AI Technology Could Predict Autism At Very Early Stage In Babies

Admin | Published 2017-02-27 20:59
Though the first signs of autism can appear in early childhood, predicting its occurence at very young ages is difficult. A behavior questionnaire is a crapshoot at 12 months. However, experts say, artificial intelligence might just be the key to making an accurate call. Researchers at the University of North Carolina have developed a deep learning algorithm that can predict autism in babies. This technology has a relatively high 81 percent accuracy and 88 percent sensitivity.

Experts have trained the algorithm to recognize early hints of autism (c) Daily Mail

The researchers trained the algorithm to recognize early hints of autism by feeding it brain scans and asking it to watch for three common factors: the brain's surface area, its volume and the child's gender (as boys are more likely to have autism). During the tests, the AI could spot the telltale increase in surface area as early as 6 months, and a matching increase in volume as soon as 12 months. That's why, it wasn't a surprise that most of these babies were formally diagnosed with autism at 2 years old.

Not a sign of autism, just a baby being funny

However, the other uses of AI diagnosis in medicine, could be challenging as it's likely to be producing additional tests that validate and refine the work seen here. Experts say that it's difficult to obtain brain scans of babies for use in replication tests, and those scans are often expensive. The researchers also told the IEEE Spectrum Also, it wouldn't be likely practical to use this prediction method all the time. It'd most likely be useful if a test suggests that a baby is at high risk of autism. Nonetheless, the AI could be extremely helpful if it either gives the all-clear or helps parents adjust to the special needs of their child.
Hey! Where are you going?? Subscribe!

Get weekly science updates in your inbox!