Computer assisted assessment of depression from behavioural cues

Themes: Software technology & Intelligent Systems, Life Sicence & Health

Early lab scale demonstration

A TRL is a measure to indicate the matureness of a developing technology. When an innovative idea is discovered it is often not directly suitable for application. Usually such novel idea is subjected to further experimentation, testing and prototyping before it can be implemented. The image below shows how to read TRL’s to categorise the innovative ideas.

Click to enlarge


Fast and reliable diagnosis of depression is of vital importance. Current methods to assess depression are subjective as they rely on clinical interviews and self-report scales, and are time-consuming.


Our system supports a medical doctor in an objective and timely diagnosis. It’s based on analysing temporal dynamics of patients’ behaviour (e.g. temporal characteristics of facial expressions and movement of head) using computer vision and machine learning techniques.


The system can already discriminate three levels of depression severity, with a 78% accuracy. At least 150 psychiatric patients and 30 healthy subjects will be observed longitudinally in this research.

Dr. Hamdi Dibeklioğlu


Dr. Jan van Gemert

Prof. dr. ir. Marcel J.T. Reinders