Children’s National brings AI into the RHD early diagnosis equation

In December of 2024, a team that included experts from Children’s National Hospital traveled to Uganda to continue work on a pilot program applying artificial intelligence (AI) to the diagnosis of rheumatic heart disease (RHD). Ugandan health care providers have been trained and equipped to acquire echocardiograms for their patients but lack expertise in consistently being able to diagnose RHD by detecting leaky heart valves. The team created a tool that uses AI to predict RHD by identifying leaky heart valves on handheld ultrasound devices, then prompts a referral for a full echocardiogram.

The goal is to find ways to help people in Uganda diagnose RHD early, before a patient is in need of surgery, and initiate antibiotics so their heart can return to normal. The team of researchers, including fellow Kelsey Brown, MD, helped to implement additional steps toward this goal in December. According to Dr. Brown, the results were excellent. After four days of seeing patients, over 450 people were screened. The AI tool has an 86% accuracy rating. After returning from Uganda, the research team plans to work on the AI tool and further improve its accuracy rating. Eventually, the vision is that this tool can roll out on a larger scale for more places around the world to access it.

Craig Sable, MD, Marius Linguraru, DPhil, MA, MSc, and Pooneh Roshanitabrizi, PhD, from our Sheikh Zayed Institute, who developed the AI algorithms, worked in partnership with the Rheumatic Heart Disease Research Collaborative (RRCU) in Uganda. This trip was also made possible thanks to a grant funded through the Children’s National Global Health Initiative. Special thank you to our AI partner, US2.AI, who made the deployment of the AI models onto a tablet that provided real-time results, possible.