Developing a personalized radiation therapy plan can take days—time that many cancer patients are unwilling to wait. But researchers have developed a new automated artificial intelligence (AI) software that can do the job in 20 minutes.
Aaron Babier, with the University of Toronto, and colleagues created a software that utilizes AI to analyze data of past radiation therapy plans. That information is then fed into an optimization engine to create a customized treatment plan that is on par with conventionally crafted plans.
"There have been other AI optimization engines that have been developed,” Babier said in a University of Toronto news story. “The idea behind ours is that it more closely mimics the current clinical best practice.”
Their method, which was applied to 217 patients with throat cancer, who had received treatments developed via conventional methods, can achieve a personalized radiation therapy plan within 20 minutes. The results were published in the journal Medical Physics.
With fine-tuning and validation, the team believes the tool can one day be used in clinics to free up providers time to focus on improving patient care and outcomes.
"Right now treatment planners have this big time sink,” Babier said. “If we can intelligently burn this time sink, they'll be able to focus on other aspects of treatment. The idea of having automation and streamlining jobs will help make health-care costs more efficient. I think it'll really help to ensure high-quality care.”
Although the software can provide a step in the right direction, doctors and specialists will still be central to improving the technology, the authors noted.
“It is very much like automating the design process of a custom-made suit," said researcher involved in the study Timothy Chanwith, with the University of Toronto. "The tailor must first construct the suit based on the customer's measurements, then alter the suit here and there to achieve the best fit. Our tool goes through a similar process to construct the most effective radiation plan for each patient."