JMIR Publications

ABSTRACT

Background:

Large language models (LLMs) such as ChatGPT are increasingly being used by people suffering from depression to discuss mental health problems.

Objective:

Based on a representative survey it was studied, i) how widespread the use of these LLMs is, ii) how positive or negative they are perceived by the users and iii) how benefits of LLMs were perceived in comparison to face-to-face psychotherapy.

Methods:

In March 2026, a representative online survey was conducted in Germany (age 16 to 39; n = 2,500). Among the participants, 537 (21.5%) reported having been professionally diagnosed with a life-time diagnosis of depression. In this subgroup, the use of LLM in the past 30 days concerning depression was assessed as well as how beneficial this use was perceived (n=185). In those who had also undergone psychotherapy (n=143) the experiences with LLMs were compared to those with psychotherapy.

Results:

56% of people with diagnosed depression reported having used LLMs recently for mental health purposes, and 35% of those had done so specifically concerning their depression. The majority perceived LLMs as positive, e.g. felt empowered after using LLMs (75.3%). However, contrary to these and other positive perceptions, 52.9% reported thoughts of self-harm or suicide following the conversations. Of those who had already undergone psychotherapy, 28.7% claimed that the conversations with LLMs were better than with the psychotherapist, and 17.7% said the opposite.

Conclusions:

The broad, unguided use of LLMs and both the huge potential benefits and risks for people suffering from depression call for urgent research in this area.