Abstract
Objective biobehavioral markers for mental health conditions remain elusive, with diagnosis typically relying on self-reports and clinical interviews. We investigate eye tracking as a potential marker of attentional and mood biases associated with symptoms of depression and suicidal ideation from self-reported screening questionnaires. We analyze eye movements from 126 young adults during reading and responding to emotionally loaded sentences. A deep learning framework was designed to account for intra-trial and inter-trial variations in eye movements, achieving an AUC of 0.793 (95% CI: 0.766–0.819) for identifying depression/suicidality against healthy controls, and 0.826 (95% CI: 0.798–0.853) for suicidality specifically. The model also exhibited moderate accuracy in differentiating depressed from suicidal individuals (AUC: 0.609, 95% CI: 0.569–0.646). Discriminative patterns were more pronounced during response generation and for stimuli of negative sentiment. These findings suggest that eye tracking can provide objective markers of self-reported symptom severity by measuring the impact of emotional stimuli on oculomotor control.
Similar content being viewed by others
Data availability
The full set of anonymized eye-tracking recordings and annotations are available upon request to shri@usc.edu.
Code availability
All presented analyses were implemented in Python (v12.0). All models were trained using two NVIDIA RTX 6000 GPUs within a secure server. The associated code is publicly accessible at https://github.com/usc-sail/precog-eye-dl.
References
for Health Metrics, I. & Evaluation. Global health data exchange (ghdx). https://vizhub.healthdata.org/gbd-results/ (2023). Accessed 4 March 2023.
Organization, W. H. Suicide. https://www.who.int/news-room/fact-sheets/detail/suicide (2023). Accessed 23 April 2025.
Abi-Dargham, A. et al. Candidate biomarkers in psychiatric disorders: state of the field. World Psychiatry 22, 236–262 (2023).
Bone, D., Lee, C.-C., Chaspari, T., Gibson, J. & Narayanan, S. Signal processing and machine learning for mental health research and clinical applications [perspectives]. IEEE Signal Process. Mag. 34, 196–195 (2017).
Harari, G. M., Müller, S. R., Aung, M. S. & Rentfrow, P. J. Smartphone sensing methods for studying behavior in everyday life. Curr. Opin. Behav. Sci. 18, 83–90 (2017).
Baumeister, R. F., Vohs, K. D. & Funder, D. C. Psychology as the science of self-reports and finger movements: whatever happened to actual behavior?. Perspect. Psychol. Sci. 2, 396–403 (2007).
Hauser, T. U., Skvortsova, V., De Choudhury, M. & Koutsouleris, N. The promise of a model-based psychiatry: building computational models of mental ill health. Lancet Digital Health 4, e816–e828 (2022).
Hansen, L. et al. Speech-and text-based classification of neuropsychiatric conditions in a multidiagnostic setting. Nat. Ment. Health 1, 971–981 (2023).
Schmaal, L. et al. ENIGMA MDD: seven years of global neuroimaging studies of major depression through worldwide data sharing. Transl. Psychiatry 10, 172 (2020).
de Aguiar Neto, F. S. & Rosa, J. L. G. Depression biomarkers using non-invasive eeg: a review. Neurosci. Biobehav. Rev. 105, 83–93 (2019).
Dennis, T. A. & Solomon, B. Frontal eeg and emotion regulation: electrocortical activity in response to emotional film clips is associated with reduced mood induction and attention interference effects. Biol. Psychol. 85, 456–464 (2010).
Murray, E. A., Wise, S. P. & Drevets, W. C. Localization of dysfunction in major depressive disorder: prefrontal cortex and amygdala. Biol. Psychiatry 69, e43–e54 (2011).
Botteron, K. N., Raichle, M. E., Drevets, W. C., Heath, A. C. & Todd, R. D. Volumetric reduction in left subgenual prefrontal cortex in early onset depression. Biol. Psychiatry 51, 342–344 (2002).
Skaramagkas, V. et al. Review of eye tracking metrics involved in emotional and cognitive processes. IEEE Rev. Biomed. Eng. 16, 260–277 (2021).
Eckstein, M. K., Guerra-Carrillo, B., Singley, A. T. M. & Bunge, S. A. Beyond eye gaze: what else can eyetracking reveal about cognition and cognitive development?. Dev. Cogn. Neurosci. 25, 69–91 (2017).
