Peer-influenced content. Sources you trust. No registration required. This is HCN.

NEJM EvidenceArtificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer

In recent studies, a multimodal artificial intelligence (MMAI) system was used to develop and validate models that surpassed the National Comprehensive Cancer Network (NCCN) risk groups in determining which men would benefit from ADT.

In the pursuit of personalized treatment for localized prostate cancer, a predictive model has been developed and validated to guide the use of androgen deprivation therapy (ADT) with radiotherapy. Utilizing digital pathology and artificial intelligence (AI), the model can potentially help identify patients who would derive significant benefits from ADT, enhancing treatment efficacy and limiting exposure to unnecessary side effects.

Key Points:

  • Trials have consistently shown oncologic benefits from adding ADT to radiotherapy for localized prostate cancer, despite no way to identify which patients specifically benefit from this approach.
  • Using data from multiple NRG Oncology North American phase 3 randomized trials, a predictive model was trained to identify men with localized prostate cancer likely to benefit from the addition of ADT to radiotherapy.
  • An AI-based predictive model was developed and validated, capable of identifying a differential benefit from the addition of short-term ADT to radiotherapy in localized prostate cancer.

Additional Points:

  • ADT has known toxicity effects, including hot flashes, libido loss, muscle mass decrease, body fat increase, osteoporosis, and potential harmful effects on cardiac and brain health.
  • Gleason grading has modest prognostic ability, and tissue-based gene expression, serum, and imaging biomarkers have been developed but not yet shown to function as predictive biomarkers for ADT use.
  • The majority of men with localized prostate cancer treated with radiotherapy alone without ADT never develop distant metastasis.


  • This AI-based predictive model could represent a significant advancement in personalizing treatment for localized prostate cancer. By accurately predicting which patients will benefit from ADT with radiotherapy, the model can inform a more targeted approach to treatment, improving outcomes and minimizing unnecessary side effects.

Urology Latest Posts

Did You Know?
Approximately one in every nine men will be diagnosed with prostate cancer during his lifetime.

The Healthcare Communications Network is owned and operated by IQVIA Inc.

Click below to leave this site and continue to IQVIA’s Privacy Choices form