Related Experiment Video
Updated: Aug 6, 2026
08:05
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Artificial Intelligence Versus Conventional Methods for NCCN Risk Stratification in Localized Prostate Cancer
Wael A Hassan1,2, Omar A El Meligy3, Iman M Talaat1,2,4
1Department of Clinical Sciences, College of Medicine, University of Sharjah, Sharjah, UAE, sharjah.ac.ae.
Prostate Cancer
|July 22, 2026
Summary
Artificial intelligence (AI) models improve localized prostate cancer risk stratification over traditional methods. Further validation is needed before widespread clinical adoption of these advanced AI tools.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Accurate risk stratification is crucial for localized prostate cancer treatment decisions.
- Current National Comprehensive Cancer Network (NCCN) guidelines use PSA, Gleason grade, and clinical stage.
- Artificial intelligence (AI) methods offer potential alternatives or complements to NCCN risk groups.
Purpose of the Study:
- To systematically review and compare AI-based models with traditional NCCN risk stratification for localized prostate cancer.
- To assess studies published between 2020 and 2025 that directly compare AI and NCCN methods.
- To evaluate the performance of AI models in predicting outcomes like adverse pathology and recurrence.
Main Methods:
- Systematic search of PubMed/MEDLINE, Scopus, and Cochrane Library (Jan 2020-Sep 2025).
- Inclusion of studies on localized prostate cancer comparing AI models with NCCN stratification.
- Exclusion of case reports, nonhuman studies, and abstracts without full data; risk of bias assessed using PROBAST.
Main Results:
- 43 full-text studies met inclusion criteria, comparing AI with conventional methods.
- AI approaches combining MRI radiomics, PET imaging, and digital pathology showed superior discrimination compared to NCCN models.
- AI models demonstrated higher accuracy in predicting adverse pathology and biochemical recurrence.
Conclusions:
- AI-based methods show promise for enhancing NCCN risk stratification in localized prostate cancer.
- AI models offer improved prognostic accuracy over traditional methods.
- Further multi-institutional prospective studies are needed due to variability in methods, limited external validation, and reporting gaps.
