SUPR
finetune LLMs to guide the treatment of emtion-related sickness
Dnr:

NAISS 2024/22-1306

Type:

NAISS Small Compute

Principal Investigator:

Xin Sun

Affiliation:

Linköpings universitet

Start Date:

2024-10-16

End Date:

2025-11-01

Primary Classification:

10201: Computer Sciences

Webpage:

Allocation

Abstract

Depression is one of the most prevalent mental health disorders worldwide, affecting millions of individuals. Despite the availability of various treatment options, including medication, psychotherapy, and behavioural interventions, the accessibility and effectiveness of mental health care remain a significant challenge. Advances in artificial intelligence, particularly Large Language Models (LLMs) such as GPT-4 and Llama, present a promising opportunity to assist in the treatment of depression. These models can provide personalized, accessible, and scalable support for individuals suffering from depression by offering early detection, cognitive behavioural therapy (CBT) interventions, and conversational support. This research proposes leveraging LLMs to assist healthcare professionals in treating depression by exploring their role in supporting therapeutic interventions, detecting depressive symptoms, and enhancing patient engagement.