The aim of the radiology department is to use artificial intelligence to supplement the workforce and keep people healthy.
Liz Martin – Photographer – Univ
dr Sandeep Laroia, a practicing interventional radiologist, photographed in an IR suite on Friday, October 7, 2022. Laroia leads a group of researchers who recently received a Phase I grant from the National Science Foundation to develop an artificial intelligence system that could help with some interventional radiology procedures.
New artificial intelligence technology for radiology practices is being developed at the University of Iowa.
The team, led by interventional radiologist Sandeep Laroia, will use programmed medical information and input from physicians to pinpoint patients’ diseases and determine the right treatment for various medical problems. Technology will supplement the workforce during a nationwide labor shortage and keep people healthy.
Several teams have helped develop the project for about four years, Laroia said.
“The concept actually started before COVID hit us — so 2018-2019,” he said. “So we put together a team and the department has been very supportive of this initiative. Then, during the COVID time, we realized that this can be turned into something really useful and really helpful.”
According to Laroia, AI in medicine serves two main functions: reducing manpower and keeping workers safe.
As of July 2022, hospitals in nearly 40 states were reporting critical staff shortages. Laroia said AI will play a crucial role by filling in gaps created by the shortage
“In the medical field, there are very complex procedures like neurosurgery or tumor surgery and things like that, but there are many tasks that don’t require as much expertise and training,” said Laroia. “It frees the workforce to do things that machines can’t do.”
Hozhabr Mozafari, Licensing Associate at UI Research Foundation, works with Laroia’s team to bring their product to market by filing patents and copyrights and offering the product to consumers.
“There’s a lot of back and forth, discussions and meetings here with the company and if they’re interested we would license that,” he said. “Basically, our main job is for these companies to make ours [intellectual property] so that the public can benefit from it.”
The team has filed several patents for Laroia’s technology, Mozafari said.
Laroia’s team isn’t the only one developing AI at the university. Mozafari said the UI Research Foundation has noticed an increase in AI projects at the university in recent years.
“AI is a hot topic. Recently, we’ve received various AI technologies for a variety of applications,” he said. “One of the uses of AI that we are seeing is scanning medical images. We have technology that can implement AI to diagnose cancerous tumors.”
The development of AI is also increasing in the USA. A White House task force has been working to expand AI development nationwide by making technological resources more accessible. The National AI Initiative Act of 2020 is a step towards that goal.
Bijaya Adhikari, UI Assistant Professor in the Department of Computer Science, said the public has concerns about AI. He said one concern is that AI will affect the quality of patient care, but he said that is not the case.
“The AI algorithms run in the background,” Adhikari said. “So things look pretty much the same for patients, but in the report, instead of just your blood test results, you might see things like your risk scores that need to be calculated using AI algorithms.”
He said another common concern about AI is that it will replace human labor and result in people being laid off, but he doesn’t see that either. He said AI will complement human expertise and inform healthcare providers about possible next steps in treatment.
Adhikari said a major obstacle for AI in its adoption in the medical field is data.
“There are many administrative issues, privacy issues and sensitivity issues that need to be resolved before these things can be deployed,” he said. “The tools that we’re building, we’re currently making in a very secure environment where there’s no potential data loss before these things can actually be used where they can impact patients’ lives.”
