A research team from the University of Pennsylvania's Perelman School of Medicine utilized artificial intelligence (AI) and machine learning to identify adalimumab—a monoclonal antibody approved by the FDA for conditions such as Crohn's disease and arthritis—as the top-predicted treatment likely to be effective for iMCD, according to a study published in The New England Journal of Medicine (NEJM).
Image Credit: Nemes Laszlo/Shutterstock.com
An artificial intelligence tool found a medication that saved a patient's life with idiopathic multicentric Castleman's disease (iMCD) after searching through 4,000 existing medications. There are not many treatment options for this uncommon illness, and its survival rate is particularly low. With the potential to be applied to other uncommon conditions, the patient may be the first of many whose lives are saved by an AI prediction system.
The study team's parallel experiments also revealed that tumor necrosis factor (TNF), a particular protein adalimumab inhibits, may contribute to iMCD. In patients with the most severe types of iMCD, they found increased levels of TNF signaling. Subsequent investigation revealed that when immune cells from iMCD patients are activated, they generate more TNF than healthy cells.
The study's senior author, David Fajgenbaum, MD, an Associate Professor of Translational Medicine and Human Genetics, and the patient's doctor, Luke Chen, MD, a Hematologist at Vancouver General Hospital in Vancouver, BC, considered these results and decided to test TNF inhibitor in an iMCD patient for the first time.
The patient in this study was entering hospice care, but now he is almost two years into remission. This is remarkable not just for this patient and iMCD, but for the implications it has for the use of machine learning to find treatments for even more conditions.
David Fajgenbaum, MD, Associate Professor, Translational Medicine and Human Genetics, University of Pennsylvania
Fajgenbaum is also the co-founder of a non-profit called Every Cure.
Drug repurposing is the process of using an existing medication for a purpose different from its original intent. Even though the symptoms, prognosis, and causes of many diseases may differ greatly, they may have some underlying similarities in the body, such as common genetic mutations or molecular triggers, that allow them to be treated with the same medication.
Over ten years ago, Fajgenbaum, who has iMCD himself, discovered a life-saving, repurposed treatment through his research that has kept him in remission ever since. To access more life-saving repurposed treatments, he co-founded Every Cure and joined the faculty at the University of Pennsylvania. To evaluate approved drugs that may be used as potential treatments for individuals with rare diseases, the organization aims to use artificial intelligence's capacity to analyze enormous volumes of data.
The AI platform utilized in this study was developed based on groundbreaking work by Research Assistant Chunyu Ma and Associate Professor David Koslicki of Penn State University's Huck Institute of the Life Sciences and Computer Science and Engineering, Biology.
One More Try
After several treatments failed him over time, the patient in this study was about to enter hospice care.
Idiopathic multicentric Castleman’s disease is a cytokine storm disorder. During cytokine storms, an overabundance of inflammatory cytokines, immune system proteins involved in cell communication, is released. This is characterized by an exaggerated and detrimental immune system response that can harm the body's tissues and organs. In people with iMCD, this can lead to life-threatening multi-organ failure, lymph node swelling, and inflammation throughout the body.
Before receiving adalimumab treatment, the patient in the study had encountered these problems.
The Next Steps
Even though only 5,000 cases of Castleman's disease are diagnosed in the US annually, this study's results could save the lives of many more people.
There are probably a few hundred patients in the United States and few thousand patients around the world who, each year, are in the midst of a deadly flare-up like this patient had been experiencing. More research is needed, but I’m hopeful that many of them could benefit from this new treatment.
David Fajgenbaum, MD, Associate Professor, Translational Medicine and Human Genetics, University of Pennsylvania
The study emphasizes the power of combining various scientific methods rather than relying solely on artificial intelligence, lab work, or clinical research techniques.
Fajgenbaum and colleagues are preparing to begin a clinical trial this year to examine the impact of a different repurposed medication on iMCD. This time, the drug in question is a JAK1/2 inhibitor.
The study was funded by the National Heart, Lung, and Blood Institute, Food and Drug Administration, National Center for Advancing Translational Sciences (NCATS), Advanced Research Projects Agency for Health, the Chan Zuckerberg Initiative, Lyda Hill Philanthropies, Arnold Ventures, the Elevate Prize Foundation, the Carolyn Smith Foundation, and the Castleman Disease Collaborative Network.
Journal Reference:
Mumau, M. D., et al. (2025) Identifying and Targeting TNF Signaling in Idiopathic Multicentric Castleman’s Disease. New England Journal of Medicine. doi.org/10.1056/nejmc2412494.