June 02, 2021
The Food and Drug Administration has approved marketing for a device that will help diagnose autism spectrum disorder (ASD) in children between the ages of 18 months and 5 years who exhibit potential symptoms.
Cognoa ASD Diagnosis Aid is a machine learning–based software program that receives information from parents or caregivers, video analysts, and healthcare providers to assist physicians in evaluating whether a child is at risk of having autism.
Autism is a developmental disorder that can cause social, communication, and behavioral challenges, according to the Centers for Disease Control and Prevention. The disorder affects about 1 in 54 children. The disorder is difficult to diagnose because there isn't a medical test to diagnose it. Instead, physicians have to look at a child's developmental history and behavior to make a diagnosis.
Many children are not diagnosed with ASD until later in childhood, which in some cases delays treatment and early intervention. ASD may be detected as early as 18 months, but the average age of diagnosis for ASD is 4.3 years, according to the FDA.
"[ASD] 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," Jeff Shuren, MD, JD, director of the FDA's Center for Devices and Radiological Health, said in a statement. "Today's marketing authorization provides a new tool for helping diagnose children with ASD."
The safety and efficacy of the Cognoa ASD Diagnosis Aid was assessed in a study of 425 patients between the ages of 18 months and 5 years old. For the study, researchers compared the diagnostic assessments made by the device to those made by a panel of clinical experts who used the current standard ASD diagnostic process. The device diagnosed 32% of the children with either a "Positive for ASD" or a "Negative for ASD" result. Researchers found that the device matched the panel's conclusions for 81% of the patients who received a positive diagnosis. For those who received a negative diagnosis, the device matched the panel's conclusions for 98% of the patients. 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.
Cognoa ASD Diagnosis Aid has three main components. One component includes a mobile app for caregivers to answer questions about the child's behavioral problems and to upload videos of the child. The next component is a video analysis portal for specialists to view and analyze uploaded videos of patients. Another component is a portal for healthcare providers that allows them to enter answers to preloaded questions about behavior problems, track the information provided by parents, and review a report of the results.
After the machine learning–based device processes the information provided by parents and healthcare providers, it reports either a positive or a negative diagnosis. If there is insufficient information to make either a positive or a negative diagnosis, the ASD Diagnostic AID will report that no result can be generated.
Some of the risks associated with this device include misdiagnosis and delayed diagnosis of ASD because of a false-positive or false-negative result, or when no result is generated. Researchers said a false-positive result occurred in 15 out of 303 study subjects without ASD and a false-negative result occurred in 1 out of 122 study subjects with ASD.
The FDA emphasized that the device is indicated to aid physicians in the process of diagnosing ASD in children. This means it shouldn't be treated as a standalone diagnostic device, but as an adjunct to the diagnostic process.