Researchers from the Technion- Dr. Gil Shamai, Prof. Ron Kimmel, and Prof. Dvir Aran – have developed a novel artificial intelligence model that can predict, on a personalized basis, the expected benefit of chemotherapy for patients with early-stage breast cancer.
The model relies on tissue samples that are routinely collected during diagnosis and provides, within minutes, an accurate assessment of recurrence risk and the likelihood of benefiting from treatment.
The system, the result of extensive international collaboration, was trained on more than 170,000 samples and validated on thousands of patients from hospitals in Israel and worldwide.
The study, published in the prestigious journal The Lancet Oncology, also leveraged data from the large-scale randomized clinical trial, enabling researchers to demonstrate for the first time that an AI-based model can not only assess risk but also predict actual treatment benefit.
Unlike costly and complex genomic tests, the model developed by Dr. Gil Shamai, Prof. Ron Kimmel, and Prof. Dvir Aran offers a faster, more accessible, and more affordable solution based on digital analysis of pathology images.
This approach has the potential to reduce unnecessary treatments, minimize side effects, and improve patients’ quality of life, while more accurately identifying those who are likely to benefit from chemotherapy.
The researchers are now working to implement the technology in healthcare systems in Israel and globally, while also expanding it to additional cancer types and treatments.
This development highlights the transformative potential of integrating artificial intelligence with clinical medicine and marks a significant step toward making personalized medicine widely accessible.
