New framework renders AI trustworthy for cancer subtyping
Peer-Reviewed Publication
Updates every hour. Last Updated: 23-Jun-2026 16:16 ET (23-Jun-2026 20:16 GMT/UTC)
Reported June 23 in Nature Biomedical Engineering, researchers at Vanderbilt Health and centers in Hong Kong have created a versatile uncertainty-aware AI framework broadly adaptable as a wrapper for digital pathology AI systems. (An AI wrapper acts as an interface layer that customizes, formats and automates how users interact with the underlying intelligence.) They demonstrate their wrapper, called TRUECAM, primarily with reference to non-small cell lung cancer (NSCLC) subtyping using whole-slide images.
UCLA scientists are calling for a large-scale initiative to understand how human cells influence one another — a missing layer of biology that could reveal how cellular interactions drive disease and inform new therapies.
A deep learning system (DL-T1b) leveraging digital pathology achieved strong performance (AUC 0.910) for predicting lymph node metastasis in T1b gastric cancer. Integration with six clinical risk factors into a nomogram further boosted predictive accuracy, offering a precise tool for personalized treatment decisions. This study establishes proof-of-concept for deep learning-based pathomics in early gastric cancer risk stratification.
A new Editorial published in Translational Exercise Biomedicine (ISSN: 2942-6812), an official partner journal of International Federation of Sports Medicine (FIMS), argues that physical inactivity can no longer be described merely as a public-health crisis. Instead, the authors contend, it represents a persistent implementation failure of modern societies to align with fundamental human biology with consequences that strain global health systems, economic sustainability, and long-term human resilience. The editorial was authored by Yannis P. Pitsiladis, Daria Obratov, Fabio Pigozzi and Ugur Erdener.