Tempus AI, Inc. (NASDAQ: TEM) presented results from a study evaluating an AI-enabled pre-screening panel for patients with advanced non-small cell lung cancer (NSCLC) at the European Society for Medical Oncology Congress in Madrid.

The study analyzed 60,459 advanced NSCLC cases across 56,969 patients from multiple centers. The AI panel, which uses routinely generated hematoxylin and eosin pathology whole slide images, achieved greater than 80% sensitivity across all 12 biomarkers assessed, with sensitivity exceeding 90% for several biomarkers.

The panel is designed to help clinicians prioritize diagnostic testing and identify patients who may need confirmatory biomarker testing, without replacing established molecular or immunohistochemistry testing.

"Precision medicine only works when clinicians have the right information at the right time," said Ezra Cohen, MD, Chief Medical Officer of Oncology at Tempus. "These findings demonstrate the potential for AI to extract meaningful information from a pathology image that is already part of routine care and help clinicians determine what testing may be most important next."

The study was conducted through a collaboration between Tempus and Pfizer focused on addressing diagnostic barriers and supporting biomarker testing. The H&E pre-screening panel remains in development.

Tempus also referenced two related products: Paige Predict, used in clinical laboratory testing to predict the likelihood of 123 biomarkers across multiple cancer types, and Tempus Preview, which provides early biomarker predictions approximately 24 hours after sample receipt.