Measuring pupil dilation and heart rate with the help of AI could allow earlier diagnosis of autism

Autism and other neurodevelopmental disorders are often only diagnosed when the child has reached the age of a few years, when behavioral interventions and speech therapy / occupational therapy become less effective . But new research this week in PNAS suggests that two simple and quantifiable measures – spontaneous fluctuations in pupil dilation or heart rate – could lead to a much earlier diagnosis of Rett syndrome and possibly other disorders with similar characteristics to those of 39; autism.

The study, led by neuroscientist Michela Fagiolini of the PhD, and postdoctoral researcher Pietro Artoni, unveils an automatic learning algorithm capable of detecting abnormalities in the predictive dilation of students' spectrum disorder. autism (TSA) in murine models. It further shows that the algorithm can accurately detect if a girl is suffering from Rett syndrome, a genetic disorder that alters cognitive, sensory, motor and autonomic functions as early as 6 to 18 months of age, as well as behaviors similar to those of autism.

Fagiolini and his colleagues hope that this system could provide an early warning signal, not only for Rett's syndrome, but for ASDs in general. In the future, they think that this could also be used to monitor the response of patients to treatments; currently, a clinical trial is testing the ketamine drug for Rett syndrome and a gene therapy trial is planned.

We want to get a glimpse of what's going on in the brain in a quantitative, objective way and sensitive to subtle changes. More generally, we lack biomarkers reflecting brain activity, easy to quantify and unbiased. A machine could measure a biomarker and not be affected by subjective interpretations of how the patient behaves. "

Michela Fagiolini, PhD, Neuroscientist, Boston Children & # 39; s Hospital

Alteration of the excitement in autism

Fagiolini and Artoni, in close collaboration with Takao Hensch, PhD, and Charles Nelson, PhD of Boston Children's, began by thinking that people with autism had altered their states of behavior. Previous evidence indicates that cholinergic brain circuits involved in stimulation are particularly disturbed and that altered stimulation affects both spontaneous dilation / constriction of the pupil and heart rate.

Fagiolini's team, supported by IRCN at Boston Children's FFM The Kirby Neurobiology Center aims to measure pupil fluctuations in several mouse models with ASD, including mice carrying mutations causing Rett syndrome or CDKL5 disorder, as well as BTBR mice. The team discovered that spontaneous dilatation and constriction of the pupils were altered even before the animals began to exhibit symptoms similar to those of an ASD.

Moreover, in mice lacking MeCP2, the mutated gene in Rett syndrome, restoring a normal copy of the gene, in cholinergic brain circuits only, prevented the occurrence of pupillary abnormalities. as well as behavioral symptoms.

Predict Rett syndrome in girls

To systematically link the observed wakefulness changes to the cholinergic system, the team capitalized on an earlier Hensch discovery: mice lacking the LYNX1 protein showed improved cholinergic signaling. Based on about 60 hours of observation of these mice, the researchers "formed" an in-depth learning algorithm to recognize abnormal pupillary patterns. The same algorithm accurately estimated cholinergic dysfunction in mice deficient in BTBR, CDKL5, and MeCP2.

The team then proposed this algorithm to 35 girls with Rett syndrome and 40 people developing typical controls. Instead of measuring the pupils' pupils (because patients can shake), they used heart rate fluctuations as a measure of excitement. The algorithm nevertheless succeeded in identifying the girls with Rett, with an accuracy of 80% during the first and second years of life.

"These two biomarkers fluctuate in a similar way as they are approximations of the activity of autonomous excitation," Artoni said. "It's the so-called" fight or flight response. "

Autonomic excitation, a highly conserved brain property in different species, is a robust indicator of an impaired development trajectory, according to Fagiolini and Artoni.

Biomarkers for babies?

In an earlier study with Nelson, Fagiolini had shown that visual evoked potentials, an EEG measure of visual processing in the brain, could also serve as potential biomarkers of Rett's syndrome. She believes that these biomarkers could provide robust and affordable screening tools for infants and young children, warning of impending neurodevelopmental issues and helping to track the progression of their development or treatment.

"If we have non-invasive, easy-to-evaluate biomarkers, even a newborn or non-verbal patient could be monitored over a number of time points," Fagiolini says.