Words by Tess Becker
Everyone knows about widespread diseases that afflict people, like cancer, HIV, and many more – but there are numerous lesser-known diseases that affect people all around the world.
One such disease, Kawasaki disease, or Kawasaki syndrome, is a leading cause of acquired heart disease in the US that primarily affects children under 5, and afflicts less than 20,000 people a year.
Ellen Xu, a 17-year-old scientist from San Diego, had close ties to the disease. Her younger sister, Kate, was diagnosed with Kawasaki when they were young children.
“If you’re like me and my family, you’ve probably never heard of Kawasaki disease before and part of the reason for that is because it’s such a huge medical mystery,” Ellen said in a Society for Science video.
In the video, she was describing an invention that she created to detect the disease in young children.
The cause of the disease is unknown and can lead to long-term complications if not treated correctly, but as long as it's treated there are usually no long-lasting effects.
The problem is that the diagnosis of Kawasaki is often difficult due to the symptoms sharing similar clinical features with other health conditions, or ‘lookalike diseases.’ This is why Ellen’s invention is so important.
“What if we could help aid in the diagnosis of Kawasaki disease through differentiating it from its look-alike diseases?” Ellen said.
The invention is called the ‘convolutional neural network’ and is a deep learning algorithm that analyzes imagery and mimics the way our eyes function, to ultimately learn data and recognize patterns. The algorithm is trained to recognize symptoms of Kawasaki, Ellen was able to create a tool that can distinguish clinical features of the disease from lookalike diseases.
Her invention was awarded $150,000 at Society for Science’s 2023 Regeneron Science Talent Search. The award is one of the most prestigious science awards for high schoolers, and she earned third place out of 40 finalists.
“I’m really excited for this, the potential of this algorithm, and I hope it demonstrates the feasibility for the use of photographs and deep learning to help prevent medical misdiagnosis,” she said.