaping teen life – and the hidden dangers that may come with them. Surveying more than 3,400 adolescents nationwide, researchers found many teens turn to chatbots not only for entertainment, but also for emotional support, advice, friendship and romantic companionship. Nearly half reported harmful experiences, including manipulation, misinformation and risky interactions, raising urgent questions about safeguards as AI becomes woven into adolescence.

Shanghai, China, May 12, 2026 --- Insilico Medicine ("Insilico", 03696.HK), a biotechnology company powered by generative artificial intelligence, today announced that the company has entered a strategic collaboration agreement with Suzhou Ribo Life Science Co., Ltd.  ("Ribo", 06938.HK), a globally leading clinical-stage company in oligonucleotide therapeutics. Building upon the automation, intelligence and scalability capabilities of Insilico's LifeStar 2 laboratory, the two parties will further deepen the existing experimental service cooperation, combining the end-to-end R&D capabilities of Insilico's proprietary Pharma.AI platform with Ribo's profound expertise in oligonucleotide therapeutics development, aiming for comprehensive efficiency boost in the oligonucleotide drug R&D cycle.

Modern optical sensors passively collect data, which is then exported for analysis. Researchers at Texas A&M University are developing optical sensors that can compress and analyze their own data, saving time, money and energy.

A team of international researchers led by senior lecturer Åsa Mackenzie at Lund University has received a $9 million USD grant from the Aligning Science Across Parkinson’s (ASAP) initiative, in partnership with The Michael J Fox Foundation for Parkinson’s Research (MJFF), to advance understanding of Parkinson’s disease treatment, with a particular focus on depression, anxiety, and other psychiatric and cognitive symptoms, with the aim of informing more targeted treatment approaches.

Proteins change shape as they function, and these changes are essential for processes such as drug interactions and cellular activity. Researchers from the Tokyo University of Science developed an AI-based method called DeepAFM that is trained on millions of simulated images representing different protein states, accurately identifying transitions between closed and open states in a protein called SecA. This approach highlights the growing potential of AI to solve complex challenges in biology and medicine.