Pupil Dilation And Heart Rate, Analyzed By AI, May Help Spot Autism Early

Autism and other neuro developmental disorders are often not diagnosed until a child is a few years old, when behavioral interventions and speech/ occupational therapy become less effective. But new research conducted this week at PNAS suggests that two simple and quantifiable measures, spontaneous fluctuations in pupil dilation or heart rate,could allow a much earlier diagnosis of Rett syndrome and possiblyother disorders with characteristics similar to autism.

The study, led by Boston Children's Hospital neuroscientist Michela Fagiolini, PhD, and her postdoctoral colleague Pietro Artoni, PhD,reveals a machine learning algorithm that can detect abnormalities inpupil dilation that predict autism spectrum disorder (ASD) in mouse models. In addition, it shows that the algorithm can accuratelydetect if a girl has Rett syndrome, a genetic disorder that affectscognitive, sensory, motor and autonomic function from 6 to 18 monthsof age, as well as behaviors similar to autism.

Fagiolini and his colleagues hope that this system can provide an early warning signal not only for Rett syndrome but also for ASD in general. In thefuture, they believe it could also be used to monitor patients'responses to treatments; Currently, a clinical trial is testing thedrug ketamine for Rett syndrome, and a gene therapy trial is planned.

"We want to have a reading of what is happening in the brain that is quantitative, objective and sensitive to subtle changes," says Fagiolini. "In more general terms, we lack biomarkers thatreflect brain activity, are easy to quantify and not biased. A machine could measure a biomarker and not be affected by subjective interpretations of how a patient is doing."

Alteredautism excitation

Fagioliniand Artoni, in close collaboration with Takao Hensch, PhD, and Charles Nelson, PhD, at Boston Children's, began with the idea thatpeople in the autism spectrum have altered behavioral states.Previous evidence indicates that the cholinergic circuits of the brain, which are involved in arousal, are especially disturbed, andthat altered arousal affects both spontaneous pupillary dilation /constriction and heart rate.

The Fagiolini team, supported by the IRCN at Boston Children's F.M. Kir by Neurobiology Center, it was proposed to measure pupil fluctuations inseveral models of mice with ASD, including mice with mutations that cause Rett syndrome or CDKL5 disorder, as well as BTBR mice. The team found that the dilatation and spontaneous constriction of the pupil were altered even before the animals began to show symptoms similar to ASD.

In addition, in mice that lack MeCP2, the gene mutated in Rett syndrome,restoring a normal copy of the gene, only in cholinergic brain circuits, prevented the appearance of pupillary abnormalities, as well as behavioral symptoms.

Predictionof Rett syndrome in girls

To systematically link the excitation changes observed with the cholinergic system, the team took advantage of a previous Hensch discovery: mice lacking the LYNX1 protein exhibit improved cholinergic signaling. Based on approximately 60 hours of observation of these mice, the researchers "trained" a deep learning algorithm to recognize abnormal pupil patterns. The same algorithm accurately estimated cholinergic dysfunction in mice deficient in BTBR, CDKL5 and MeCP2.

Then,the team took this algorithm to 35 girls with Rett syndrome and 40controls in development. Instead of measuring the girls' pupils(since patients may be restless), they used heart rate fluctuationsas a measure of arousal. However, the algorithm successfullyidentified girls with Rett, with an accuracy of 80 percent in thefirst and second year of life.

"Thesetwo biomarkers fluctuate in a similar way because they are representatives of the activity of autonomous excitation," says Artoni. "It's the so-called 'fight or flight' response."

Autonomous excitation, a property of the brain that is strongly preserved indifferent species, is a robust indicator of an altered developmentaltrajectory, Fagiolini and Artoni discovered.

Biomarkers for babies?

Ina previous study with Nelson, Fagiolini showed that visual evoked potentials, an EEG measure of visual processing in the brain, could also serve as a potential biomarker for Rett syndrome. She believes that together, these biomarkers could offer robust but affordablescreening tools for infants and young children, warning about impending neurological development problems and helping to track theprogression of their development or treatment.

"If we have bio markers that are not invasive and are easily evaluated,even a newborn baby or a non verbal patient could be monitored at multiple time points," says Fagiolini.

By:Preeti Narula

Content:https://www.sciencedaily.com/releases/2019/07/190724104019.htm