Ozlem Garibay ’01MS ’08PhD earned her degrees from UCF in computer science. She instructs classes in the Department of Industrial Engineering and Management Systems. Yet here she is, using all this expertise to help a team of UCF researchers change medicine — specifically, how diseases are diagnosed and prescription drugs are developed. Garibay turns from her computer monitor for a few minutes to explain the potential impact of the team’s work and why they’re motivated to put in the hours to make it happen.
“I’m glad we’re having this conversation,” Garibay says. “It allows me to step back from the micro-details and remember the reason we’re doing this.”
In simple terms, how can artificial intelligence (AI) improve drug development?
The process is like finding a matching key for a lock. Every virus is extremely complex, with million of unique characteristics. Each compound has its own characteristics, too. With the human mind, it’s impossible to match the right compounds with a virus. Through the best trial and error being used now, it can take up to 10 or 20 years to find a match. But with artificial intelligence, we can screen for suitable candidates of drugs that can be tested quicker and with fewer resources.
Give us an idea of the cost of savings.
We recently received a research grant from UCF for $40,000. It sounds like a lot of money, until you consider that it can cost more than $20 billion annually for pharmaceutical companies to develop a drug using traditional methods. Those high costs are passed down to the consumer. We want to get to a point where those companies can use our research to make the process faster and cheaper.
How did you get involved in this?
It started during the early stages of the pandemic. I saw friends and colleagues getting sick, and I feared for family members all over the globe. That summer, I attended a workshop in Orlando and heard how AI can extrapolate volumes of data to discover drugs to fight viruses. It sounded brilliant. Then a few days later, an engineering professor here at UCF, Sudipta Seal, told me he was working on a similar problem in the Research Park. It made perfect sense to put a team together and pursue it.
What do you credit your progress to?
We aren’t motivated by accolades or personal gain. We know this research can help protect precious lives around the world for generations. That’s what keeps us pressing forward.
Could the research be used for diagnosis and prevention, too?
Definitely. We’re looking at how AI might be used to identify “markers” in basic tests before a person even knows they have an affliction. Our goal is to make it possible for healthcare providers to understand each person completely by connecting data about lifestyle, environment, health history, genetic composition and other factors. That way, they can truly individualize care, whether there are symptoms or not.
Why do you have to be careful with this research?
Advancing AI research in an ethical and responsible way is near and dear to my heart. We want very much to help people have better lives, but the technology must be reliable, safe and secure. There can be no compromises. We have recently published a paper on human-centered AI that highlights the six challenges for the research community to guide responsible AI. These include centering human well-being, responsible design, respecting privacy, following human-centered design principles, appropriate governance and oversight, and interacting with individuals while respecting humans’ cognitive capacities.
Might this be a silver lining out of the pandemic?
Oh my goodness, this goes far beyond COVID. The applications in healthcare have the potential to slow down diseases like Alzheimer’s, cancer and the next global virus. And if it does, then we can say it happened partly because a group of researchers came together, motivated by a singular mission to make lives better.