Authors say this classification has the potential to minimize overtreatment and undertreatment<\/p>\n<\/h3>\n
By Lori Solomon HealthDay Reporter<\/b>
\n<\/b><\/p>\n
WEDNESDAY, Nov. 6, 2024 (HealthDay News) — Artificial intelligence (AI)-based risk classification improves prognostication with localized prostate cancer, according to a study published online Oct. 24 in JCO Precision Oncology<\/em>.<\/p>\n 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.<\/p>\n The researchers found that according to National Comprehensive Cancer Network (NCCN) risk categories, 30.4 percent of patients were low-risk, 25.5 percent intermediate-risk, and 44.1 percent high-risk. Based on MMAI risk classification, 43.5 percent of patients were low-risk, 34.6 percent intermediate-risk, and 21.8 percent high-risk, yielding reclassification of 1,039 patients (42.0 percent). The 10-year metastasis risks were comparable despite the MMAI low-risk group being larger than the NCCN low-risk group (1.7 percent for NCCN versus 3.2 percent for MMAI). For NCCN high-risk patients, the overall 10-year metastasis risk was 16.6 percent, with MMAI further stratifying this group into low-, intermediate-, and high-risk, with metastasis rates of 3.4, 8.2, and 26.3 percent, respectively.<\/p>\n “This approach aims to prevent both overtreatment and undertreatment in localized prostate cancer, facilitating shared decision-making,” the authors write.<\/p>\n Several authors disclosed ties to pharmaceutical and biotechnology companies.<\/p>\n