Treating autism by targeting the temporal lobes

Identifying autism spectrum disorder in resting-state fNIRS signals based on multiscale entropy and a two-branch deep learning network

BACKGROUND

The demand for early and precise identification of autism spectrum disorder (ASD) presented a challenge to the prediction of ASD with a non-invasive neuroimaging method.

NEW METHOD

A deep learning model was proposed to identify children with ASD using the resting-state functional near-infrared spectroscopy (fNIRS) signals. In this model, the input was the pattern of brain complexity represented by multiscale entropy of fNIRS time-series signals, with the purpose to solve the problem of deep learning analysis when the raw signals were limited by length and the number of subjects. The model consisted of a two-branch deep learning network, where one branch was a convolution neural network and the other was a long short-term memory neural network based on an attention mechanism.

RESULTS

Our model could achieve an identification accuracy of 94%. Further analysis used the SHapley Additive exPlanations (SHAP) method to balance the accuracy and the number of optical channels, thus reducing the complexity of fNIRS experiment. COMPARISON WITH PREVIOUSLY USED METHOD(S): in identification accuracy, our model was about 14% higher than previously used deep learning models with the same input and 4% higher than the same model but directly using fNIRS signals as input. We could obtain a discriminative accuracy of 90% with nearly half of the measurement channels by the SHAP method.

CONCLUSIONS

Using the pattern of brain complexity as input was effective in the deep learning model when the fNIRS signals were insufficient. With the SHAP method, it was possible to reduce the number of optical channels, while maintaining high accuracy in ASD identification.

A Developmental Study of Abnormal Behaviors and Altered GABAergic Signaling in the VPA-Treated Rat Model of Autism

Although studies have investigated the role of gamma-aminobutyric acid (GABA)ergic signaling in rodent neural development and behaviors relevant to autism, behavioral ontogeny, as underlain by the changes in GABAergic system, is poorly characterized in different brain regions. Here, we employed a valproic acid (VPA) rat model of autism to investigate the autism-like behaviors and GABAergic glutamic acid decarboxylase 67 (GAD67) expression underlying these altered behaviors in multiple brain areas at different developmental stages from birth to adulthood. We found that VPA-treated rats exhibited behavioral abnormalities relevant to autism, including delayed nervous reflex development, altered motor coordination, delayed sensory development, autistic-like and anxiety behaviors and impaired spatial learning and memory. We also found that VPA rats had the decreased expression of GAD67 in the hippocampus (HC) and cerebellum from childhood to adulthood, while decreased GAD67 expression of the temporal cortex (TC) was only observed in adulthood. Conversely, GAD67 expression was increased in the prefrontal cortex (PFC) from adolescence to adulthood. The dysregulated GAD67 expression could alter the excitatory-inhibitory balance in the cerebral cortex, HC and cerebellum. Our findings indicate an impaired GABAergic system could be a major etiological factor occurring in the cerebral cortex, HC and cerebellum of human cases of autism, which suggests enhancement of GABA signaling would be a promising therapeutic target for its treatment.