Retrieval Augmented Generation System for Mental Health Information

Hurmat Ali Shah, Ashhadul Islam, Zain Ul Abideen Tariq, Samir B. Belhaouari, Mowafa Househ

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Retrieval Augmented Generation (RAG) systems enable LLMs to avoid hallucinations and thus can be used for knowledge-intensive tasks that require higher accuracy. RAG systems have been developed for a variety of purposes, including some health-related domains. But developing a RAG system specifically tailored for mental health and based on highly reputable scientific evidence has not been considered. This paper proposes an accurate RAG system for mental health. The proposed RAG system can be useful for policymakers in designing specific interventions for mental health issues by building further support systems around it. The RAG system can be extended through more knowledge base and can help in mental health counselling. This study validates the utility of RAG systems in augmenting information retrieval for mental health, emphasizing the importance of leveraging external knowledge bases to ensure data accuracy and reliability.

Original languageEnglish
Title of host publicationMEDINFO 2025 - Healthcare Smart x Medicine Deep
Subtitle of host publicationProceedings of the 20th World Congress on Medical and Health Informatics
EditorsMowafa S. Househ, Mowafa S. Househ, Zain Ul Abideen Tariq, Mahmood Al-Zubaidi, Uzair Shah, Elaine Huesing
PublisherIOS Press BV
Pages693-697
Number of pages5
ISBN (Electronic)9781643686080
DOIs
Publication statusPublished - 7 Aug 2025
Event20th World Congress on Medical and Health Informatics, MEDINFO 2025 - Taipei, Taiwan, Province of China
Duration: 9 Aug 202513 Aug 2025

Publication series

NameStudies in Health Technology and Informatics
Volume329
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference20th World Congress on Medical and Health Informatics, MEDINFO 2025
Country/TerritoryTaiwan, Province of China
CityTaipei
Period9/08/2513/08/25

Keywords

  • Retrieval augmented generation
  • information retrieval
  • large language models
  • mental health
  • natural language processing

Fingerprint

Dive into the research topics of 'Retrieval Augmented Generation System for Mental Health Information'. Together they form a unique fingerprint.

Cite this