We’ve heard about how Watson flopped in medicine — and yet a remote surgical robot is going to the International Space Station:

On Earth, this technology already allows doctors to assist people in faraway locations where services are not readily available. However, the MIRA technology has the added benefit of performing operations autonomously, meaning that astronauts serving on the Moon and Mars could receive medical care without the need for a human surgeon.

Matt Williams, “A Remote Surgical Robot is Going to the International Space Station” at Universe Today (August 8, 2022)

Integrating AI and medicine is a complex dance. The Virtual Incision machine, slated for 2024, is part of a program to enable long-term life in space: “NASA has ambitious plans for long-duration space travel, and it’s important to test the capabilities of technology that may be beneficial during missions measured in months and years,” said Shane Farritor, co-founder and chief technology officer at Virtual Incision. “MIRA continues to push the boundaries of what’s possible in RAS, and we are pleased with its performance so far during clinical trials. We’re excited to take it a step further and help identify what could be possible in the future as space travel is becoming more of a reality for mankind.” It may not be possible to fly a surgeon in.

In another groundbreaking advance, surgeons were able to practice for months using virtual reality before they separated conjoined twins whose brains were fused:

The twins, who had shared vital veins in their brains, underwent seven surgeries involving nearly 100 medical staff. The final surgery alone took more than 27 hours, Insider notes, though surgeons had already spent countless more hours preparing in VR. Alive and well, the two boys are now the oldest children to have survived the complex separation procedure.

Aside from the sheer amount of hours of preparation VR simulations provide, the technology also let surgeons in Brazil work cross-continentally with a medical team in the United Kingdom. Gemini Untwined, a charity responsible for funding the operation, said this was the first time VR was used for such a complex surgery in Brazil.

Mack DeGeurin, “How Virtual Reality Training Helped Surgeons Separate These Conjoined Twins” at Gizmodo (August 2, 2022)

Similarly, a machine learning program cut the death rate of patients with a high risk of sepsis by 20 percent over two years, but enabling treatment to begin two hours sooner:

In a well-connected electronic-records system, known sepsis risk factors are available but may take time to find. That’s where machine-learning algorithms come in. Several academic and industry groups are teaching these programs to recognize the risk factors for sepsis and other complications and to warn health care providers about which patients are in particular danger. Saria and her colleagues at Johns Hopkins University, where she directs the Machine Learning and Healthcare Lab, began work on one such algorithm in 2015. The program scanned patients’ electronic health records for factors that increase sepsis risk and combined this information with current vital signs and lab tests to create a score indicating which patients were likely to develop septic shock. The paper requires a fee or subscription.

Sophie Bushwick, “Algorithm That Detects Sepsis Cut Deaths by Nearly 20 Percent” at Scientific American (August 1, 2022)

AI also enables scientists to, as it is put in Nature, “dream up revolutionary new proteins: Huge advances in artificial intelligence mean researchers can design completely original molecules in seconds instead of months.”

AI doesn’t replace human judgment; it allows us to save time and energy, and make space less of a factor in decisions.