The Stanford-Princeton AI Coscientist Team has launched MedOS, the first AI-XR-Cobot system engineered to actively assist clinicians within real clinical environments. This platform combines smart glasses, robotic arms, and multi-agent artificial intelligence to function as a real-time co-pilot for doctors and nurses, aiming to reduce medical errors, accelerate precision care, and support overburdened clinical teams.
Physician burnout has reached crisis levels, with over 60% of U.S. doctors reporting symptoms. MedOS (https://ai4med.stanford.edu) addresses this by reducing cognitive overload, catching errors, and extending precision through intelligent automation and robotic assistance, rather than replacing clinicians. Built on innovation from the team's previous breakthrough, LabOS (https://ai4lab.stanford.edu), MedOS bridges digital diagnostics with physical action, perceiving the world in 3D, reasoning through medical scenarios, and acting in coordination with care teams.
MedOS introduces a "World Model for Medicine" that integrates perception, intervention, and simulation into a continuous feedback loop. Using smart glasses and robotic arms, it understands complex clinical scenes, plans procedures, and executes them collaboratively with clinicians. The platform has shown early promise in tasks like laparoscopic assistance, anatomical mapping, and treatment planning. In surgical simulations, it interprets real-time video from smart glasses, identifies anatomical structures, and assists with robotic tool alignment, functioning as a true clinical co-pilot.
Key capabilities include a multi-agent AI architecture that mirrors clinical reasoning logic, synthesizes evidence, and manages procedures in real time. MedOS achieved 97% accuracy on MedQA (USMLE) and 94% on GPQA, outperforming frontier AI models like Gemini-3 Pro, GPT-5.2 Thinking, and Claude 4.5 Opus. It leverages MedSuperVision, the largest open-source medical video dataset with over 85,000 minutes of surgical footage from 1,882 clinical experts. The system has demonstrated success in helping nurses and medical students reach physician-level performance, reducing human error in fatigue-prone environments, with registered nurses improving from 49% to 77% and medical students from 72% to 91% with MedOS assistance.
Case studies highlight MedOS's impact, including uncovering immune side effects of the GLP-1 agonist Semaglutide (Wegovy) from FDA databases and identifying prognostic implications of driver gene co-mutations on cancer patients' survival. The platform is modular by design, built to adapt across clinical settings and specialties. Dr. Le Cong, leader of the Stanford-Princeton AI Coscientist Team, stated that the goal is to amplify doctors' intelligence, extend their abilities, and reduce risks from fatigue, oversight, or complexity, marking the beginning of AI as a true clinical partner.
MedOS is launching with support from NVIDIA, AI4Science, and Nebius, and has been deployed in early pilots. It will be showcased at a Stanford event in early March, followed by a public unveiling at the NVIDIA GTC conference in March 2026, with session information available at https://www.nvidia.com/gtc/session-catalog/sessions/gtc26-s81748/. For more details, visit the project page at https://medos-ai.github.io/ or the official site at https://ai4medos.com/.
