Predicting aggressive prostate cancer with AI and biological markers

Dissecting and Predicting Lethal Prostate Cancer using Biologically Informed Artificial Intelligence

NIH-funded research Dana-Farber Cancer Inst · NIH-11182642

This project uses AI combined with genetic tests and tumor tissue scans to predict which men with intermediate or high-risk localized prostate cancer are likely to develop aggressive, life-threatening disease.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionDana-Farber Cancer Inst NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-11182642 on NIH RePORTER

What this research studies

You or other patients' tumor tissue, genetic data, and clinical records will be combined and examined with deep learning models to find patterns that signal high risk of lethal prostate cancer. The team will analyze inherited (germline) and tumor (somatic) DNA changes, gene expression biomarkers, and digital pathology images to train AI to recognize risky combinations. Large, diverse patient groups and known clinical outcomes will be used to teach and test the models. The goal is to create computer tools that could one day help doctors pick the right treatment for each person.

Who could benefit from this research

Good fit: Ideal candidates are men with intermediate or high-risk localized prostate cancer who have available tumor tissue, genetic testing, or detailed clinical outcome records.

Not a fit: Men with very low-risk prostate cancer, widely metastatic disease, or no available tissue/genetic data are less likely to benefit directly from this project.

Why it matters

Potential benefit: If successful, this could help doctors choose more personalized treatments—treating high-risk men more aggressively and avoiding over-treatment for lower-risk men.

How similar studies have performed: Genomic risk tests and AI-based pathology tools have shown promise, but integrating germline and somatic genetics with gene expression and digital histology using biologically informed AI is relatively new and still experimental.

Where this research is happening

Boston, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions Cancer and Leukemia Group B
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.