Adding a lookup step makes AI better at assigning medical diagnosis codes
Peer-Reviewed Publication
Updates every hour. Last Updated: 27-Dec-2025 11:11 ET (27-Dec-2025 16:11 GMT/UTC)
A new study from researchers at the Mount Sinai Health System suggests that a simple tweak to how artificial intelligence (AI) assigns diagnostic codes could significantly improve accuracy, even outperforming physicians. The findings, reported in the September 25 online issue of NEJM AI [DOI: 10.1056/AIcs2401161], could help reduce the time doctors spend on paperwork, cut billing errors, and improve the quality of patient records.
Only 1 in 3 pupils meet the in-school activity target but this varies greatly across schools.
Professor Alexander Hoffmann and Genhong Cheng from University of California, Los Angeles, jointly with Professor David Baltimore from California Institute of Technology, published a review article in the newly launched journal Immunity & Inflammation. This article provides a systematic overview of NF-κB, covering its activation mechanisms, gene regulatory networks, physiological and pathological roles. It also summarizes recent advances in therapeutic strategies targeting NF-κB, offering a critical foundation for deeper understanding the pathway’s functions and mechanisms.
The unfolded protein response (UPR) is a protective pathway that helps cells manage stress during protein production. Cancer cells exploit this system to survive harsh tumor environments. In bones, they also disrupt the balance of bone-building and bone-resorbing cells, leading to skeletal fragility. Emerging therapies that target the UPR show promise in restoring bone health while selectively killing malignant cells, offering new hope for patients with cancer-associated bone disease.