Artificial intelligence (AI)-based risk classification improves prognostication with localized prostate cancer, according to a study published online Oct. 24 in JCO Precision Oncology . Jonathan David Tward, M.
D., Ph.D.
, from the University of Utah in Salt Lake City, and colleagues developed a clinically usable risk grouping system using multimodal AI (MMAI) models to risk-stratify localized prostate cancer. The analysis included 9,787 patients with localized prostate cancer from eight phase 3 trials treated with radiation therapy , androgen deprivation therapy, and/or chemotherapy followed for a median 7.9 years.
The researchers found that according to National Comprehensive Cancer Network (NCCN) risk categories, 30.4% of patients were low-risk, 25.5% intermediate-risk, and 44.
1% high-risk. Based on MMAI risk classification, 43.5% of patients were low-risk, 34.
6% intermediate-risk, and 21.8% high-risk, yielding reclassification of 1,039 patients (42.0 %).
The 10-year metastasis risks were comparable despite the MMAI low-risk group being larger than the NCCN low-risk group (1.7% for NCCN versus 3.2% for MMAI).
For NCCN high-risk patients, the overall 10-year metastasis risk was 16.6%, with MMAI further stratifying this group into low-, intermediate-, and high-risk, with metastasis rates of 3.4, 8.
2, and 26.3%, respectively. "This approach aims to prevent both overtreatment and undertreatment in localized prostate cancer , facilitating shared decision-making," the authors write.
Several authors disclosed ties to pharmaceutical and biotechnology companies . More information: Jonathan David Tward et al, Prostate Cancer Risk Stratification in NRG Oncology Phase III Randomized Trials Using Multimodal Deep Learning With Digital Histopathology, JCO Precision Oncology (2024). DOI: 10.
1200/PO.24.00145 © 2024 HealthDay .
All rights reserved..
Health
AI aids risk prediction classification for prostate cancer
Artificial intelligence (AI)-based risk classification improves prognostication with localized prostate cancer, according to a study published online Oct. 24 in JCO Precision Oncology.