# Artificial Intelligence-Based Depression Detection

## TL;DR

An AI system using eye tracking and iris recognition can detect depression with high accuracy, potentially preventing accidents caused by impaired decision-making in drivers and pilots.

## Contribution

A novel AI-based system combining iris identification and pupillometric analysis for real-time depression detection is introduced and validated.

## Key findings

- The depression-detecting CNN-LSTM network achieved 89% accuracy and an AUC of 0.94.
- Depressed individuals showed significantly greater pupil dilation in response to negative stimuli compared to non-depressed individuals.
- Depressed individuals exhibited slower saccadic movement and longer fixation times, consistent with cognitive distortions in depression.

## Abstract

Decisions made by pilots and drivers suffering from depression can endanger the lives of hundreds of people, as demonstrated by the tragedies of Germanwings flight 9525 and Air India flight 171. Since the detection of depression is currently based largely on subjective self-reporting, there is an urgent need for fast, objective, and reliable detection methods. In our study, we present an artificial intelligence-based system that combines iris-based identification with the analysis of pupillometric and eye movement biomarkers, enabling the real-time detection of physiological signs of depression before driving or flying. The two-module model was evaluated based on data from 242 participants: the iris identification module operated with an Equal Error Rate of less than 0.5%, while the depression-detecting CNN-LSTM network achieved 89% accuracy and an AUC value of 0.94. Compared to the neutral state, depressed individuals responded to negative news with significantly greater pupil dilation (+27.9% vs. +18.4%), while showing a reduced or minimal response to positive stimuli (−1.3% vs. +6.2%). This was complemented by slower saccadic movement and longer fixation time, which is consistent with the cognitive distortions characteristic of depression. Our results indicate that pupillometric deviations relative to individual baselines can be reliably detected and used with high accuracy for depression screening. The presented system offers a preventive safety solution that could reduce the number of accidents caused by human error related to depression in road and air traffic in the future.