AI Detecting Risk of Genetic Syndromes in Children

Artificial Intelligence (AI) machine learning is increasingly used as a diagnostic tool for healthcare, biotechnology research, medical care and the life sciences intelligence. A new study published today in The Lancet Digital Health by researchers at the Children’s National Hospital in Washington, DC unveils an AI deep learning tool that can detect the risk of genetic syndromes in children with an accuracy of 88 percent.

“Genetic syndromes can be associated with severe cardiovascular, immune, endocrine, and neurodevelopmental risks, and thus have an impact on the quality of life of patients and their families,” wrote the researchers affiliated with the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National Hospital in Washington, DC, and George Washington University.

Researchers designed the AI ​​deep learning architecture to consist of three artificial neural networks to perform image standardization, facial morphology detection, and genetic syndrome risk assessment.

“Delays in the diagnosis of genetic syndromes are common, particularly in low and middle-income countries with limited access to genetic screening services,” the scientists wrote. “We, therefore, aimed to develop and evaluate a machine learning-based screening technology using facial photographs to evaluate a child’s risk of presenting with a genetic syndrome for use at the point of care.”

The data used for the study include 128 different genetic diseases, such as Down syndrome, Williams-Beuren syndrome, Cornelia de Lange syndrome, 22q11.2 deletion, and Noonan syndrome.

“In this retrospective study, we developed a facial deep phenotyping technology based on deep neural networks and facial statistical shape models to screen children for genetic syndromes,” wrote the researchers.

To train deep neural networks, the researchers used a dataset of 2,800 retrospective facial photos of children, including 1,400 children diagnosed with 128 genetic disorders, as well as 1,035 syndromic photos from the Hospital Nacional de Niños and 365 from other datasets from other research studies, Face2Gene, and the Atlas of Human Malformations in Different Populations from the National Institute for Human Genome Research.

“Facial appearance is key in a geneticist’s evaluation of people with suspected genetic syndromes,” explained the researchers. “However, primary care physicians, who are not trained to identify dysmorphology in diverse populations, often miss subtle indicators of genetic conditions. Additionally, cautious clinicians might refer healthy children with an atypical facial appearance to expensive and unnecessary genetic evaluations.”

The researchers reported that their deep learning artificial intelligence solution could detect the genetic syndrome with a high accuracy of 88 percent for the general population.

“This provides a substantial improvement over the reported accuracy of trained pediatricians to identify well studied conditions such as Down syndrome (64% accuracy from physical examination),” reported the researchers. “Our results demonstrate the feasibility of our method, and the potential to improve the early detection of genetic syndromes.”

With this proof of concept, the researchers next identify the clinical validation using a prospective patient cohort. According to the scientists, their technology will be used for artificial intelligence at the point of care, for example in primary care centers, pediatric health clinics and during childbirth via a smartphone app, to detect genetic syndromes at an early stage. It is not intended to replace genetic tests, but to serve as an aid for doctors for prevention, diagnosis and screening.

“This genetic screening technology could support early risk stratification at the point of care in global populations, which has the potential to accelerate diagnosis and reduce mortality and morbidity through preventive care,” the researchers concluded.

Source link