Automated Schizophrenia Detection from Handwriting Samples via Transfer Learning Convolutional Neural Networks

TL;DR

The paper tackles the need for objective, non-invasive schizophrenia screening by leveraging a transfer-learning CNN on handwriting images. Using Crespo et al. 2019 data, the authors preprocess and augment a small image dataset, compare multiple CNNs, and find InceptionV3 to be the top performer with approximately 92% accuracy. They also deliver a clinician-facing secure web platform to deploy the model in real-world settings. The work demonstrates the feasibility of handwriting-based biomarkers for schizophrenia and paves the way for broader, data-rich extensions and integration with other clinical signals.

Abstract

Schizophrenia is a globally prevalent psychiatric disorder that severely impairs daily life. Schizophrenia is caused by dopamine imbalances in the fronto-striatal pathways of the brain, which influences fine motor control in the cerebellum. This leads to abnormalities in handwriting. The goal of this study was to develop an accurate, objective, and accessible computational method to be able to distinguish schizophrenic handwriting samples from non-schizophrenic handwriting samples. To achieve this, data from Crespo et al. (2019) was used, which contains images of handwriting samples from schizophrenic and non-schizophrenic patients. The data was preprocessed and augmented to produce a more robust model that can recognize different types of handwriting. The data was used to train several different convolutional neural networks, and the model with the base architecture of InceptionV3 performed the best, differentiating between the two types of image with a 92% accuracy rate. To make this model accessible, a secure website was developed for medical professionals to use for their patients. Such a result suggests that handwriting analysis through computational models holds promise as a non-invasive and objective method for clinicians to diagnose and monitor schizophrenia.

Figures (8)

• Figure 1: An image of handwriting taken from a non-schizophrenic patient.
• Figure 2: An image of handwriting taken from a schizophrenic patient.
• Figure 3: The participants' view of data collection. Participants followed the loops on an A4 paper affixed to a digital tablet with a digital pen, and the Ductus software was used to collect data.
• Figure 4: The image data that was received from the researchers.
• Figure 5: The image data after undergoing all four steps of pre-processing: cropping, centering, padding, and the LoG filter.