Penn's Percival AI Flags Hidden Disease Signals in Routine CT Scans

Oct 20, 2026
Penn Medicine researchers developed Percival, an AI model that finds signs of chronic disease and future health risks in routine CT scans. The model remains in preclinical testing.

Researchers at University of Pennsylvania developed Percival, an AI model that identifies disease signals and potential health risks in routine CT scans, according to News Medical. The study was published in npj Digital Medicine.

The researchers trained Percival using roughly 400,000 CT scans from about 50,000 patients. The model identified signs associated with conditions including atrial fibrillation and chronic kidney disease. It also flagged pancreatic cancer, cirrhosis, and bacterial pneumonia more reliably than the comparable TotalSegmentator model.

Percival remains in preclinical testing. The researchers plan further testing in early 2027 before pursuing regular clinical use, while also studying larger data sets from multiple institutions. Its code and training specifications are available as open source software.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Healthcare & Life Sciences AI AI Brief AI Brief (X)
Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.