NASA tests AI medic for astronauts too far from Earth to call a doctor

AI AND ML NASA tests AI medic for astronauts too far from Earth to call a doctor Please state the nature of the medical emergency Richard Speed Richard Speed Published sat 27 Jun 2026 // 10:20 UTC NASA researchers are testing an AI clinical decision support system to help astronauts diagnose and treat medical symptoms during deep-space missions. The  Crew Medical Officer Digital Assistant (CMO-DA) is powered by a Red Hat-backed open source tool called RamaLama, designed to simplify how developers run, pull, and serve AI models. While it's no Star Trek-esque Emergency Medical Hologram (EMH) quite yet, it could be a boon to ailing astros far from home. Earlier this year, NASA decided to bring Crew-11 back from the International Space Station (ISS) early because of a medical concern. As missions venture further afield – to the Moon, Mars, and beyond – an early return may no longer be practical, while communication delays can rule out real-time consultation with doctors on Earth. REG AD Red Hat says that CMO-DA started life as a proof of concept before moving from a cloud-dependent model to a fully disconnected edge deployment. It currently runs on a terrestrial twin of the HPE Spaceborne Computer aboard the ISS. REG AD Inference is multimodal. "RamaLama provides the engine to run both large language models (LLMs) for complex medical reasoning and Vision Language Models (VLMs) for image-based symptom analysis," Red Hat stated. "This allows the CMO-DA to process both text and visual data without needing a massive infrastructure footprint." CMO-DA runs locally on the device, which means responses do not depend on a connection to Earth. MORE CONTEXT HPE's updated Spaceborne Computer-2 ready to hitch another ride to the ISS Edgy: HPE's first message from the International Space Station to Microsoft's Azure? 'hello world' Red Hat blasts RHEL 10.1 into orbit aboard Voyager's micro datacenter HPE Spaceborne Computer-2 slips off the shelf – and off the planet: Boxen h