2024-01-21 19:18:56
PrintShare
A wearable echo machine and ultrasound probe (right) stand next to the wearable AI device developed by Children’s National and Us2.ai during initial testing in northern Uganda. © Children’s National Hospital
An AI-powered tool evaluates patient data and can predict rheumatic heart disease with 90 percent accuracy.
When Kelsey Brown met Mohammed, the 15-year-old Ugandan boy looked terribly worried. He was in the final stages of rheumatic heart disease, which kills around 400,000 people worldwide every year. His scheduled heart surgery to treat the illness had been postponed for a day.
By this time, fluid from Muhammad’s heart had backed up into his lungs, making it so difficult for him to breathe that he had to sleep sitting upright. Brown, a cardiologist at Children’s National Hospital in Washington, assumed he was afraid of the surgery. But Mohammed told her that he was not afraid of the procedure.
“What he was most afraid of was that the surgery would be canceled and his heart wouldn’t be repaired,” Brown said, noting a striking difference from children in the United States whose understandable fear is the surgery itself.
Read The Washington Post for free for four weeks
Your quality ticket from washingtonpost.com: Get exclusive research and 200+ stories free for four weeks.
AI-assisted diagnosis of rheumatic heart disease
Now, researchers at Children’s National have developed a new AI-powered tool to diagnose rheumatic heart disease long before a patient needs surgery – an advance that shows the potential of artificial intelligence for medicine. Working with staff at the Uganda Heart Institute, the team has developed a system that allows trained nurses to screen and diagnose children early, when they can still be treated with penicillin, for less than $1 a year. Early treatment could save thousands from surgery.
“We are focusing on a dramatically neglected global health problem, the big one [Todes- und Krankheits-]said Craig A. Sable, director of the global health program at Children’s National and one of the authors of an article describing the AI tool in the Journal of the American Heart Association.
Sable, who has made more than 40 trips to Uganda to treat children, said that on his last trip in November he was performing eight or nine heart surgeries a week but found that 1,500 children were on a national waiting list for the procedure. “Only a quarter have surgery before they die,” he said.
Rheumatic heart disease is a largely preventable disease that results from repeated bouts of rheumatic fever caused by group A streptococci bacteria. This group of bacteria, considered the fifth most dangerous pathogen in the world, causes streptococcal infections in an estimated 600 million people each year.
A minority of those infected develop rheumatic heart disease, which results from an abnormal immune response that damages the heart and its valves. It is estimated that around 5 to 10 percent of people have a genetic predisposition to this immune reaction. But environmental factors, such as poor and cramped living conditions, also play a role.
The first symptoms of the disease often appear in children between the ages of 8 and 10. It can be detected early with an ultrasound examination of the heart, a so-called echocardiogram. The problem is that in countries like Uganda there are too few cardiologists who can evaluate the images, so comprehensive screening is not feasible. As a result, the disease often goes undetected in its early stages. “The child doesn’t know he has them. The parents don’t know,” Brown said. “If they go to the doctor, the doctor wouldn’t hear it.”
Rheumatic heart disease plagues poor countries
Rheumatic heart disease plagues poor countries like Uganda, where between 2 and 3 percent of all children are affected. There are many different strains of bacteria in these countries, and children are often repeatedly infected. The condition worsens with each new attack.
Although the disease is no longer a major problem in the United States, it was as recently as the 1940s and 1950s, as Sable knows all too well. He was a teenager when his grandmother died from complications of rheumatic heart disease and emphysema.
“In the first half of the 20th century, this was the leading cause of cardiac death in the United States,” Sable said. “More than 100,000 military personnel were expelled from the army during World War II because they suffered from rheumatic fever or rheumatic heart disease.”
The use of artificial intelligence in healthcare has exploded since 2018, when the Food and Drug Administration launched the first independent AI-based diagnostic tool – known as IDx-DR – to screen for diabetic retinopathy, a serious eye disease that occurs in people with diabetes can develop, has allowed. Just over five years later, there are nearly 700 FDA-approved medical devices that use artificial intelligence and machine learning.
While echocardiogram machines in a hospital weigh about 500 pounds and cost $250,000, the equipment developed by the Children’s National team would be lightweight and cost between $2,000 and $5,000. A Singapore-based company, Us2.ai, is developing software using the team’s algorithm, which was trained on more than 1,000 echocardiograms.
Algorithm evaluates echocardiograms
The algorithm can interpret images in seconds and classify them as either “normal” or “rheumatic heart disease.” In tests on the echocardiograms of more than 500 patients, the new tool interpreted the images with an accuracy of almost 90 percent.
“The value of artificial intelligence is extraordinary when you can use it to improve the accuracy of images,” said Chris Longenecker, director of the Global Cardiovascular Health Program at the University of Washington, who was not involved in the study. He said artificial intelligence will make ultrasound a particularly powerful tool because “you can take it to the most remote corners of a low-income country.”
Longenecker said artificial intelligence can also help doctors learn more about the critical features of rheumatic heart disease.
“AI can work like a doctor and potentially complement the work of a doctor,” said Pooneh Roshanitabrizi, a research associate at Children’s National who developed the new algorithm for echocardiogram interpretation along with Marius Linguraru, principal investigator at the Sheikh Zayed Institute for Pediatric Surgical innovation of the hospital.
The new screening system will be tested and improved based on up to 200,000 pediatric cases in Uganda, according to Children’s National researchers. Each child participating in the program is examined using the current standard, in which trained nurses independently interpret echocardiograms.
The vast majority of data from the 200,000 cases is then used to train and improve the algorithm.
“Very encouraging work”
If the new screening tool is approved by Ugandan and U.S. regulators, each nurse would be equipped with a probe the size of a computer mouse – used to create images of the heart – and a tablet equipped with the AI component.
In cases identified as possible rheumatic heart disease, an examination by a cardiologist would follow. Cardiologist visits could be conducted using telemedicine, eliminating the need to travel to or from remote areas.
Shelby Kutty, director of pediatric congenital cardiology at Johns Hopkins Children’s Center, who was not involved in the project, said that while there is similar research for adult heart disease, work in pediatric heart disease is relatively limited.
“Overall, I think this is a very encouraging piece of work,” Kutty added. “I think the field is on the right track.”
To the author
Mark Johnson joined The Washington Post in July 2022 after 22 years at the Milwaukee Journal Sentinel, where he covered health and science. He wrote about the first person to survive rabies without vaccination and reported the first use of whole gene sequencing to diagnose and treat a new disease.
We are currently testing machine translations. This article was automatically translated from English into German.
This article was first published in English on January 17, 2024 at the “Washingtonpost.com” – as part of a cooperation, it is now also available in translation to readers of the IPPEN.MEDIA portals.
#doctors #diagnose #hidden #heart #disease #children