- NASA’s AI medical tool works where Earth-based doctors simply cannot reach
- Deep space has no signal – so NASA built its own offline doctor
- RamaLama runs AI models the same way containers run software – predictably
Astronauts aboard the International Space Station (ISS) currently rely heavily on ground-based doctors when medical problems arise hundreds of kilometers overhead.
This arrangement works reasonably well in low Earth orbit, where communication delays remain short enough for near-real-time consultation sessions.
That becomes far less practical when crews travel beyond Earth orbit, where signals can take minutes rather than seconds to arrive.
An AI doctor built to work without an internet connection
Researchers at NASA’s Johnson Space Center in Houston are now testing a clinical decision support system called the Crew Medical Officer Digital Assistant, or CMO-DA.
The system is designed to help astronauts diagnose and treat medical conditions during deep space missions, where real-time communication with ground-based doctors may be limited or impossible.
Powering it is RamaLama, a Red Hat-backed open source tool built to simplify how developers run and operate AI models across different hardware environments.
According to Red Hat, RamaLama treats AI models as container images and runs them in isolated environments with security first using Open Container Initiative-compliant containers that are portable and predictable across hardware.
This approach enables CMO-DA to perform what the team calls multimodal inference—processing both large language models for complex medical reasoning and Vision Language Models for image-based symptom analysis.
The system can therefore evaluate both written symptom descriptions and visual data without requiring any connection to a terrestrial cloud server.
This offline capability is not a convenience feature, but a mission-critical requirement, since deep space communication delays make cloud dependence truly dangerous to crew health outcomes.
Testing is currently running on HPE hardware—specifically, the ground-based twin of the spaceborne computer already aboard the ISS—giving researchers a reliable ground-based replica of the actual deployment environment.
Using open source tools throughout, NASA scientists have built a system that is reproducible and auditable, which the team describes as essential for human safety in mission-critical environments.
From ground experiments to the ISS and beyond
Once the ground-based test phase is complete, CMO-DA will be demonstrated to NASA management for evaluation of further deployment aboard the International Space Station.
The next iteration of the system will integrate Red Hat Enterprise Linux AI, known as RHEL AI.
This is to provide a stable, hardened foundation for scaling and managing containerized AI applications in remote and extreme environments.
RamaLama itself was built with the stated goal of making AI “boring” – meaning reliable, predictable, and loveless in the best possible sense for mission-critical applications.
The same architecture being tested for the health of astronauts may eventually serve as a blueprint for delivering medical support in the most remote areas of Earth.
Whether the CMO-DA will eventually evolve into something similar to Star Trek’s handheld Tricorder is still unknown.
What is known is that an open source AI tool is already diagnosing symptoms aboard replica hardware currently orbiting Earth.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
