Create your Personal Health Record and unlock support built around you

  • Treatments and trials you qualify for
  • Education for your stage of care
  • Financial support for your medications
  • Solutions to your side effects
Video

AI Using Multimodal Datasets to Predict Response to CAR-T Treatment | Ciara Freeman, MD, PhD

Posted by
HealthTree Logo HealthTree
• December 16, 2025

Description

Can artificial intelligence improve how we predict patient response to CAR-T cell therapy? In this ASH 2025 presentation, Ciara Freeman, MD, PhD, explores how AI models leveraging multimodal data—including clinical characteristics, genomic data, laboratory values, and imaging—can help forecast treatment response, durability, and toxicity following CAR-T therapy. This talk highlights how integrating machine learning and multimodal datasets may enable more personalized treatment strategies

On this video

Transcript

My name is Doctor Ciara Freeman.

I work at the Moffitt Cancer Center in Tampa, Florida, and I'm here at the annual Society of Hematology annual meeting in Orlando, Florida.

And I'm presenting some of our work involving utilizing the new thing on the block, which is artificial intelligence.

So we're looking at trying to incorporate some of these advanced technologies and help us better understand which of the patients receive CAR-T cell therapy.

So that's therapy that we manufacture from a patient's own immune cells and use to fight their cancer.

Can we utilize that technology to teach about a patient's history, about how they are, and then incorporate all of their lab routines under care lab testing, and then layer on top of it some other features that are relatively easy to extract now with these new technologies?

Things like metabolic tumor volume from their standard-of-care PET scans, and clean, bring all of that information together.

In addition, with some biomarkers from their blood, like soluble BCMA, which is something that we can measure now more routinely, and layering all that information to really extract which patients are going to do really well with that CAR-T cell therapy, and which patients are going to need more.

Are they going to need more surveillance, or are they going to need maybe alternative strategies to help them get better duration of response and be less at risk of early treatment failure?

So what we're really trying to do is leverage all of the information that we now have at our fingertips for patients and really try and help patients and physicians understand which patients are going to do really well, and which patients need extra support or alternative treatment strategies, maybe novel trials.

So we're really excited to present these findings at the meeting here.

We're excited to meet with other collaborators and scientists with the same kind of ideas in mind and to really drive the science forward.

If our videos have helped you in any way, and you're able to, please consider making a donation to help us continue this important work.

Your gift will go three times as far when we reach $500,000 by the end of the year.

Every contribution, big or small, makes a difference, and we're deeply grateful for your support.

Related Content