For children who need braces or jaw correction, timing is everything. If treatment starts before or after a growth spurt, it can be far less effective. But doctors have long struggled to predict exactly when those spurts will happen. Now, a team of South Korean researchers has created an artificial intelligence (AI) tool that can read simple neck X-rays and spot the signs of rapid growth. The technology could give orthodontists a powerful new way to plan care with precision.

Conventionally, deep neural networks (DNNs), including convolutional neural networks (CNNs), are trained using backpropagation—a standard algorithm in AI learning. However, backpropagation suffers from several limitations, such as high computational cost and overfitting. Researchers have now developed a new training approach called the Visual Forward–Forward Network (VFF-Net), which overcomes these challenges. By eliminating the need for backpropagation, VFF-Net enables more efficient, less resource-intensive training while maintaining high accuracy and robustness.

A new review in BMC Medicine explores how large language models (LLMs) can enhance the design and conduct of clinical trials, from protocol design and informed consent to patient recruitment, data management, safety monitoring, and outcome prediction. The authors highlight LLMs’ advantages over traditional natural language processing, including contextual understanding, few-shot learning, and multitask capability. While applications such as data mapping and real-time adverse event monitoring show early promise, challenges in data privacy, model transparency, and regulatory alignment must be addressed to ensure safe, effective integration into clinical research.

Griffith researchers built and tested a digital archaeology framework to learn more about the ancient humans who created one of the oldest forms of rock art, finger fluting.

Finger flutings are marks drawn by fingers through a soft mineral film called moonmilk on cave walls.

Experiments were conducted - both with adult participants in a tactile setup and using VR headsets in a custom-built program - to explore whether image-recognition methods could learn enough from finger-fluting images made by modern people to identify the sex of the person who created them.

In the International Journal of Extreme Manufacturing, A novel conductive hydrogel, termed AirCell Hydrogel and developed by Tianjin University researchers, exhibits an ultra-high sensitivity of 18.9. Its smooth surface enables conformal adhesion that effectively suppresses motion artifacts, while its porous interior structure lowers the Young's modulus during deformation tracking.