Handwriting and Drawing for Depression Detection: A Preliminary Study

TL;DR

This study explores the use of online handwriting and drawing analysis to differentiate between healthy individuals, those with sub-clinical depressive traits, and clinically depressed patients, aiming to aid mental health diagnosis.

Contribution

It introduces a novel online handwriting and drawing analysis method with specific features that can distinguish different depression levels.

Findings

Time features effectively differentiate healthy and sub-clinical individuals.

Ductus and Pressure features distinguish clinical depression from healthy controls.

Seventeen features were analyzed using ANOVA to identify discriminative markers.

Abstract

The events of the past 2 years related to the pandemic have shown that it is increasingly important to find new tools to help mental health experts in diagnosing mood disorders. Leaving aside the longcovid cognitive (e.g., difficulty in concentration) and bodily (e.g., loss of smell) effects, the short-term covid effects on mental health were a significant increase in anxiety and depressive symptoms. The aim of this study is to use a new tool, the online handwriting and drawing analysis, to discriminate between healthy individuals and depressed patients. To this aim, patients with clinical depression (n = 14), individuals with high sub-clinical (diagnosed by a test rather than a doctor) depressive traits (n = 15) and healthy individuals (n = 20) were recruited and asked to perform four online drawing /handwriting tasks using a digitizing tablet and a special writing device. From the raw collected online data, seventeen drawing/writing features (categorized into five categories) were extracted, and compared among the three groups of the involved participants, through ANOVA repeated measures analyses. Results shows that Time features are more effective in discriminating between healthy and participants with sub-clinical depressive characteristics. On the other hand, Ductus and Pressure features are more effective in discriminating between clinical depressed and healthy participants.