Skip to main content
Advertisement
Live broadcast

The expert spoke about the pros and cons of AI as a psychologist

Kinkulkina's psychiatrist: chatbots should not replace a doctor, but they can help in the beginning
0
Photo: IZVESTIA/Polina Violet
Озвучить текст
Select important
On
Off

Chatbots can lower the barrier to seeking help for psychological problems, but using them instead of a psychiatrist or psychotherapist poses serious risks. Marina Kinkulkina, Director of the S.S. Korsakov Psychiatric Clinic at Sechenov University, Corresponding Member of the Russian Academy of Sciences, Professor, MD, told Izvestia about this.

According to the expert, it is sometimes easier for a person to tell their problems to a chatbot due to the lack of fear of condemnation or violation of confidentiality. In psychology, this is called the "online disinhibition effect."

"When a person communicates with a chatbot, these fears go away, and it's much easier for them to talk about their problems," Kinkulkina noted.

Lowering the threshold for seeking help can be useful, especially for people who are afraid to tell a specialist about stigmatizing conditions. At the same time, it is important that in further communication the chatbot recommends contacting a psychiatrist or psychotherapist, rather than independently diagnosing or prescribing treatment, the specialist noted.

But using AI as a substitute for a doctor, on the contrary, can lead to the postponement of necessary medical care. According to Kinkulkina, a person may form a "surrogate therapeutic alliance" — the feeling that they are already receiving treatment, although there is no full-fledged psychotherapy.

"This leads to a postponement of the necessary intervention. It turns out such an illusion of solving the problem through a dialogue with a bot. But this is an illusion, not a real psychotherapeutic job," the specialist explained.

The expert called the inability of language models to recognize certain dangerous conditions another risk. In particular, a chatbot may not notice signs of suicidal or auto-aggressive behavior if a person does not express them directly.

Read more in the Izvestia article:

Trust, but verify: is AI capable of working with the human psyche

Переведено сервисом «Яндекс Переводчик»

Live broadcast