Applying Deep Learning to Specific Learning Disorder Screening

TL;DR

This study explores using deep convolutional neural networks, specifically MobileNetV2, to automatically screen students for specific learning disorder from handwriting images, achieving promising accuracy for early detection.

Contribution

It is the first to apply deep learning to detect specific learning disorder through handwriting analysis, demonstrating potential for rapid screening.

Findings

Mean AUC of 0.89 on validation set

Deep CNN outperforms traditional screening methods

Potential for fast initial screening of students

Abstract

Early detection is key for treating those diagnosed with specific learning disorder, which includes problems with spelling, grammar, punctuation, clarity and organization of written expression. Intervening early can prevent potential negative consequences from this disorder. Deep convolutional neural networks (CNNs) perform better than human beings in many visual tasks such as making a medical diagnosis from visual data. The purpose of this study was to evaluate the ability of a deep CNN to detect students with a diagnosis of specific learning disorder from their handwriting. The MobileNetV2 deep CNN architecture was used by applying transfer learning. The model was trained using a data set of 497 images of handwriting samples from students with a diagnosis of specific learning disorder, as well as those without this diagnosis. The detection of a specific learning disorder yielded on the validation set a mean area under the receiver operating characteristics curve of 0.89. This is a novel attempt to detect students with the diagnosis of specific learning disorder using deep learning. Such a system as was built for this study, may potentially provide fast initial screening of students who may meet the criteria for a diagnosis of specific learning disorder.