Key Takeaways
- Percival is an AI model developed at Penn Medicine that extracts hidden health information from routine CT scans beyond the original clinical indication.
- Trained on the Penn Medicine BioBank’s diverse dataset of >350,000 individuals, the model leverages >400,000 CT scans from ~50,000 patients.
- Percival can detect chronic conditions such as atrial fibrillation and chronic kidney disease, and outperforms a comparable model (TotalSegmentator) in flagging pancreatic cancer, cirrhosis, and bacterial pneumonia.
- The technology supports “opportunistic screening,” enabling early identification of disease trajectories and potential complications before symptoms appear.
- Developers aim to test Percival clinically early next year, improve robustness with larger multi‑institution data, and release its code and training specifications as open‑source assets.
- Percival joins a growing portfolio of Penn Medicine AI tools (e.g., AInSights, cardiac‑MRI analyzer) funded by NIH grants, pointing toward a future where medical imaging drives personalized, proactive care.
Overview of Percival’s Capabilities
When analyzed by a new artificial intelligence model developed at Penn Medicine, CT scans reveal much about a patient’s health beyond the specific condition they were originally ordered for, according to a new study published in NPJ Digital Medicine. The AI model, dubbed Percival, can uncover nearly hidden patterns in disease and potential future health risks that might have otherwise gone unnoticed by human eyes. While other models may need to be directed to find certain health conditions or outcomes, Percival can effectively run in the background to pick up what is unseen.
Development Roots and Naming Inspiration
Built on the back of the BioBank, Percival was named as a reference to one of the knights of King Arthur’s Round Table, and also in reverence of the late Eugene Percival Pendergrass, a prominent radiologist and educator at Penn. Walter Witschey, PhD, senior author, associate professor of Radiology and associate vice chair of Research IT, explained, “Our teams have developed something that learns broadly from imaging data and uncovers connections between scans, lab values, people’s physiology, and clinical outcomes to potentially give more accurate assessments of health, or even ring alarm bells early. This is work that points toward a future in which medical imaging becomes a foundation for more personalized and proactive healthcare.”
Training on the Penn Medicine BioBank
With information from more than 350,000 people collected across the University of Pennsylvania Health System over the course of two decades, the BioBank provides an exceptionally diverse source of data for a model like Percival to be built upon. Cameron Beeche, a PhD candidate in Bioengineering at the University of Pennsylvania and lead author, noted, “Research in AI has shown that training on larger, more diverse datasets can improve performance, and this can provide a stronger foundation for adapting a model to a hospital or patient population almost anywhere.” The researchers used roughly 400,000 CT scans from approximately 50,000 patients to hone Percival’s abilities, which are still being tested preclinically.
Opportunistic Screening in Practice
In analyzing Percival’s performance, the Penn Medicine teams were able to show that CT scans contain a plethora of useful information hiding in plain sight. Percival was found to uncover traces of several chronic conditions, including atrial fibrillation (a form of irregular heartbeat) and chronic kidney disease in scans. Witschey elaborated on the vision: “We’re hoping to elevate ‘opportunistic screening,’ where results are found beyond the original purpose of a scan, such as finding the early traces of cancer on a scan that was maybe assessing pneumonia. We believe the totality of what’s in a CT scan can be made much more useful with help from a model like this.”
Superior Detection Compared to Existing Models
Additionally, when compared to a similar AI model called TotalSegmentator, Percival was found to flag conditions like pancreatic cancer, cirrhosis, and bacterial pneumonia much more reliably. Charles Kahn, MD, a professor of Radiology and co‑author, emphasized the clinical relevance: “Percival can help identify unrecognized disease, predict future progression, and anticipate major cardiovascular and liver complications. Because many patients already have substantial heart or metabolic disease when they enter specialty care, routine imaging may provide an opportunity for earlier recognition and intervention.”
Path Toward Robustness and Clinical Deployment
The developers behind Percival are hoping to test it early next year with an eye toward bringing the model into the clinic for regular use. They believe their work in another Penn Medicine‑developed AI radiological solution, AInSights, will help them in this process. In the meantime, the team is examining how even larger data models and those spanning multiple institutions could make Percival more robust and predictive. Percival’s code and training model specifications are open source, which could also help it improve. Witschey affirmed the collaborative ethos: “Percival benefited enormously from researchers who shared their code, methods, and insights into these types of models. We believe strongly in contributing to that same spirit of open science.”
Expanding Penn Medicine’s AI Portfolio
Penn Medicine’s portfolio of AI models built to uncover more information from scans continues to grow. In addition to AInSights and Percival, developers at Penn Medicine also recently developed a model built specifically to analyze cardiac MRI scans and help diagnose new conditions. A test found that it had near-perfect accuracy in its diagnoses. This work is supported by the National Institutes of Health (NIH) Office of the Director under award OT2OD038048 and the National Institute of Biomedical Imaging and Bioengineering under award R21EB036734.
Implications for Future Healthcare
Taken together, the advances represented by Percival signal a shift toward imaging‑driven, proactive medicine. By extracting latent signals from routine CT scans, the model enables clinicians to anticipate disease trajectories, intervene earlier, and tailor preventive strategies to individual risk profiles. As Witschey succinctly put it, the research “points toward a future in which medical imaging becomes a foundation for more personalized and proactive healthcare.” If the upcoming clinical trials validate these preliminary findings, Percival could become a routine adjunct to radiology reports, turning every scan into a comprehensive health snapshot.
https://www.news-medical.net/news/20261020/New-AI-model-detects-hidden-diseases-in-routine-CT-scans.aspx