Federated Machine Learning for Multi-Aspect Neuro-developmental Disorders

Abstract

Autism Spectrum Disorder (ASD) is a neuro-developmental syndrome resulting from alterations in the embryological brain pre-birth. This disorder distinguishes its patients by special socially restricted and repetitive behavior, in addition to specific behavioral traits. Hence, this would possibly deteriorate their social behavior among other individuals, as well as their overall interaction within their community. Moreover, medical research has proved that ASD also affects the facial characteristics of its patients, making the syndrome recognizable from distinctive signs within an individual’s face. Given that as a motivation behind our work, we propose a novel privacy-preserving Federated Learning scheme to predict ASD in a certain individual based on their behavioral and facial features, embedding a merging process of both data features through facial feature extraction, while respecting patient data privacy. After training behavioral and facial image data on Federated Machine Learning models, promising results are achieved, with 70% accuracy for prediction of ASD according to behavioral traits in a federated learning private environment, and a 62% accuracy is reached for prediction of ASD given an image of the patient’s face. Then, we test the behavior of regular as well as federated learning on our merged data, behavioral and facial, where a 65% accuracy is achieved with regular logistic regression model and 63% accuracy with federated learning model.