AI that combines past and current scans and records to detect and predict fatty liver (MASLD)

Multimodality and Longitudinal Artificial Intelligence for Diagnosis and Prognosis in Hepatic Steatosis

NIH-funded research University of Pennsylvania · NIH-11233600

This project will create AI that uses past and current images plus lab and medical-record data to help doctors find and predict fatty liver disease in adults.

Quick facts

Grant typeR21 grant
Study typeNIH-funded research
Funding institutionUniversity of Pennsylvania NIH-funded
Lab location1 site (Philadelphia, United States)
Project IDNIH-11233600 on NIH RePORTER

What this research studies

The team will train deep learning models that combine imaging (for example MRI and other abdominal scans), lab values like alkaline phosphatase, and information from electronic health records over time. The AI will be taught to compare current images with prior studies and to merge different test types into a single prediction about disease presence and future risk. Much of the work uses existing patient scans and clinical data to teach the models how MASLD progresses. The goal is a clinical tool that could support doctors in monitoring, risk-stratifying, and planning care for adults with fatty liver.

Who could benefit from this research

Good fit: Adults (21+) with known or suspected metabolic dysfunction-associated steatotic liver disease who have prior imaging and medical record data available are the most relevant candidates.

Not a fit: People without prior imaging or clinical records, children under 21, or those with liver disease from unrelated causes are unlikely to benefit from this specific project.

Why it matters

Potential benefit: If successful, this could help doctors detect MASLD earlier and better predict who will progress to inflammation, cirrhosis, or liver cancer so patients get the right follow-up and treatment.

How similar studies have performed: Previous AI work has shown promise for detecting liver fat from single imaging tests, but combining multiple test types across time is relatively new and less proven.

Where this research is happening

Philadelphia, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-10 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.