ECOG-ACRIN Cancer Research Group and Caris Life Sciences have embarked on a multiyear research collaboration for biomarker analysis of 10,000 tumor tissue samples from the TAILORx breast cancer trial.
Leading the project are Mitchell Schnall, MD, PhD, and Peter O'Dwyer, MD. Both are co-chairs of the ECOG-ACRIN Cancer Research Group and both are from the University of Pennsylvania in Philadelphia.
As part of the collaboration, Caris will perform molecular characterization (whole exome and transcriptome sequencing) on tumor tissues contributed by nearly 10,000 patients with early-stage breast cancer who participated in the TAILORx trial. Participants have been followed for 11 years or more, with planned follow-up for 20 years.
“I’m excited to build on the trial’s initial findings which prevented millions of women with early breast cancer from having to endure toxic treatments, to continue discerning valuable insights related to long-term recurrence risk, and to identify even more women who may benefit from more efficient treatment options,” said George Sledge Jr., MD, executive vice president and chief medical officer of Caris in an announcement released by ECOG-ACRIN.
The Trial Assigning Individualized Options for Treatment, or TAILORx, is one of the world's largest breast cancer research resources, according to the ECOG-ACRIN group, a multidisciplinary scientific organization that designs and conducts cancer research involving adults. ECOG-ACRIN consists of nearly 1,400 academic and community-based cancer centers and hospitals.
The new TAILORx project explores early-stage breast cancer, where the risk of recurrence is a primary concern. Data from the project will be made publicly available after a designated time period following completion of the research project plan.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)






![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)









