A project led by the Germans Trias i Pujol University Hospital and Research Institute has developed an AI-based facial recognition system, AcroFace, capable of detecting early signs of acromegaly with 93% accuracy. The researchers are now conducting a larger pilot study with 4,000 images from the general population to confirm these promising results and improve early diagnosis of this rare disease.

A new review highlights major advances in bio-hydrovoltaic technology, marking a shift from traditional non-living materials to living biological systems that generate electricity through metabolic processes. This revolutionary energy approach offers self-regulation, environmental adaptability, and biodegradability, with strong potential in wearables, environmental monitoring, and distributed energy networks. Future directions include a “hydrovoltaic internet,” “hydrovoltaic intelligence,” and “hydrovoltaic ecology,” while key challenges remain in material stability, scalable manufacturing, and biosafety.

With a newly developed method that compares AI-generated protein sequences with naturally occurring ones, function- and structure-regulating amino acids can be determined much more precisely than before.

Biomarkers for predicting suicide risk in hospitalised patients with mental disorders have been understudied. Currently, suicide risk assessment tools based on objective indicators are limited in China. To examine the value of various biomarkers in suicide risk prediction and develop a risk assessment model with clinical utility using machine learning.

Innovative artificial muscles made from silicone and equipped with microbubbles can achieve programmable deformation in response to wireless ultrasound activation. Researchers at ETH Zurich have demonstrated an array of potential applications, from a gripper arm to stingray-inspired robots and tissue patches for use as drug delivery systems. While these uses remain limited to laboratory trials for the time being, the technology has potential uses in robotics and medicine.

Researchers at University of Tsukuba have developed a technology for real-time estimation of the valence state and growth rate of iron oxide thin films during their formation. This novel technology was realized by analyzing the full-wavelength data of plasma emission spectra generated during reactive sputtering using machine learning. It is expected to enable high-precision control of the film deposition process.