Using Eye-Tracking During Sentence Reading to Identify Subject Tendency to Depression

Depression is a common and disabling mental health disorder, which impacts hundreds of millions of people worldwide. Current diagnosis methods rely almost solely on self-report and are prone to subjectivity and biases. In recent years, computational psychiatry has employed advanced sensing technology, utilizing rich data, in order to train accurate algorithms to detect depression from passive, non-invasive physiological markers. In order to better identify and treat depression, there is a need to identify it in a data-driven, objective way. Previous studies have demonstrated that participants with tendency to depression has an attentional bias toward negative stimuli; Eye-Tracking (ET) is an accurate surrogate of attention; Therefore, collecting ET during reading could be useful for passive identification of tendency to depression

The concept of data-driven diagnosis of mental illness in computational ways is gaining interest and use in many abnormalities. However, providing the proper experimental paradigm to support it and highlight the inherent differences, in a way that is robust and generalizable to the real world. An objective and quantitative identification of the tendency to depression will have major effect of early diagnosis and treatment on one of the most prevalent condition in current days

We used data from gaze-tracking while participants were engaged in sentence reading to build a classifier for depression tendency. We created sentences constructed to highlight expected attention biases in depression. We recorded gaze data during reading from a sample of 100 participants and analyzed the data as a raw time-series. We used the validated PHQ-9 questionnaire to obtain depression levels per participant. The technology allows to passively identify tendency to depression as this paradigm aims to identify attentional bias during reading.

Using this invention, eye-tracking can be used as a potential biomarker for detecting individual preference and pleasantness while engaged in VR, and in the future, allow real-time updating of VR content for various applications.

Fully active prototype

US Provisional

Sign up for
our events

    Life Science