# Towards Multi-Brain Decoding in Autism: A Self-Supervised Learning Approach

## TL;DR

This study uses self-supervised learning to analyze brain activity during social interactions to better understand autism.

## Contribution

A novel self-supervised learning approach for multi-brain decoding in autism using hyperscanning EEG data.

## Key findings

- The SSL model achieved 78.13% accuracy and 98.90% recall in classifying autism during social interactions.
- SSL outperformed supervised baselines and logistic regression using spectral EEG biomarkers.
- The method addresses the challenge of limited labeled data in autism diagnosis.

## Abstract

This study introduces a self-supervised learning (SSL) approach to hyperscanning electroencephalography (EEG) data, targeting the identification of autism spectrum condition (ASC) during social interactions. Hyperscanning enables simultaneous recording of neural activity across interacting individuals, offering a novel path for studying brain-to-brain synchrony in ASC. Leveraging an unlabeled, large-scale single-brain EEG dataset for SSL pretraining, we developed a multi-brain classification model fine-tuned with hyperscanning data from dyadic interactions involving ASC and neurotypical participants. The SSL model demonstrated superior performance (78.13% accuracy and 98.90% recall) compared to supervised baselines and logistic regression using spectral EEG biomarkers. These results underscore the efficacy of SSL in addressing the challenges of limited labeled data, enhancing EEG-based diagnostic tools for ASC, and advancing research in social neuroscience.

The online version contains supplementary material available at 10.1007/s12021-025-09755-0.