The new tool recognizes bacterial DNA in tiny genetic fragments, making it faster and easier to study the complex communities living in soil.

This study reviews the use of 3D printing in orthodontics, with the focus mainly on future implications given current information. Sustainability in materials and processes is a major component, as the workflow streamlined by the 3D printing process and artificial intelligence may prove to be negated depending on a few components. The volume in manufacturing, appliance type and the necessary improvements needed in materials and material efficiency will be determining factors for the method’s sustainability and future clinical usage.

A new study has found that almost one in three Israeli adults surveyed who use generative artificial intelligence (AI) tools reported seeking emotional support, coping advice, or mental health assistance from platforms such as ChatGPT and Gemini. Among users experiencing severe psychological distress, that figure rose to nearly one in two, according to researchers from Tel-Hai University of Kiryat Shmona in the Galilee and collaborating institutions.

75 years after Rosalind Franklin’s pioneering work, Oxford chemists have used machine learning simulations to reveal how hard carbon forms at the atomic scale.

The simulations reveal why some carbon resists forming graphite: as a common packaging polymer (PVDC) breaks down, reactive carbon sites link together, forming five- and seven-membered rings that disrupt the formation of ordered graphite layers.

With hard carbon emerging as a key material for sodium-ion batteries, the findings show how machine learning can unlock the atomic-scale processes behind complex materials, paving the way for more targeted material design.

Accurate diagnosis of diabetic nephropathy (DN) typically requires invasive kidney biopsies. In a recent Chinese Medical Journal study, Chinese researchers developed a non-invasive model combining retinal vascular parameters with clinical data. Using AI to analyze fundus images, they demonstrated that retinal microvasculature serves as an effective DN biomarker. The model accurately distinguished DN from non-diabetic renal disease and predicted progression, offering a safer tool for patient management.

Artificial intelligence (AI) can be helpful in analyzing medical images and support radiotherapy planning workflows. However, huge amounts of sensitive patient data are needed to train robust AI models. Researchers at the Karlsruhe Institute of Technology (KIT) have investigated how hospitals can jointly develop AI models for radiation therapy applications without exchanging such data. In their project, they use federated learning, a process in which a single model is trained at a decentralized location while the data remains in place. Their results demonstrate not only the technical feasibility of the approach but also its safe, more sustainable, and accessible use.