AI-Assisted Diagnosis Could Expand Access to Targeted Breast Cancer Therapy

A groundbreaking study presented at the American Society of Clinical Oncology (ASCO) annual meeting has demonstrated that artificial intelligence (AI) can significantly improve the identification of HER2-low and HER2-ultralow breast cancers, potentially expanding access to targeted therapies for patients previously classified as HER2-negative.

AI Tool Enhances Diagnostic Accuracy

Researchers, led by Marina De Brot from the A.C. Camargo Cancer Center in São Paolo, Brazil, conducted a multinational study involving 105 pathologists from 10 countries. The study evaluated the impact of an AI support tool developed by AstraZeneca and diagnostic company Mindpeak on the accuracy of HER2 expression assessment in breast cancer samples.

The results showed a marked improvement in diagnostic accuracy when pathologists used the AI tool:

• Agreement with expert consensus scores increased from 76% to approximately 90%
• Misidentification of HER2-ultralow cases as HER2-negative decreased by over 25 percentage points

"Our study provides the first multinational evidence that artificial intelligence can help close a critical diagnostic gap and open the door to new therapies like antibody-drug conjugates for a majority of patients who, until recently, had not been offered these options," De Brot stated.

Implications for Targeted Therapy

The improved diagnostic accuracy has significant implications for patient treatment, particularly in light of the recent success of Enhertu, an antibody-drug conjugate developed by AstraZeneca and Daiichi Sankyo. Enhertu has shown efficacy in treating tumors with low and ultra-low levels of HER2 expression, which were previously classified as HER2-negative and ineligible for HER2-targeted therapies.

Julian Hong, associate professor and medical director of radiation oncology informatics at the University of California, San Francisco, emphasized the potential impact: "These findings shed light on the promising role for AI in oncology, not as a replacement for the physician, but as a powerful tool to help us work smarter and faster to deliver high-quality, more personalized care."

Future Directions

The research team plans to expand their study by sharing the AI support tool with more pathologists from additional countries. They also aim to conduct an implementation study to measure the tool's impact on treatment decisions and patient outcomes in routine clinical practice.

As the field of breast cancer diagnosis and treatment continues to evolve, tools like this AI-assisted diagnostic system may play a crucial role in ensuring patients receive the most appropriate and effective therapies available.