Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study

TL;DR

This study demonstrates the feasibility of using deep learning models to detect hand flapping behaviors in children from unstructured home videos, aiming to assist in earlier autism diagnosis.

Contribution

It introduces a deep learning approach utilizing landmark-driven methods and MobileNet V2 to identify autism-related hand flapping behaviors in videos.

Findings

Achieved a testing F1 score of 84% in detecting hand flapping.

Utilized 75 videos from the SSBD dataset with 100 hand flapping clips.

Demonstrated the potential of digital tech to aid autism diagnosis.

Abstract

A formal autism diagnosis can be an inefficient and lengthy process. Families may wait months or longer before receiving a diagnosis for their child despite evidence that earlier intervention leads to better treatment outcomes. Digital technologies which detect the presence of behaviors related to autism can scale access to pediatric diagnoses. This work aims to demonstrate the feasibility of deep learning technologies for detecting hand flapping from unstructured home videos as a first step towards validating whether models and digital technologies can be leveraged to aid with autism diagnoses. We used the Self-Stimulatory Behavior Dataset (SSBD), which contains 75 videos of hand flapping, head banging, and spinning exhibited by children. From all the hand flapping videos, we extracted 100 positive and control videos of hand flapping, each between 2 to 5 seconds in duration. Utilizing both landmark-driven-approaches and MobileNet V2's pretrained convolutional layers, our highest performing model achieved a testing F1 score of 84% (90% precision and 80% recall) when evaluating with 5-fold cross validation 100 times. This work provides the first step towards developing precise deep learning methods for activity detection of autism-related behaviors.