App can screen for autism in 10 minutes

An app driven by AI can run on a tablet to accurately screen for autism in children by measuring and weighing a variety of distinct behavioural indicators, researchers in the US have demonstrated.

Called SenseToKnow, the app delivers scores that evaluate the quality of the data analysed, the confidence of its results and the probability that the child tested is on the autism spectrum.

The results are fully interpretable, meaning that they spell out exactly which of the behavioural indicators led to its conclusions and why.

This provides healthcare providers with detailed information on what to look for and consider in children referred for full assessments and intervention.

The app’s ease of use and lack of hardware limitations, combined with its demonstrated accuracy across sex, ethnicity and race, could help eliminate known disparities in early autism diagnosis and intervention by allowing autism screening to take place in any setting, even in the child’s own home.

Study co-senior author Geraldine Dawson, director of the Duke University Center for Autism and Brain Development, said:

“Autism is characterised by many different behaviours, and not all children on the spectrum display all of them equally, or at all.

“This screening tool captures a wide range of behaviours that more accurately reflect the complexity and variability found in autism.”

Recent research has shown promising results from tracking children’s eye movements in response to specially designed films that can help diagnose autism in a clinical setting.

SenseToKnow, the researchers say, detects a wider range of behaviours such as facial expression, gaze patterns, head movements and blink rate.

The app also incorporates an on-screen bubble-popping game to assess motor movement and skills, as delays in motor skills are one of the earliest signs of autism.

SenseToKnow uses almost every sensor in the tablet’s arsenal to measure and characterise the child’s response without the need for any sort of calibration or special equipment.

It then uses AI to analyse the child’s responses to predict how likely it is that the child will be diagnosed with autism.

Sam Perochon is a PhD student working in the laboratory of Guillermo Sapiro, the James B. Duke Distinguished Professor of Electrical and Computer Engineering and co-senior author of the study.

Perochon said: “The AI we’ve built compares each child’s biomarkers to how indicative they are of autism at a population level.

“This allows the tool to capture behaviours other screening tests might miss and also report on which biomarkers were of the most interest and most predictive for that particular child.”

The AI tool is able to provide scores for both the quality of data that the app was able to capture as well as its level of confidence in its own analysis—both of which are a novel feature, the researchers believe.

Matias Di Martino, assistant research professor of electrical and computer engineering at Duke, who co-led the analysis of the study, said:

“This is an important aspect for a healthcare provider to know, just like they would need to know if a blood test did not have a big enough sample to produce reliable results.”

Image: Duke University