Methodist Mansfield Hospital finds success using AI tools to support healthcare staff

Methodist Mansfield Hospital is currently a pioneer in medical technology with the recent incorporation of artificial intelligence (AI) into its new neurological intensive care unit.

Methodist Mansfield’s AI technology was developed by a brain imaging analysis software company FAST AI. The technology was implemented at the hospital late last year. It was then transferred to the neurology department, which opened in February.

By using this tool, staff can save a significant amount of time while protecting brain tissue.

“That speed gives us an extra five to 10 minutes to get to our destination,” Juan Fresquez, president of Methodist Mansfield, said at an Arlington City Council meeting. “Just like a heart attack, when the blood flow is blocked, you start losing heart muscle. It’s the same with the brain, every minute, every second counts.”

Methodist Mansfield uses RAPID-AI technology, running CT scans through software programmed to flag potential abnormalities. When the AI ​​finds an abnormality, the medical team is notified. A neuroradiologist then determines whether further treatment is needed.

Fresquez then told the story of Kristin Booth, 45, who was hospitalized after she woke up unable to speak or move her right hand.

According to the Shine Hospital’s internal magazine, the mother of five underwent treatment to remove a large blockage in a vessel. Just two days after it was discovered and treated, she was cheering on her son’s basketball game.

Clots like the one Booth suffered can cause permanent problems with walking and speaking, as well as paralysis or numbness of the face, arm, or leg if left untreated. But thanks to the AI ​​software’s quick detection, staff were able to prevent these lasting effects.

However, as Fresquez later told KERA, AI technology is not entirely new to healthcare.

“AI has been around for a long time,” Fresquez said. “I’ve been in healthcare since the mid-1980s, and I’ve been around a lot of the early development of AI, which really started with computer-aided sensing (CAD) and imaging. It’s really the infant version of what we have today in AI.”

The use of artificial intelligence has recently become a controversial topic to talk about in recent years. A world where AI takes on traditional human roles has been depicted in countless science fiction works, such as the Will Smith-starring film I, Robot or Disney-Pixar’s Wall-E. But with the advancement of generative AI tools like ChatGPT and Dall-E, concerns have never been louder.

SAG-AFTRA and WGA, the unions for actors and writers, have even taken action to prevent studies from the use of AI to create content during last year’s historic strikes.

But “fear” isn’t the word Rachel Cochran, head of the neurology intensive care unit, would use. She says AI can’t do what trained doctors and radiologists can do because the technology isn’t always perfect.

“A human doctor will always be the one diagnosing the patient, (AI) is not replacing that person,” Cochran said. “Health care is very holistic; we have to consider a lot of different things when we’re considering treating people.”

Jamboor Vishwanatha is vice president of minority health and health disparities at the UNT Health Science Center. Like Cochran, he believes that AI will never be able to fully replace humans in the health care industry.

“At best, AI tools will be an aid, not a replacement for professionals,” Vishwanatha said. “The outcome will be better, and surgery can be done much faster than it is now. But at no point do I think a robot will take over what a surgeon can do.”

Vishwanathy’s team is currently working on several national projects on AI-based machine learning that aim to “increase healthcare equity and researcher diversity.”

Part of that mission includes making sure AI tools are trained on a diverse set of data. The potential flaw in AI lies in what the tool learns, according to Vishwanathy.

If data from a single demographic group based on race, ethnicity, or gender is collected and then fed into the educational system, it could provide physicians and healthcare providers with misleading information.

“I think there’s a huge opportunity in surgical care to leverage AI learning models,” Vishwanatha said. “With that in mind, I’m also very concerned about how it could impact different communities. Not all of our communities are getting the surgical care they need. So, if AI surgical models are developed based on existing surgical data, it could impact certain communities because they’re not represented in that data.”

Fresquez agrees with this view, citing an issue that plagued marginalized communities in the 1980s.

“You want to have databases that include all nationalities and genders,” Fresquez said. “Looking back to the early days of imaging, Computer Aided Detection, or CAD, was primarily used in mammography. And there were clear differences in cancer rates, so it’s not detection, among the different nationalities and ethnicities that were being evaluated.”

Cancer databases were then updated to better serve Black and Brown communities. When hospitals first collected data, only white, affluent women could afford treatment.

Fresquez says Methodist Mansfield intends to submit a variety of results to these databases.

“The more data you collect, the better,” Fresquez said. “The size of the database really closes the gap in standard deviation. So the more data points you have, the more precise your data and reporting of results will be.”

RAPID-AI is currently used in over 2,000 healthcare facilities in over 100 countries which will help in diverse data collection.

KERA contacted RAPID-AI regarding data collection methods but had not received any response at the time of writing.

Currently, Methodist Mansfield is only using AI in its Neuro ICU. However, Fresquez says the hospital is more than willing to use AI tools in the future.

“We want to make sure we don’t have to wait too long to make changes,” Fresquez said. “I didn’t think this technology would be available. We’re fortunate that I think we’re the first in our health system to actually implement it. I’m very optimistic and excited about what the future holds.”

Emmanuel Rivas Valenzuela is a KERA intern in the SPJ news department for summer 2024. Have a tip? Email Emmanuel Rivas Valenzuela at [email protected].

KERA News is made possible by the generosity of our members. If you found this reporting valuable, please consider making a tax-deductible donation today. Thank you.