Educational content on VJOncology is intended for healthcare professionals only. By visiting this website and accessing this information you confirm that you are a healthcare professional.

Share this video  

ASCO 2026 | MMAI model validation for chemotherapy benefit prediction in breast cancer

Corey Speers, MD, PhD, University of Alabama at Birmingham, Birmingham, AL, presents external validation of a multimodal artificial intelligence (MMAI) prognostic model using data from the Phase III SWOG S8814 trial (NCT00929591) evaluating postmenopausal women with node-positive HR-positive (HR+) breast cancer. Results confirmed MMAI’s prognostic value for disease-free and overall survival, and its ability to identify patients most likely to benefit from adjuvant chemotherapy, supporting MMAI as a scalable, cost-effective alternative to genomic testing in this setting. This interview took place during the 2026 American Society of Clinical Oncology (ASCO) Meeting in Chicago, IL.

These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.

Transcript

This is a trial in which we validated a multimodal artificial intelligence test, the Artera AI breast test, in patients with ER positive or estrogen receptor positive, hormone receptor positive, node-positive breast cancer. And really the purpose of this study was to identify patients for whom chemotherapy provided the most benefit. We know that in patients with node-positive disease, there’s heterogeneous benefit with chemotherapy in these patients...

This is a trial in which we validated a multimodal artificial intelligence test, the Artera AI breast test, in patients with ER positive or estrogen receptor positive, hormone receptor positive, node-positive breast cancer. And really the purpose of this study was to identify patients for whom chemotherapy provided the most benefit. We know that in patients with node-positive disease, there’s heterogeneous benefit with chemotherapy in these patients. We really wanted to identify the patients that derive the most benefit from treatment in an effort to identify patients for whom treatment de-escalation might be appropriate. That is, patients with one to three nodes positive, for example, might not need chemotherapy. How do we identify the patients that are going to benefit from it from those that are not? And that was the purpose of the study. And so this test had previously been validated for prognosis in the ABCSG8 breast trial. It had been validated for chemotherapy benefit in the NSABP B20 trial in women with node-negative breast cancer. This was an extension of that study into women with higher-risk node-positive breast cancer, again, trying to answer that question of who benefits from chemotherapy and who does not. So with that locked model in the MammaPrint model, we then asked the question, can we identify patients at low risk of recurrence at five and 10 years with disease-free survival and overall survival? And we were able to show that in the MammaPrint low-risk group, they had no benefit from chemotherapy and are appropriately candidates for de-escalation of therapy. In the MammaPrint high-risk or non-low-risk group, those were the patients that were deriving the most benefit from chemotherapy in the SWOG 8814 trial. And therefore, we can potentially use MammaPrint as a risk stratifier, not just for prognosis, but also benefit from chemotherapy in that patient population.

This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.

Read more...