AI Supports Clinical Trial for Rare Genetic Disease Treatment

Artificial intelligence (AI) supported a clinical trial focused on assessing treatment methods for a rare genetic disease known as activity-dependent neuroprotective protein (ADNP) syndrome.

ADNP syndrome is a rare condition due to a mutation of the ADNP gene. The disease affects the brain and various body functions, including hearing and vision, according to the National Institutes of Health.

Researchers from the Hugh Kaul Precision Medicine Institute at the University of Alabama at Birmingham used an AI tool known as mediKanren that flagged useful clinical evidence, helping them identify low-dose ketamine as a potential therapeutic target for ADNP syndrome.

Matt Might, PhD, the director of the UAB Precision Medicine Institute, created the mediKanren tool with funding from the National Center for Advancing Translational Sciences. The AI tool is capable of assessing large amounts of medical literature and identifying potential results for a specific condition.

Once they found that ketamine was a potential therapeutic target for ADNP syndrome, UAB researchers contacted the ADNP Kids Research Foundation. 

“We had a surgical resident at UAB whose son had ADNP syndrome,” said Might in a press release. “I was also in contact with Sandra Sermone, the founder of the ADNP Kids Research Foundation, which now has a registry of 250 children with the syndrome. We were able to present mediKanren with enough information on ADNP to solicit an answer. And the answer was ketamine.”

Ketamine has been approved for use in the US since 1970. According to the press release, Sermone, whose son was the first person in the US to be diagnosed with ADNP syndrome, began examining the literature that mediKanren flagged. She then presented the evidence to researchers at the Seaver Autism Center for Research and Treatment at Mount Sinai Hospital, who launched a clinical trial. Findings from the trial were published in Human Genetics and Genomic Advances.

The trial determined that low-dose ketamine is a safe, well-tolerated, and applicable method for treating children diagnosed with the condition.

“In several studies using animal models, researchers reported that ketamine appeared to boost ADNP production in brain cells,” said Sermone in the press release. “Children born with ADNP syndrome have one healthy copy of the ADNP gene and one broken copy. The healthy copy produces the ADNP protein, which is essential for proper neurologic development, while the broken copy does not. As a result, the child does not get enough ADNP protein for normal development.”  

The clinical trial also showed that ketamine led to improvements in various areas, such as social behavior, attention deficit and hyperactivity, and restricted and repetitive behaviors.

Further, clinician-rated assessments showed improvement based on the Clinical Global Impression-Improvement scale, which indicates how much a condition may have improved or worsened since the beginning of treatment.

The use of AI in treating various conditions has become increasingly common.

For example, in August, researchers from the AI in Medicine Program of Brigham and Women’s Hospital developed a deep-learning algorithm to improve lung cancer radiation therapy treatment. The AI model was trained to detect non-small cell lung cancer tumors within computed tomography scans.