It’s not just the masterminds at IBM that can create machines designed to think like doctors. A pair of researchers at Indiana University say they have devised an artificial intelligence framework that may outperform physicians in making cost-effective clinical decisions that result in good outcomes.
“The Markov Decision Processes and Dynamic Decision Networks enable the system to deliberate about the future, considering all the different possible sequences of actions and effects in advance, even in cases where we are unsure of the effects,” said Casey Bennett, a doctoral student at IU’s School of Informatics and Computing, in a university release.
The non-disease-specific AI system created by Bennett and Kris Hauser, an assistant professor of computer science, was recently put to the test in a study using electronic health record data from 500 patients with clinical depression. By comparing the real outcomes and costs associated with the 500 cases to the hypothetical models their computer algorithms generated, they estimated that AI could improve patient outcomes by 30 to 35 percent.
“Modeling lets us see more possibilities out to a further point, which is something that is hard for a doctor to do,” Hauser said in a statement. “They just don’t have all of that information available to them.”
But the researchers don’t think the kinds of frameworks they’re developing will ever be able to actually replace doctors. “We believe that the most effective long-term path could be combining artificial intelligence with human clinicians,” Bennett said. “Let humans do what they do well, and let machines do what they do well. In the end, we may maximize the potential of both.”
Read the entire study published in a January edition of the journal Artificial Intelligence in Medicine.
[Photo from Wikipedia]