Stolicyn, A., Steele, J. D. & Seriès, P. Prediction of depression symptoms in individual subjects with face and eye movement tracking. Psychol. Med. 52, 1784–1792 (2022).
Tsypes, A., Owens, M. & Gibb, B. E. Suicidal ideation and attentional biases in children: An eye-tracking study. J. Affect. Disord. 222, 133–137 (2017).
Ramey, M. M., Yonelinas, A. P. & Henderson, J. M. Conscious and unconscious memory differentially impact attention: eye movements, visual search, and recognition processes. Cognition 185, 71–82 (2019).
Gotlib, I. H., Krasnoperova, E., Yue, D. N. & Joormann, J. Attentional biases for negative interpersonal stimuli in clinical depression. J. Abnorm. Psychol. 113, 127 (2004).
Suslow, T., Junghanns, K. & Arolt, V. Detection of facial expressions of emotions in depression. Percept. Mot. Skills 92, 857–868 (2001).
Sriram, H., Conati, C. & Field, T. Classification of alzheimer’s disease with deep learning on eye-tracking data. In Proceedings of the 25th International Conference on Multimodal Interaction, 104–113 (2023).
Kobo, O., Meltzer-Asscher, A., Berant, J. & Schonberg, T. Classification of depression tendency from gaze patterns during sentence reading. Biomed. Signal Process. Control 93, 106015 (2024).
Hodgson, T. L., Parris, B. A., Gregory, N. J. & Jarvis, T. The saccadic stroop effect: evidence for involuntary programming of eye movements by linguistic cues. Vis. Res. 49, 569–574 (2009).
Hollingworth, A. & Bahle, B. Eye tracking in visual search experiments. Spatial Learning and Attention Guidance 23–35 (2020).
Spitzer, R. L. et al. Validation and utility of a self-report version of prime-md: the phq primary care study. Jama 282, 1737–1744 (1999).
Joormann, J. & Gotlib, I. H. Emotion regulation in depression: relation to cognitive inhibition. Cognition Emot. 24, 281–298 (2010).
Maalouf, F. et al. Bias to negative emotions: a depression state-dependent marker in adolescent major depressive disorder. Psychiatry Res. 198, 28–33 (2012).
Cavanagh, J. F., Wiecki, T. V., Kochar, A. & Frank, M. J. Eye tracking and pupillometry are indicators of dissociable latent decision processes. J. Exp. Psychol.: Gen. 143, 1476 (2014).
Smith, S. M. & Krajbich, I. Gaze amplifies value in decision making. Psychol. Sci. 30, 116–128 (2019).
Shneidman, E. S.Suicide as Psychache: A Clinical Approach to Self-destructive Behavior (Jason Aronson, 1993).
Rudd, M. D. The prevalence of suicidal ideation among college students. Suicide Life-Threatening Behav. 19, 173–183 (1989).
Kroenke, K. et al. The phq-8 as a measure of current depression in the general population. J. Affect. Disord. 114, 163–173 (2009).
Spitzer, R. L., Kroenke, K., Williams, J. B. & Löwe, B. A brief measure for assessing generalized anxiety disorder: the gad-7. Arch. Intern. Med. 166, 1092–1097 (2006).
Wu, H. et al. Timesnet: Temporal 2d-variation modeling for general time series analysis. International Conference on Learning Representations (2023).
Szegedy, C. et al. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9 (2015).
Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In International Conference on Machine Learning, 3319–3328 (PMLR, 2017).
Acknowledgements
This study was sponsored by the Defense Advanced Research Projects Agency (DARPA) under cooperative agreement No. N660012324006. The content of the information does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred.
Author information
Authors and Affiliations
Contributions
K.A. contributed to the conception, design, analysis, and evaluation of the computational framework for eye movement analysis. K.A. and M.M. pre-processed the eye-tracking recordings. W.J., C.M., M.H., and T.M. contributed to the experimental design and acquisition of the data. D.B., A.H., R.C., Th.M., I.B., K.L., R.L., and S.N. contributed to the conception and design of the experimental procedure and data collection protocol. W.J., A.K., S.K., M.M., E.K., and D.B. contributed to the data analysis and interpretation of model results. R.L., I.B., E.K., D.B., and S.N. provided scientific oversight and supervision throughout the study implementation. All authors contributed to the writing of the manuscript and the figures.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Avramidis, K., Jeong, W., Kommineni, A. et al. Deep learning characterizes depression and suicidal ideation in young adults from eye movements. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-02550-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41746-026-02550-4
