FDA Authorizes Marketing of Diagnostic Aid for Autism Spectrum Disorder

FDAThe U.S. Food and Drug Administration authorized marketing of a device to help diagnose autism spectrum disorder (ASD). The Cognoa ASD Diagnosis Aid is a machine learning-based software intended to help health care providers diagnose ASD in children 18 months through 5 years of age who exhibit potential symptoms of the disorder.

"Autism spectrum disorder can delay a child’s physical, cognitive and social development, including motor skill development, learning, communication and interacting with others. The earlier ASD can be diagnosed, the more quickly intervention strategies and appropriate therapies can begin," said Jeff Shuren, M.D., J.D., director of the FDA's Center for Devices and Radiological Health. "Today's marketing authorization provides a new tool for helping diagnose children with ASD."

The Centers for Disease Control and Prevention defines ASD as a "developmental disability that can cause significant social, communication and behavioral challenges" and is estimated to affect about 1 in 54 children. Because ASD symptoms can vary greatly, the disorder may be difficult to diagnose. While ASD may be detected as early as 18 months old, many children are not diagnosed until later in childhood, which can delay treatment and early intervention. The average age of diagnosis for ASD is 4.3 years. Some delays in diagnosis are due to the need for children to be referred to specialists with expertise in ASD.

The Cognoa ASD Diagnosis Aid is a software as a medical device that uses a machine learning algorithm to receive input from parents or caregivers, video analysts and health care providers to assist physicians evaluate a patient at risk of ASD. The device consists of three main components: a mobile app for caregivers and parents to answer questions about behavior problems and to upload videos of their child; a video analysis portal that allows manufacturer-trained and certified specialists to view and analyze uploaded videos of patients; and a health care provider portal that is intended for a health care provider to enter answers to pre-loaded questions about behavior problems, track the information provided by parents or caregivers and review a report of the results. After processing the information provided by parents, caregivers and healthcare providers, the ASD Diagnosis Aid reports a positive or negative diagnosis if there is sufficient information for its algorithm to make a diagnosis. If there is insufficient information to render a "Positive for ASD" or "Negative for ASD" result to help determine a diagnosis, the ASD Diagnosis Aid will report that no result can be generated.

The FDA assessed the safety and effectiveness of the Cognoa ASD Diagnosis Aid in a study of 425 patients aged 18 months through 5 years in 14 different clinical care sites, with an average age of 2.8 years. The study compared the assessments made by the device directly against the assessments made by a panel of clinical experts who used the current standard ASD diagnostic process. The device provided a "Positive for ASD" or "Negative for ASD" result to aid in making a diagnosis in 32% of patients. For those with a "Positive for ASD" or "Negative for ASD" result, the device results matched the panel's conclusions for 81% of patients who tested positive for ASD by the device and 98% of patients who tested negative for ASD by the device. In addition, the device made an accurate ASD determination in 98.4% of patients with the condition and in 78.9% of patients without the condition.

The risks associated with the use of the device include misdiagnosis and delayed diagnosis of ASD, based on a false positive result (observed in 15 out of 303 study subjects without ASD), a false negative result (observed in one out of 122 study subjects with ASD) or when no result was generated. Both misdiagnosis or missed diagnosis can result in delayed treatment of ASD and delivery of treatment not appropriate for ASD.

The FDA reviewed the Cognoa ASD Diagnosis Aid through the De Novo premarket review pathway, a regulatory pathway for low- to moderate-risk devices of a new type. Along with this authorization, the FDA is establishing special controls for devices of this type, including requirements related to labeling and performance testing. When met, the special controls, along with general controls, provide reasonable assurance of safety and effectiveness for devices of this type. This action creates a new regulatory classification, which means that subsequent devices of the same type with the same intended use may go through the FDA's 510(k) premarket process, whereby devices can obtain marketing authorization by demonstrating substantial equivalence to a predicate device.

The Cognoa ASD Diagnosis Aid is indicated as an aid in the diagnosis of ASD for patients 18 months through 5 years of age who are at risk of developmental delay based on concerns of a parent, caregiver, or health care provider. The device is not indicated for use as a stand-alone diagnostic device but as an adjunct to the diagnostic process.

The FDA granted the marketing authorization to Cognoa, Inc.

About the U.S. Food and Drug Administration (FDA)

The FDA, an agency within the U.S. Department of Health and Human Services, protects the public health by assuring the safety, effectiveness, and security of human and veterinary drugs, vaccines and other biological products for human use, and medical devices. The agency also is responsible for the safety and security of our nation’s food supply, cosmetics, dietary supplements, products that give off electronic radiation, and for regulating tobacco products.

Most Popular Now

Can Language Models Read the Genome? Thi…

The same class of artificial intelligence that made headlines coding software and passing the bar exam has learned to read a different kind of text - the genetic code. That code...

Bayer and Google Cloud to Accelerate Dev…

Bayer and Google Cloud announced a collaboration on the development of artificial intelligence (AI) solutions to support radiologists and ultimately better serve patients. As part of the collaboration, Bayer will...

Study Shows Human Medical Professionals …

When looking for medical information, people can use web search engines or large language models (LLMs) like ChatGPT-4 or Google Bard. However, these artificial intelligence (AI) tools have their limitations...

Shared Digital NHS Prescribing Record co…

Implementing a single shared digital prescribing record across the NHS in England could avoid nearly 1 million drug errors every year, stopping up to 16,000 fewer patients from being harmed...

North West Anglia Works with Clinisys to…

North West Anglia NHS Foundation Trust has replaced two, legacy laboratory information systems with a single instance of Clinisys WinPath. The trust, which serves a catchment of 800,000 patients in North...

Can AI Techniques Help Clinicians Assess…

Investigators have applied artificial intelligence (AI) techniques to gait analyses and medical records data to provide insights about individuals with leg fractures and aspects of their recovery. The study, published in...

AI Makes Retinal Imaging 100 Times Faste…

Researchers at the National Institutes of Health applied artificial intelligence (AI) to a technique that produces high-resolution images of cells in the eye. They report that with AI, imaging is...

SPARK TSL Acquires Sentean Group

SPARK TSL is acquiring Sentean Group, a Dutch company with a complementary background in hospital entertainment and communication, and bringing its Fusion Bedside platform for clinical and patient apps to...

Standing Up for Health Tech and SMEs: Sh…

AS the new chair of the health and social care council at techUK, Shane Tickell talked to Highland Marketing about his determination to support small and innovative companies, by having...

GPT-4 Matches Radiologists in Detecting …

Large language model GPT-4 matched the performance of radiologists in detecting errors in radiology reports, according to research published in Radiology, a journal of the Radiological Society of North America...

ChatGPT Extracts Data for Ischaemic Stro…

In an ischaemic stroke, an artery in the brain is blocked by blood clots and the brain cells can no longer be supplied with blood as a result. Doctors must...

Experts Propose Specific and Suited Guid…

Current Artificial Intelligence (AI) models for cancer treatment are trained and approved only for specific intended purposes. GMAI models, in contrast, can handle a wide range of medical data including...