Depression screening using a non-verbal self-association task: A machine-learning based pilot study

•Depression screening is often based on subjective verbal information.•Non-verbal behavioural data from self and emotion assessment can effectively identify depression with machine-learning.•Behavioural signatures to predict depression were identified.•Non-verbal depression screening may be a viable and cost-effective addition to depression screening.•Non-verbal depression screening may facilitate informed clinical decision-making.