Upon entering a hospital to give birth, parents-to-be place their trust in the medical staff. But what if an integral member of the hospital staff happened to be a robot?
Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory have spent two years attempting to answer this question by studying whether or not a robot could serve as an effective resource nurse.
Filling the shoes of a resource nurse requires quick decision making, a thorough understanding of patients' needs, and the ability to handle scheduling decisions.
The job also entails making sound decisions in a stressful and often unpredictable environment. Who better to remain unfazed by such an atmosphere than a robot?
Researchers from MIT trained the Nao robot to learn from scheduling decisions while taking into account patient complexity and nurse availability. They also sought to help the robot understand why nurses chose certain decisions over others.
The robot was then sent to Beth Israel Deaconess Medical Center in Boston, where nine out of 10 times it gave “high-quality recommendations” that doctors and nurses ultimately implemented, according to CNN Money.
“This indicates that a hospital service robot may be able to learn context-specific decision strategies and apply them to make reasonable suggestions for which tasks to perform and when,” the authors wrote in recently published paper.
Senior author of the study, MIT professor Julie Shah, says “measured steps” are being taken in the advancement of the technology. Verifying the safety and effectiveness of using a robot in a medical setting will require future studies in other hospitals.
See 'Ginger’ the robot nurse in action in the video below.