ChatGPT went viral in late 2022, seemingly kicking off the age of AI. We’ve seen rapid advancements since then, with AI becoming the central focus of every big tech announcement, whether hardware or software.
At the same time, there’s been a growing debate about the safety of AI. Some look forward to the AI of the future, which might save lives and innovate in a way the human mind can’t. Others fear that AI might lead to the destruction of the world.
We’re yet to create a type of all-knowing AI that’s more intelligent than humans and can quickly devise new drugs. However, modern AI models are already capable enough to save lives by using existing medicine.
The best example is the use of AI models to power drug repurposing. This involves using drugs that are currently approved to treat certain conditions as therapies for rare illnesses that don’t have effective treatments.
Essentially, AI can comb the literature and find drug side effects that are actually beneficial for patients suffering from those potentially life-threatening conditions.
It’s not just a theory or wishful thinking. About a year ago, a 37-year-old man was left for dead. Suffering from POEMS syndrome, Joseph Coats experienced severe complications that prevented him from getting the only potential life-saving cure, a stem cell transplant. While his doctors abandoned hope, his girlfriend didn’t, reaching out to a different doctor who used AI to come up with a new therapy.
“A little over a year ago, Joseph Coates was told there was only one thing left to decide. Did he want to die at home, or in the hospital?” – that’s how The New York Times story detailing the emerging world of AI-based repurposing story starts.
It’s a horrifying prospect to have doctors tell you there’s no chance of survival despite the highly advanced medicine currently available. Thankfully, Coates’s girlfriend did not take no for an answer. Tara Theobald contacted David Fajgenbaum, a doctor in Philadelphia whom they met at a rare disease summit.
A day later, Dr. Fajgenbaum replied, offering an unconventional therapy. He proposed the combination of chemotherapy, immunotherapy, and steroids for Coates. The therapy worked, and Coates was strong enough to receive the stem cell treatment four months later.
POEMS syndrome is a rare blood disorder that can impact various organs. Coates’s hands and feet were numb, his heart had enlarged, and his kidneys were failing. Every few days, doctors needed to drain fluid from his abdomen. That was the condition that preceded Fajgenbaum’s approach.
The doctor did not devise the therapy himself; AI suggested it. Fajgenbaum had previously treated his rare condition (Castleman disease) with a drug called sirolimus, which is usually used for kidney transplant patients.
Fajgenbaum founded Every Cure, a nonprofit that uses AI for drug repurposing. The nonprofit received over $100 million in funding from TED’s Audacious Project for Advanced Research Projects Agency for Health. Every Cure will use the funding, in part, to conduct clinical trials for AI-based repurposed drugs.
The Times reports that this type of AI use might benefit hundreds of millions of people worldwide who suffer from rare, difficult-to-treat diseases.
Each of these conditions might only impact hundreds of thousands of people in a country. The National Institutes of Health (NIH) defines rare diseases as conditions that affect fewer than 200,000 people in the US. But it quickly adds up when you take into account the entire world.
As cynical as it may sound, those figures are not great incentives for pharmaceutical companies to develop new drugs for those specific illnesses. As clever as it might be, drug repurposing isn’t lucrative either. The AI is finding novel uses for drugs that are already approved to use for certain conditions. Drug patents usually expire after a few decades, so there’s little incentive to study additional uses for them.
What’s brilliant about using AI for drug repurposing is that the AI is doing a simple job that humans could replicate, at least in theory.
You could search the web for existing drugs that can offer a desired effect that might treat a rare illness. Essentially, you’d be looking for side effects in patients who take those drugs for the condition the medicine is effective for. But it would take humans a lot of work to comb the available literature. Some patients would not have the time to wait.
Using AI models customized for the medical field can significantly improve this task. Suddenly, the AI can find drugs doctors wouldn’t have considered for a certain condition.
“If you comb through enough drugs, you eventually find the side effect you’re looking for,” Dr. Matt Might told The Times, “and then that becomes the main effect.”
Like Fajgenbaum, Might is working on drug repurposing with the help of AI. He and his team at the University of Alabama developed an AI model that helped them treat a 19-year-old patient suffering from chronic vomiting.
They used a prompt similar to what you’d type in ChatGPT to find answers to a specific question: “Show us every proposed treatment there has ever been in the history of medicine for nausea.” The AI suggested the young patient inhale isopropyl alcohol through the nose, which is usually used as an antiseptic.
Regardless of what the AI discovers, doctors still have to decide whether to use the drug combinations these models suggest.
Luckily for Coates, the doctors tried the therapy AI proposed, and it worked. A year after his seemingly imminent death scare, Coates is doing much better, and it’s all thanks to AI drug repurposing.
