Prostate cancer is the most commonly diagnosed male malignancy, with over 25,500 cases estimated in Australia in 2023. Although frequently slow-growing and often manageable with effective treatments, prostate cancer remains the leading cause of cancer-related disability worldwide.
This high incidence of disability primarily results from the adverse outcomes linked to both over- and under-treatment. The majority of prostate cancers are diagnosed with local disease and the management for cure can either be surgery or radiotherapy, sometimes in combination with androgen deprivation therapy (ADT).
Understanding ADT in prostate cancer treatment is important. Short-term ADT (4-6 months) has been shown to improve disease outcomes when added to radiation therapy for patients with intermediate risk localised prostate cancer.
However, ADT is associated with several risks, including weight gain, decreased bone mineral density, decreased insulin sensitivity, and a worsening lipid profile. These complications can negatively impact patients’ quality of life and can be a significant burden on healthcare systems.
Potential adverse effects of ADT include acute myocardial infarctions, fractures and the necessity for medications to manage glucose tolerance, blood pressure and cholesterol levels, as well as to mitigate ADT side effects such as hot flashes.
The challenge lies in identifying the patient population that will benefit most from ADT treatment intensification when combined with radiotherapy.
ArteraAI prostate test
The ArteraAI prostate test represents an advancement in the management of prostate cancer. Developed using a multi-modal AI (MMAI) deep learning architecture, this test leverages both clinical and imaging data. It comprises two AI models: a prognostic model that estimates the risk of distant metastasis and prostate cancer-specific mortality, and a hormone therapy benefit model that provides a binary result on the likelihood of benefit from short-term ADT after radiation.
The AI models were trained and validated using data from five phase III randomised controlled trials (NRG/RTOG 9202, 9408, 9413, 9910, and 0126), involving a total of 5654 patients and a dataset of 16,204 histopathology slides. The test uses clinical variables such as combined Gleason score, primary and secondary Gleason scores, clinical T-stage, baseline PSA, and age.
It employs two distinct machine learning pipelines: one for pathological image analysis and another for the combined clinical and image data analysis. The AI systems independently generate MMAI scores for distant metastasis and prostate cancer-specific mortality.
The ArteraAI prostate test is endorsed by the National Comprehensive Cancer Network (NCCN) guidelines for prostate cancer. This biomarker test has the potential to change staging and prognostication in prostate cancer. Utilising this test could allow lower-risk patients to be treated with radiotherapy alone, avoiding the toxicities associated with combined radiotherapy and ADT.
Conversely, it can also select patients who would benefit from treatment intensification, thereby improving outcomes related to distant metastasis and prostate cancer-specific mortality. This would suggest improvements in health and economic outcomes and help standardise management decisions among clinicians.
ASTuTE clinical trial
The ASTuTE clinical trial is a research study collecting de-identified health information, treatment recommendations and decisions to assess the clinical utility of the ArteraAI prostate test in managing short-course ADT for intermediate-risk prostate cancer. The study will enrol 800 participants across NSW, VIC, SA, QLD and WA.
The research will investigate how the ArteraAI prostate test affects doctors’ treatments recommendations, and what the outcomes for patients are five years after having the test.
To be eligible, patients must meet the following guidelines:
- Adult males over 18 years of age
- Intermediate-risk, localised adenocarcinoma of the prostate according to NCCN risk stratification
- Absence of high-risk and very high-risk group features
- Presence of one or more intermediate-risk factors:
– Clinical stage cT2b-cT2c based on digital rectal exam
– Grade Group 2 or 3 (Gleason Score 7 {3+4} or 7 {4+3})
– PSA 10-20 ng/mL
The ArteraAI prostate test is a promising tool in the landscape of prostate cancer treatment. Its ability to refine patient stratification and optimise treatment plans could significantly improve patient outcomes and reduce the burden of ADT-related toxicities. As the ASTuTE trial progresses, it’s real-world utility and impact will become clearer.
Key messages
- Much prostate cancer disability is related to adverse treatment outcomes from over or under treatment
- The ArteraAI prostate test represents an advancement in management of prostate cancer
- The ASTuTE trial is recruiting in Australia-wide including WA.
– References available on request
Author competiting interests – nil