Artera, the developer of multimodal artificial intelligence (MMAI)-based prognostic and predictive cancer tests, will present two oral abstracts at the 2024 American Society for Radiation Oncology Annual Meeting (ASTRO).
Artera’s MMAI platform applies AI to images of hematoxylin and eosin (H&E)-stained pathology slides. The AI-enabled algorithms use these digitized images of the H&E slides, along with the patient’s clinical data to provide personalized insights.
The data to be presented validates the MMAI biomarker’s ability to help inform treatment decisions for patients with oligometastatic castration-sensitive prostate cancer (omCSPC), including metastasis-directed therapy (MDT) benefit. OmCSPC is an early stage of metastatic prostate cancer and providing treatment at this stage of the disease can be vital to prevent cancer from spreading further. MDT is often used as a treatment option for this type of cancer and involves directly treating metastatic lesions with radiation or surgery.
“We’re thrilled to present our latest data at ASTRO 2024, showcasing how Artera’s biomarker can help address the specific needs of this unique patient population, while also addressing the explainability of the AI algorithm,” said Andre Esteva, CEO of Artera. “Patients with omCSPC are at a pivotal point in their cancer journey, and it is our privilege to leverage our digital pathology AI to empower them and their clinicians with personalized insights to guide more tailored treatment plans.”
Key takeaways from the abstracts include:
- The biomarker was validated as prognostic for overall survival (HR=4.38, p=0.022)
- It was also validated as predictive for MDT in omCSPC, as patients with high MMAI (HR=0.32, 95% CI=0.12-0.90; p=0.03) showed therapeutic benefit, but not in patients with low MMAI (HR=1.59, 95% CI=0.63-4.04; p=0.33), demonstrating an improvement in metastasis free survival when treated with MDT (p-interaction=0.02).
- The biomarker aligns with established genomic mutations associated with cancer aggressiveness, with DNAseq showing that a high MMAI score (top median or quartile) had a trend towards more WNT pathway (APC/CTNNB1) mutations or had significantly more BRCA2/ATM mutations than those with low MMAI scores (p=0.13 and p=0.008, respectively). Patients with low MMAI (<median) score had more SPOP mutations, which are known to correlate with better prognosis (p=0.03). This shows the biomarker is detecting patterns closely corresponding to well-known biological pathways.
“The findings from this research validate the ability of the MMAI biomarker to help personalize treatments for patients with omCSPC in the future,” said Dr. Phuoc Tran, Professor and Vice Chair of Research at the University of Maryland Greenebaum Comprehensive Cancer Center. “These data demonstrate the power of the biomarker to predict which patients will benefit from MDT and understanding that the AI algorithm is detecting the mutations and transcriptional pathways associated with metastasis should give clinicians and patients greater confidence in its use.”
ASTRO will be held Sept. 29 - Oct. 2, 2024, at the Walter E. Washington Convention Center, Washington, DC. These two oral abstracts will be presented on Oct. 2. To learn more, visit Artera’s booth, #2606, at the conference, or visit Artera.ai to find out more about the commercially available ArteraAI Prostate Test. Details on each abstract are below:
Validation of a digital pathology-based multimodal artificial intelligence model in oligometastatic castration-sensitive prostate cancer, including in patients from the STOMP and ORIOLE phase II randomized clinical trials (Abstract 334)
Several randomized trials have demonstrated improvements in progression-free survival in patients with omCSPC treated with MDT. However, clinical outcomes can differ and response to MDT is variable, raising the need for prognostic and predictive biomarkers. The MMAI biomarker that leverages digital pathology and clinical variables was trained using data from patients with localized prostate cancer and found to be prognostic.
Results showed that the Artera MMAI biomarker is prognostic for overall survival in patients with omCSPC. Further, MMAI is predictive of benefit from MDT with high MMAI scores demonstrating a greater improvement in metastasis-free survival following MDT. Further work in validating these findings is warranted to allow for greater personalization in the management of patients with omCSPC.
A digital pathology multimodal artificial intelligence algorithm is associated with pro-metastatic genomic pathways in oligometastatic prostate cancer (Abstract 333)
Artera’s MMAI algorithm, which incorporates digital pathology and clinical information, has been shown to be prognostic in localized prostate cancer. Researchers have now evaluated the association between the MMAI score and vector features (VF) of the score with genomics in omCSPC.
Findings concluded that the digital pathology MMAI algorithm validated on localized castration-sensitive prostate cancer is also prognostic in omCSPC and the MMAI scores are correlated with mutations and transcriptional programs in metastatic pathways (e.g. WNT, BRCA2/ATM, EMT) in metachronous omCSPC. These data suggest that digital pathology-based MMAI algorithms identify phenotypic pathologic features that are representative of underlying biological genomic and transcriptomic pathways.
About Artera
Artera is a leading precision medicine company developing AI tests to personalize cancer therapy. Artera offers an AI-enabled test that is the first of its kind to provide both prognostic and predictive results for patients with localized prostate cancer: ArteraAI Prostate Test.
Artera’s multimodal artificial intelligence (MMAI) biomarker test leverages a unique algorithm that assesses digital images from a patient’s biopsy and their clinical data. The AI combines this information to determine their prognosis and predict whether a patient will benefit from a particular therapy and has been validated using many Phase 3 randomized trials.
ArteraAI Prostate Test is the first test that can both prognosticate long-term outcomes and predict therapy benefit in localized prostate cancer. The test is clinically available through our CLIA-certified laboratory in Jacksonville, Florida and can be ordered online at Artera.ai.
View source version on businesswire.com: https://www.businesswire.com/news/home/20240927485612/en/