Top of page
Technology

Researchers Using Machine Learning for Earlier Autism Diagnosis

baby with app
Photo: Duke University

Parents and doctors face a difficult dilemma when it comes to detecting and treating autism in children.

A team of researchers at Duke University, led by Geri Dawson and electrical and computer engineering professor Guillermo Sapiro, hope to improve the difficult problem of early autism detection by combining the ubiquity of mobile devices with the power of machine learning and computer vision.

Autism affects roughly 1 in every 59 children in the United States and occurs more often in boys than girls.

Dawson and Kollins began to explore the possibility of applying modern computational resources to the problem. They knew that the field of machine learning, in which computer algorithms are applied to problems that involve sifting enormous amounts of data in order to find hidden patterns and associations, could offer the tools they needed.

“Early intervention is important no matter what,” Kollins adds, although he emphasizes that it’s even more important in the case of Autism, due to the impact on language and socialization. “It leads to better outcomes across the board.”

The method they developed has not only led to new insights about autism, but it could also enhance how doctors evaluate patients for other behavioral disorders.

You might also like

baby with app baby with app

Autism rates soar in New York and New Jersey region, study finds

Documented cases of autism spectrum disorder (ASD) in the New…

woman using smartphone woman using smartphone

App-monitoring of thinking difficulties could help treatment of depression

New research with over 500 participants diagnosed with depression has…

blind person teating the cane blind person teating the cane

‘Smart’ walking stick could help blind people with groceries, finding a seat

Engineers at CU Boulder are tapping into advances in artificial…

Hippo Camera app Hippo Camera app

New smartphone app can significantly improve memory recall

Researchers at the University of Toronto have demonstrated that a…