Journal of Clinical Oncology Publishes Significant Evidence in Advancing Racial Equity in Cancer Care Through Artera's Multimodal AI Model

• The validation study shows no evidence of algorithmic bias.
• The development of the model may help mitigate the risk of racial bias in treating prostate cancer patients.
• This is the first comparative analysis of a large digital pathology AI prognostic model in African American versus non-African American patients with prostate cancer.

SAN FRANCISCO--(BUSINESS WIRE)--Artera, the developer of multimodal artificial intelligence (MMAI)-based prognostic and predictive cancer tests, announced the publication of a validation study in the JCO Clinical Cancer Informatics on Artera’s MMAI model. The study assessed the ability of the MMAI model to perform similarly across racial subgroups using data from prostate cancer trials with diverse representation.

AI tools are becoming instrumental in helping with clinical decision-making, but there are ongoing concerns that they could also exacerbate inequities due to racial bias. This is an especially prevalent concern, as many AI tools were developed with datasets that are not representative of the real world. In particular, African American men have been reported to have a worse prognosis for prostate cancer; this is due to several reasons, including underrepresentation in the development of AI and genomic biomarkers.

“It’s important to conduct studies to ensure new clinical decision support tools work well across a diverse patient population,” said Mack Roach III, Professor of Radiation Oncology and Urology at the University of California San Francisco, and lead investigator for the study. “Especially in the realm of AI, where there can be a lot of healthy skepticism, this study is reassuring to African American men that they too will benefit from using advanced risk stratification tools from Artera.”

For the study, a total of 5,708 patients from five randomized Phase 3 clinical trials were included. The MMAI algorithm demonstrated a significant ability to predict the likelihood of distant metastasis (DM) and prostate cancer specific mortality (PCSM) in both African American and non-African American patients with prostate cancer. These findings suggest that the MMAI algorithm is a powerful tool for identifying patients at higher risk of metastasis and/or death, allowing clinicians to tailor treatment plans more effectively. The algorithm's ability to predict outcomes across diverse populations also emphasizes its potential to improve personalized care for prostate cancer patients, regardless of race.

“We’re thrilled to have this important validation study published as we continue our ongoing validation efforts across additional racial subgroups,” said Timothy Showalter, Chief Medical Officer at Artera. “As the leader in leveraging AI for more personalized care, this work is crucial to ensure our tools are broadly representative.”

Artera remains committed to incorporating diverse datasets in the training and validation of its AI model. The company has partnered with organizations globally to access diverse data to ensure its MMAI model is trained on datasets that properly represent diverse patient populations.

For more information on Artera, visit Artera.ai.

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.

Artera’s laboratory is CLIA-certified and College of American Pathologists (CAP) accredited. The ArteraAI Prostate Test is clinically available through Artera’s laboratory in Jacksonville, Florida, and can be ordered online at Artera.ai