Boston Children’s Hospital has made a breakthrough in diagnosing rare diseases in children with the help of AI tools. The hospital’s center for rare diseases and the AI company OpenAI have found that off-the-shelf AI tools can help identify genetic causes of rare diseases in children.

How AI Helps

The AI tool, called o3, was used to analyze the genomes of 376 patients who had not received diagnoses for their rare diseases. The tool helped identify new diagnoses for 18 children, including 10 with rare neurodevelopmental diseases, four with neuromuscular disorders, two who had died suddenly, and two with early childhood psychosis illnesses.

One of the children who received a diagnosis was Kyra Benton, who had been struggling with a rare disease since she was nine years old. Benton’s mother had taken her to see a neuromuscular disease expert in New York City, but the expert had not been able to diagnose her condition. Years later, Benton visited Boston Children’s Hospital, where the o3 tool was used to analyze her genome and identify the cause of her symptoms: myofibrillar myopathy, a progressive genetic neuromuscular disorder.

Impact of AI in Medicine

The use of AI tools in medicine has the potential to revolutionize the way doctors diagnose and treat diseases. According to Adam Rodman, a doctor and expert on the use of AI in medicine, the new research is an exciting demonstration of AI systems’ ability to diagnose diseases when used by doctors. Rodman noted that a diagnostic yield of 5% is truly meaningful and could serve as a significant screening tool to help speed up the reanalysis of significant backlogs of cases.

The research team emphasized that the use of AI tools is not a replacement for human doctors, but rather a tool to help them make more accurate diagnoses. The team also noted that the results of the AI tool must be carefully reviewed by human researchers to ensure their accuracy.

Original reporting: Dallas TX News (HLL/CB) — read the source article.