Such cognitive robots may also find a role in clinical pathology laboratories
Pathologists and clinical laboratory managers might soon have new cognitive robotic tools to help them diagnose disease. Engineers and emergency medicine specialists at Vanderbilt University have joined together to develop a system of cognitive robots that would reduce the wait times physicians and staff experience in America’s emergency departments (ED).
These cognitive robots would be programmed to perform basic tests and deliver results on patients. By handling these functions, the Vanderbilt development team believes that their cognitive robots would reduce the workload on triage nurses and speed the process of treating patients in the emergency room.
Artificial Intelligences to Examine Patients and Assess Medical Laboratory Data
In “Heterogeneous Artificial Agents for Triage Nurse Assistance,” a paper written by D. Mitchell Wilkes, Ph.D., Associate Professor of Electrical and Computer Engineering, Vanderbilt University, et al., researchers introduced the concept of the “TriageBot System,” which would “gather both logistical and medical information, as well as take diagnostic measurements, from an incoming patient for later use by the triage team. TriageBot would also give tentative, possible diagnoses to the triage nurses, along with recommendations for non-physician care.”
The plan is for such a cognitive robot to examine patients who arrive “by car or walk in on foot,” and whose ailments would not be considered “severe,” in order to reduce the burden on the emergency department staff.
Professors D. Mitchell Wilkes, Ph.D. (right), and Kazuhiko Kawamura, Ph.D., of Vanderbilt University. Images sourced from Vanderbilt University website.
“Advances in humanoid robotic design, in sensor technology and in cognitive control architectures now make such a system feasible,” said Wilkes at a conference in Nashville on humanoid intelligence.
TriageBot would conduct a slew of vital tasks, including:
- “gathering data from the patient,
- “taking diagnostic measurements,
- “assessing the severity of the patient’s condition for ordering priority of treatment, and
- updating the patient’s data at timely intervals.”
The Vanderbilt engineers are developing a “cognitive architecture” for the robotic healthcare “assistant” that mimics the “working memory” of the human brain. They realized that for such a cognitive robot to be successful, it must have decision-making ability that rivals humans. The development team recognized that the controlled-chaos of a busy ED makes it an ideal testing ground for the cognitive robot prototypes.
“Our architecture is designed to allow robots to integrate quick decision-making with the more common deliberate decision-making process in flexible ways,” said Kazuhiko Kawamura, Ph.D., Professor of Electrical and Computer Engineering, and Engineering Management, at Vanderbilt University. “If cognitive robots are to operate successfully in a human environment, they must be able to choose actions with a similar rapidity, particularly in a chaotic environment like the emergency room.”
Artificial Intelligence Bests Humans at Jeopardy
Dark Daily readers may recall that IBM is also working on an artificial “brain”—dubbed “Watson”—with the goal of providing evidence-based diagnostic tools for physicians at the point of care. Watson might someday also direct the actions of future cognitive robotic healthcare workers, for example. (See Dark Daily, June 15, “After Taking on Jeopardy Contestants, IBM’s Watson Super Computer Might Be a Resource for Pathologists.”)
This IBM Watson supercomputer recently defeated its human competitors on the television trivia show “Jeopardy,” and in doing so, put to rest any doubt that artificial intelligences could out perform humans on a variety of levels—even those requiring natural language recognition.
IBM subsequently announced that Watson would be used to develop new ways to assist physicians in delivering better healthcare. Researchers at Vanderbilt University seem to be thinking along the same lines.
“While there may be a role for robots to play in the severe trauma situations,” wrote the study’s authors, “this paper focuses on the less severe cases with particular emphasis on the role of the triage nurse, and how robots may be used to assist the nurse in the performance of his/her duties.”
As these cognitive robots are developed, they have the potential to be useful to pathologists, clinical chemists, and clinical laboratory scientists. By calling up all relevant patient data and utilizing care algorithms developed from evidence-based medicine (EBM) guidelines, IBM’s Watson and his cognitive robot colleagues could help pathologists and laboratory professionals drill down to a fast and accurate diagnosis.
Related Information:
Developing robots for the hospital emergency room
Heterogeneous Artificial Agents for Triage Nurse Assistance
Computer Wins on ‘Jeopardy!’: Trivial, It’s Not (New York Times)
