Medication-related osteonecrosis of the jaw (MRONJ) can be difficult to treat once it develops, making prevention especially important. In a retrospective study, a Hiroshima University researcher found that quantitative measurements extracted from CT images taken before treatment, when analyzed with machine learning, could distinguish patients who later developed the condition from those who did not—an early step toward predicting MRONJ risk before bone resorption inhibitor therapy begins.

Governor Kathy Hochul today announced that Empire AI Beta is officially online, giving researchers at New York's leading public and private universities access to the most powerful academic research computer in the country and marking a major milestone in New York's effort to lead the nation in responsible artificial intelligence for the public good. As convened by Governor Hochul and consortium partners, the Empire AI initiative is already serving as a national model for public-interest AI use. As the federal National Science Foundation has announced a major investment to support regional AI infrastructure and shared research capacity through their new State and Regional AI Infrastructure Hubs initiative, Empire AI is already powering world-class research and serving academics, students and communities across the state.

Portal hypertension is a serious complication of chronic liver disease that can lead to life-threatening conditions such as internal bleeding and liver failure. A new study examines how advances in imaging, blood-based biomarkers, predictive models, and artificial intelligence are reshaping the non-invasive diagnosis of the condition. By bringing together the latest evidence, the review highlights how these approaches could support earlier detection, improve disease monitoring, and reduce the need for invasive procedures.

Seoul National University’s College of Engineering announced that Hyunsoo Lee, an undergraduate student in the Department of Electrical and Computer Engineering, has presented research in generative visual computing, spanning image editing and 3D content generation, at leading international conferences in machine learning and computer vision, including NeurIPS, CVPR, and ECCV. These conferences represent premier venues in their respective fields, making Lee’s sustained record of publication as an undergraduate particularly noteworthy.

Wake Forest University School of Medicine researchers show AI analysis of ECG data could make screening for heart dysfunction more accessible 

-  A team led by KAIST Chair Professor Shinhyun Choi develops a programmable dynamic memtransistor (PDM) whose response characteristics can be configured to match different input-data timescales

-  The device reduces time-series prediction errors by up to 40-fold compared with conventional fixed-response AI semiconductors, with potential applications in autonomous vehicles, robotics, wearables, and other edge AI systems