David Fajgenbaum, MD, MBA
In 2010, halfway through his medical training at the University of Pennsylvania, David Fajgenbaum, MD, MBA, lay in a bed at Duke University Hospital, dying from a rare disease.
Tests showed he had idiopathic multicentric Castleman disease, which causes the overgrowth of cells in the body's lymph nodes. Castleman weakens the immune system, shuts down organs, and triggers deadly infections.
The chemotherapy that Duke doctors tried didn't seem to be working. He was growing sicker by the day, and doctors told him he wouldn't survive.
His heartbroken family and friends bid their final goodbyes, and a priest gave Fajgenbaum last rites. His mind in those last moments was a swirl of grief and anger, Fajgenbaum says.
This was partly due to a vow he made to his mother just before her 2004 death from brain cancer.
"I promised my mom, 'I'm going to become a doctor to treat patients like you,'" Fajgenbaum says. "I was so upset that I wasn't going to be able to fulfill that promise."
And then, an unexpected turnaround: Within hours of receiving the last rites, the chemo seemed to take effect and Fajgenbaum started to improve.
The chemo saved him, but Fajgenbaum still faced a grave reality: Castleman disease had no known cure, and most people with the disease lived for less than 2 years.
Embracing Second Chances
Over the next 3.5 years, Fajgenbaum nearly died four more times from Castleman disease and was in and out of the hospital with complications. Despite his condition, Fajgenbaum graduated from medical school and went on to the Wharton School in Philadelphia to pursue a business degree.
Chemotherapy seemed to keep the disease at bay for short periods. That allowed Fajgenbaum not only to pursue his studies but also to study his own condition in a friend's laboratory.
By analyzing his own blood samples, Fajgenbaum made a breakthrough: A pathway in his immune system was stuck in overdrive. He theorized that an inhibitor drug used to manage the same pathway problem in kidney transplant patients might also work for Castleman. He was right.
Within a couple of days of starting a drug called sirolimus, Fajgenbaum began feeling better, and his bloodwork improved. Months went by, and the disease remained in remission.
But finding his own cure sparked a question that would alter the course of Fajgenbaum's career: How many other drugs sitting on pharmacy shelves could unknowingly benefit people with rare diseases?
And so Fajgenbaum changed direction. Rather than going into an oncology residency, as he'd planned, he joined the faculty at the University of Pennsylvania where he founded the Center for Cytokine Storm Treatment & Laboratory to help identify medications and best treatment approaches for Castleman and other diseases.
Since the center's initiation, Fajgenbaum and his team have discovered nine more treatments for various types of Castleman disease and have repurposed treatments for COVID-19 and angiosarcoma, a rare form of cancer.
Scaling His Success With Artificial Intelligence
Ecstatic at his team's success, Fajgenbaum wanted to find a way to investigate a larger swath of rare diseases. And so in 2022, he and friend Grant Mitchell, MD, a business entrepreneur with experience in machine learning, co-founded Every Cure, a nonprofit organization that links existing drugs to rare diseases using artificial intelligence (AI).
Every Cure uses the Biomedical Data Translator Program, which integrates multiple types of information like disease symptoms, drug effects, and biological data. Every Cure applies their own AI algorithms to infrastructure from the National Center for Advancing Translational Sciences to find potential matches between rare diseases and existing drugs.
This makes it possible to search all 3,000 FDA-approved drugs against all 20,000 known diseases and produce a score for how likely each drug could treat each disease. That's 60 million possible combinations.
"The AI enables us to calculate a likelihood for all 60 million possibilities. Does aspirin treat colon cancer? Does aspirin treat sickle cell disease? You name it. It comes up with a score for every one," says Fajgenbaum.
Fajgenbaum and his team of researchers and scientists then go through the scores and prioritize which pairs are most promising for potential clinical trials.
For example, AI scores have led the team to investigate whether arginine, a heart drug, could help treat sickle cell disease. Or whether leucovorin, currently used to prevent chemo side effects, might help improve verbal ability in autistic children.
"Because leucovorin has been around for decades, and it's cheap and no one can make any money off of it, no one's doing anything with it," Fajgenbaum says. "We want to do a big, definitive trial."
Looking Back to Go Forward
Fajgenbaum has now been healthy for 10 years. He thinks often of his mom. "Something my mom used to always tell me when bad stuff happened was: Don't just look for a silver lining, look to create a silver lining," he says.
"Something my mom used to always tell me when bad stuff happened was: Don't just look for a silver lining, look to create a silver lining."
-- David Fajgenbaum, MD, MBA
Loading...
"Learning from her, I've been able to do that. She would be so excited to see Every Cure's impact and to hear about the progress and the patients. She would be completely over the moon."
Every Cure plans to further refine and advance its AI technology in the coming years. In February 2024, the organization received $48.3 million in funding from the Advanced Research Projects Agency for Health (ARPA-H), a federal agency that aims to advance high-potential, high-impact biomedical and health research. Every Cure will use the funding to develop its own AI-driven, open-source drug repurposing database and to establish a portal for doctors, researchers, and patients to contribute repurposing ideas.
"My hope is that we create a system that immediately finds new uses for drugs," he says.
"We have to keep developing new drugs, but right now, in a world where drugs are not fully utilized, we need to do everything we can to use them more fully."
Related: Read more about efforts to find treatments for rare diseases.
More in This Series
Regina Barzilay, PhD
A breast cancer diagnosis seemed to come out of the blue for Regina Barzilay, PhD. That inspired her to develop an AI system to help better predict breast cancers before they start.
Suchi Saria, PhD
Sepsis kills -- as Suchi Saria knows from the tragic death of her own nephew. That's part of the driving force behind the AI tool she helped to develop to detect and stop sepsis in hospitals.