Turn on cookies to sign in
Signing in saves your progress to your Curie account. We can only do that with cookies on — turn them on to continue.
AI is already changing the game in CAR T-cell therapy research, revealing limitations that computer models alone can't catch. At ACR Convergence, CHAI's Brian Anderson, MD, highlighted how AI-designed models are exposing real-world drug design flaws — and why physician oversight, regulatory sandboxes, and public-private partnerships are critical to making AI in healthcare trustworthy and effective.
AI is no longer just a buzzword in medicine — it's actively reshaping how next-generation therapies like CAR T-cell treatments are designed and tested. At ACR Convergence 2026, Brian Anderson, MD, president and CEO of the Coalition for Health AI (CHAI), delivered a keynote highlighting how AI is already influencing drug research, particularly in rheumatology.
Anderson described an AI model that evaluated over 1,700 binders targeting key proteins involved in CAR T-cell therapy. While the computational design was powerful, real-world experiments revealed critical flaws — including off-target activity, unwanted signaling, and inaccessible epitopes — that the AI alone couldn't detect. The takeaway: AI and human experimentation must work hand in hand.
Key Takeaways:
Why it matters: As AI tools become embedded in drug development and clinical care, getting governance right is essential. Anderson's call for physician and patient voices in AI development — alongside regulatory oversight — underscores that the future of treatments like CAR T-cell therapy depends not just on the technology, but on the trust built around it.
