Using AI Predictive Analytics to Transform Patient Care
In this compelling conversation, Dr. David Fajgenbaum describes how his team uses a platform called Matrix, powered by a biomedical knowledge graph, to scan all known relationships between drugs, diseases, and genes. The goal? To apply AI for healthcare data analysis in identifying potential treatments, some of which had been previously overlooked or discarded due to lack of profitability. One powerful example includes the identification of a TNF inhibitor for Castleman disease that led to a lifesaving intervention. Dr. Fajgenbaum emphasizes how this technology doesn't just discover new solutions but also revalidates forgotten ones, shedding light on opportunities to repurpose existing drugs. This showcases the transformative potential of AI predictive analytics in healthcare.
Episode Contents:
About the Guest
David Fajgenbaum, MD, MBA, MSc is a physician-scientist at the University of Pennsylvania, co-founder of Every Cure and the CDCN, and bestselling author of Chasing My Cure.
Notable Quote
AI is really good at just finding patterns that us humans have already found but overlooked.
Key Takeaways
- AI predictive analytics can resurface discarded but effective treatments.
- Biomedical knowledge graphs enhance comprehensive drug-disease analysis.
- Human oversight is essential in validating AI-generated leads.
- Real-world impact includes a lifesaving TNF inhibitor treatment for Castleman disease.
- A disease-agnostic approach lets AI direct attention to overlooked opportunities.
Condensed Transcript
Q: How does AI prediction translate into real-world patient care?
A (Dr. Fajgenbaum): We use a platform called Matrix to analyze a biomedical knowledge graph of drugs, diseases, genes, and proteins. By training algorithms on known treatments, we score the likelihood that a drug might work for a different disease. Out of about 75 million scores, we focus on the highest. This has led to novel discoveries—like using a TNF inhibitor for Castleman disease—and also revived interest in treatments like leucovorin for autism, previously overlooked due to low profitability.
Q: What surprises have come from using this AI system?
A: One surprise is that many "new" predictions from AI are rediscoveries—treatments we’ve already known about but abandoned. For example, leucovorin has shown promise in randomized trials for improving communication in children with autism, yet it hasn’t gained clinical traction. AI helps spotlight these underused solutions.
About the Series
AI and Healthcare—with Mika Newton and Dr. Sanjay Juneja is an engaging interview series featuring world-renowned leaders shaping the intersection of artificial intelligence and medicine.
Dr. Sanjay Juneja, a hematologist and medical oncologist widely recognized as “TheOncDoc,” is a trailblazer in healthcare innovation and a rising authority on the transformative role of AI in medicine.
Mika Newton is an expert in healthcare data management, with a focus on data completeness and universality. Mika is on the editorial board of AI in Precision Oncology and is no stranger to bringing transformative technologies to market and fostering innovation.