Tempus AI has entered a research collaboration with Angiosarcoma Awareness to accelerate data-driven research in angiosarcoma, a rare malignant tumor known for its aggressive behavior and poor prognosis. The partnership aims to address the lack of molecular understanding and limited access to data that hinder research on rare cancers. By combining resources, the initiative seeks to identify biological patterns and potential therapeutic opportunities that are difficult to detect in smaller, fragmented datasets.

The collaboration will leverage Tempus’ robust datasets and compute and analytical resources to deepen understanding of angiosarcoma biology. This includes access to approximately 600 de-identified angiosarcoma records, each with paired DNA and RNA sequencing data. Associated de-identified clinical information is also included where available, creating one of the largest known disease-specific molecular datasets for angiosarcoma.

Angiosarcoma starts in endothelial cells, which form the inner lining of blood vessels, and is diagnosed in only about 1,000 people in the U.S. each year. Key challenges in studying rare cancers include the absence of effective pre-clinical models and the difficulty of detecting patterns in limited data. This initiative is designed to overcome those barriers by providing researchers with a comprehensive molecular and clinical dataset.

Key Data Components

The collaboration provides access to the following resources:

The dataset is expected to support researchers in identifying potential therapeutic opportunities and advancing the understanding of angiosarcoma biology.

Tempus AI, Inc. announced the publication of a successful multi-site software validation study titled "Multi-Center Validation of an Artificial Intelligence-Enabled ECG Model to Predict 1-Year Risk of Atrial Fibrillation or Flutter" in Heart Rhythm. The study evaluated the Tempus ECG-AF software across three geographically distinct clinical sites, demonstrating the technology's ability to identify patients at risk of atrial fibrillation (AF), a prevalent cardiac arrhythmia associated with increased risks of stroke, heart failure, and death. The resulting data supported Tempus' U.S. Food and Drug Administration clearance of the ECG-AF technology received in 2024.

The application of artificial intelligence to electrocardiogram (ECG) interpretation offers a promising avenue for improving diagnosis, particularly given that AF is frequently asymptomatic and paroxysmal. The study aggregated ECG data and involved manual review of patient charts to identify eligible participants aged 65 and older with no prior AF and no history of pacemaker or defibrillator use.

Study Methodology and Endpoints

The study focused on a specific patient demographic and defined clear endpoints to measure the software's efficacy. The primary goal was to determine if the Tempus ECG-AF software could accurately predict the likelihood of AF development within a specific timeframe.

Key Findings and Regulatory Impact

Among the 4,017 patients evaluated, the ECG-AI-derived risk score surpassed pre-specified performance thresholds. "This study marks an important step toward shifting cardiac care from late-stage intervention to early risk detection," said Brandon Fornwalt, MD, PhD, SVP of Cardiology at Tempus and a coauthor of the study. "The ability of our AI model to consistently predict atrial fibrillation across varied clinical environments highlights its potential as a dependable decision-support tool."

The Tempus ECG-AF was the first FDA-cleared ECG-AI device in Tempus' growing portfolio of next-generation devices designed to identify patients at risk for a variety of cardiovascular conditions.