Related Experiment Video
Updated: Jul 4, 2025
07:25
A Bioluminescent and Fluorescent Orthotopic Syngeneic Murine Model of Androgen-dependent and Castration-resistant Prostate Cancer
Published on: March 6, 2018
13.1K
Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer.
Daniel E Spratt1, Siyi Tang2,3, Yilun Sun1,4
1Department of Radiation Oncology, University Hospitals Seidman Cancer Center, Case Western Reserve University, Cleveland.
NEJM Evidence
|February 6, 2024
Summary
An artificial intelligence model can predict which prostate cancer patients benefit from androgen deprivation therapy (ADT) combined with radiotherapy. This AI tool helps personalize treatment, improving outcomes and quality of life for localized prostate cancer patients.
Area of Science:
- Oncology
- Artificial Intelligence in Medicine
- Digital Pathology
Background:
- Androgen deprivation therapy (ADT) combined with radiotherapy offers benefits for localized prostate cancer.
- However, ADT can negatively impact patient quality of life.
- Validated predictive models are needed to guide ADT use effectively.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI)-derived predictive model for patient-specific benefit from ADT.
- The model aims to identify patients likely to develop distant metastasis, guiding ADT decisions.
Main Methods:
- Utilized digital pathology images and clinical data from 5727 patients across five phase 3 trials.
- Developed an AI model using baseline data to predict individual patient response to ADT.
- Validated the model on the NRG/RTOG 9408 trial (n=1594) with a median follow-up of 14.9 years.
Main Results:
- The AI model identified a subgroup of patients (34%) who significantly benefited from ADT.
- In model-positive patients, ADT reduced the risk of distant metastasis compared to radiotherapy alone.
- Patients identified as model-negative (66%) did not show benefit from ADT.
Conclusions:
- An AI-based predictive model can identify patients, particularly those with intermediate-risk prostate cancer, who are likely to benefit from short-term ADT.
- This AI tool facilitates personalized treatment strategies, potentially improving outcomes and minimizing side effects.
- The findings support the integration of AI in clinical decision-making for localized prostate cancer management.
