Using machine learning to accurately identify genetic syndromes in children

0


© iStock / SDI Productions

New machine learning technology has demonstrated impressive efficacy in detecting genetic syndromes in children, a significant breakthrough in diagnosing a plethora of disorders.

In a study conducted by the Children’s National Hospital, researchers developed a machine learning tool that allows rapid screening for genetic syndromes with an average accuracy of 88%, recommending further investigation or referral to a specialist. The breakthrough machine learning technology was formed with data from 2,800 pediatric patients from 28 countries and takes into account facial variability related to age, gender, and racial and ethnic origin.

Marius George Linguraru, lead author of the study and senior researcher at the Sheikh Zayed Institute for Pediatric Surgical Innovation at the National Children’s Hospital, said: not immediately evident to the human eye or intuition and to help physicians who do not specialize in genetics. This technological innovation can help children without access to specialist clinics, which are not available in most countries. Ultimately, this can help reduce health inequalities in underfunded societies. “

The study is published in The digital health of the Lancet.

Identify genetic syndromes

Pioneering machine learning technology uses a photograph of the patient’s face to check for the presence of any genetic syndrome, with the image being obtained at points of service, such as pediatricians’ offices, maternity hospitals, and general practitioner clinics.

Marshall L. Summar, director of the Rare Disease Institute at Children’s National Hospital, said: Hands of community caregivers. This can dramatically speed up diagnostic time by providing a robust indicator for patients who need further examination. This first step is often the biggest obstacle to progressing to a diagnosis. Once a patient is in the checkup system, the likelihood of diagnosis (by many means) is greatly increased. “

Around the world, millions of children are born each year with genetic syndromes, such as Down syndrome, Williams-Beuren syndrome, and Noonan syndrome. Down syndrome is a condition in which a child is born with developmental delays and disabilities due to having an extra copy of his or her 21st chromosome. Williams-Beuren syndrome is triggered by a submicroscopic deletion of a region of chromosome seven and is a rare multisystem disease, while Noonan syndrome is a genetic disorder caused by a defective gene that interrupts normal development in many parts of the body. body.

Unfortunately, the vast majority of children born with genetic syndromes live in areas of the world with limited resources and limited access to genetic testing services, which can be extremely expensive. In addition, there is also a lack of specialists in these regions who can identify genetic syndromes in the early stages of development where preventive care is essential to save children’s lives. This is seen mainly in low income areas, with limited resources and isolated communities.

Linguraru said, “The technology presented can help pediatricians, neonatologists and family physicians in the routine or remote assessment of pediatric patients, especially in areas where access to specialist care is limited. Our technology can be a step forward for the democratization of health resources for genetic screening. “

Refine the machine learning technique

To optimize their machine learning technology, the team trained the system with 2,800 retrospective facial photographs of children with and without genetic syndromes from 28 countries including Argentina, Australia, Brazil, China. , France, Morocco, Nigeria, Paraguay, Thailand and the United States. The architecture of machine learning technology was designed to accommodate normal facial variations among populations of various demographic groups.

“The appearance of the face is influenced by the race and ethnicity of the patients. The wide variety of conditions and the diversity of populations impact the early identification of these conditions due to the lack of data that can serve as a benchmark, ”Linguraru said. “Racial and ethnic disparities still exist in the survival of the genetic syndrome, even under some of the most common and best studied conditions. “

In the future, researchers aim to train the technology with more datasets from under-represented groups, adapting the model to locate phenotypic variations within more specific demographic groups. Additionally, in addition to being an accessible tool for telehealth services to examine genetic risk, there are a range of other applications for machine learning technology.

“I am also excited about the potential of the technology in newborn screening,” Linguraru commented. “There are approximately 140 million newborns worldwide each year, eight million of whom are born with severe congenital disabilities of genetic or partially genetic origin, many of which are discovered late.

Children’s National recently announced that it has entered into a licensing agreement with MGeneRx Inc. for its patented pediatric medical device technology.

Nasser Hassan, Interim CEO of MGeneRx Inc., said: “The social impact of this technology cannot be underestimated. We are excited about this licensing agreement with the Children’s National Hospital and the opportunity to improve this technology and extend its application to populations where precision medicine and the earliest possible interventions are absolutely necessary in order to save and improve children’s lives.




Subscribe to our newsletter

Recommended related articles






Share.

Leave A Reply