ASCO 2023 | AI biomarker predicts benefit of long-term ADT in prostate cancer

Andrew J. Armstrong, MD, MSc, Duke Cancer Institute, Durham, NC, shares an overview of a study aiming to development and validate an AI-derived digital pathology-based biomarker to predict benefit of long-term androgen deprivation therapy with radiotherapy in men with localized high-risk prostate cancer across multiple Phase III NRG/RTOG trials.The researchers utilized digitized pre-treatment prostate biopsy slides from multiple phase III trials and trained an artificial intelligence (AI)-derived biomarker to predict the differential benefit of long-term (LT) ADT on distant metastasis (DM). The biomarker was then validated on a separate trial. Results showed that the AI biomarker accurately predicted the benefit of LTADT, allowing for personalized treatment decisions. The biomarker identified subgroups of patients who could derive similar benefits with short-term ADT, avoiding unnecessary side effects. This study demonstrates the potential of AI-derived biomarkers in guiding ADT duration for improved patient outcomes. This interview took place at the American Society of Clinical Oncology (ASCO) 2023 Annual Congress 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.