|Help / Recent Posts / Search / Login / Register|
Stats: 2413 Members, 4737 topics. Date: March 30, 2017, 11:32:19 PM
|MIT Researchers Trains Robot Resource to recommend good and bad decisions by Idowu Olabode : July 12, 2016, 07:31:54 AM|
-Researchers trained robot to differentiate between good and bad decisions
-It was then given tasks of a resource nurse, assigning beds and scheduling
-Study revealed nurses and doctors complied with suggestions 90% of time
Robots could soon lend nurses a helping hand in the delivery ward.
Researchers from MIT Computer Science and Artificial Intelligence Laboratory trained a Nao robot to learn the differences between good and bad decisions on the delivery floor at Beth Israel Deaconess Medical center in Boston
In a two-year study, researchers from MIT have investigated whether robots can effectively take on the job of a ‘resource nurse,’ making complex decisions in a fast-paced environment.
Resource nurses are tasked with making thousands of critical decisions, including bed assignments and selecting the right nurse to perform a C-section – and so far, the researchers found that doctors and nurses accepted the robot-made recommendations 90 percent of the time.
In the study, the researchers from MIT’s Computer Science and Artificial Intelligence Laboratory trained a Nao robot to learn the differences between good and bad decisions on the delivery floor, according to CNN Money.
Then, the robot named ‘Ginger’ was taken to Beth Israel Deaconess Medical Center in Boston to test out her skills.
Being a resource nurse requires complex problem-solving, and at Beth Israel, the job means coordinating 10 nurses, 20 patients, and 20 rooms all at once. But, Ginger showed her ability to give advice that the medical staff was willing to follow
‘Our robot used machine learning computer vision techniques to read the current status of the labour floor and make suggestions about resource allocation and used speech recognition to receive feedback from the resource nurse,’ the authors wrote in a recently published paper.
Being a resource nurse requires complex problem-solving, and at Beth Israel, the job means coordinating 10 nurses, 20 patients, and 20 rooms all at once.
But, Ginger showed her ability to give advice that the medical staff was willing to follow.
In a video on the experiment, the robot can be seen providing examples of both good and bad decisions for doctors and nurses.
‘I recommend placing a scheduled caesarean section patient in Room 5. Nurse Merideth can take care of her,’ the robot says when asked to offer a good decision.
When asked about a bad decision, Ginger says, ‘A bad decision would be to place a scheduled caesarean section patient in Room 14 and have nurse Kristen take care of her.’
The researchers investigated the differences between this type of decision-making support from a computer-based system, and with the robot.
While previous studies have suggested that humans often place ‘inappropriate degrees of trust and reliance’ on artificial intelligence, the experiments found that the use of robots did not have this outcome.
Though medical staff was not over-reliant on the robot, they largely agreed with the suggestions it made, and the team found Ginger produced ‘high-quality recommendations accepted by nurses and physicians at a compliance rate of 90%,’ the authors wrote.
‘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.’
These findings indicate that robotic assistants could one day be used effectively for patient care, the researchers explain, though more work is necessary to ensure the safety of such a system.
WILL ROBOTS STEAL YOUR JOB?
Claims made by an expert in artificial intelligence predict that in less than five years, office jobs will disappear completely to the point where machines will replace humans.
The idea that robots will one day be able to do all low-skilled jobs is not new, but Andrew Anderson from UK artificial intelligence company, Celaton, said the pace of advance is much faster than originally thought.
AI, for example, can carry out labour intensive clerical tasks quickly and automatically, while the latest models are also capable of making decisions traditionally made by humans.
'The fact that a machine can not only carry out these tasks, but constantly learn how to do it better and faster, means clerical workers are no longer needed in the vast quantities they once were,' Mr Anderson said.
For example, a machine can recognise duplicate insurance claims by knowing it has seen a phone number or an address before.
Source : UK Dailymail
Viewing this topic: 0 Members and 1 Guest
Meet your newest friend, nurse and carer: a robot who reads your moods and emoti
Started by Idowu Olabode
January 10, 2016, 06:11:00 PM
by Idowu Olabode
Robot nurses to the rescue
Started by Idowu Olabode
February 20, 2016, 05:51:01 PM
by Idowu Olabode