IDEAS home Printed from https://ideas.repec.org/a/bjc/journl/v12y2025i5p2006-2021.html
   My bibliography  Save this article

Mindcare: A Multi-Agent AI Architecture for Personalized and Responsible Mental Health Support

Author

Listed:
  • Vishal Pattar

    (Dept. of Artificial Intelligence & Machine Learning PES’s Modern College of Engineering Pune, MH, India)

  • Tanishk Patil

    (Dept. of Artificial Intelligence & Machine Learning PES’s Modern College of Engineering Pune, MH, India)

  • Bhaskar Dhuri

    (Dept. of Artificial Intelligence & Machine Learning PES’s Modern College of Engineering Pune, MH, India)

  • Amanullah Karel

    (Dept. of Artificial Intelligence & Machine Learning PES’s Modern College of Engineering Pune, MH, India)

  • Aboli Deole

    (Dept. of Artificial Intelligence & Machine Learning PES’s Modern College of Engineering Pune, MH, India)

  • Sampada Kulkarni

    (Dept. of Information Technology PES’s Modern College of Engineering Pune, MH, India)

Abstract

Mental health challenges such as stress, anx- iety, depression, and loneliness are increasingly prevalent worldwide, exacerbated by stigma and limited access to professional care—especially in low-resource settings. This paper introduces MindCare, an AI-powered mental health companion chatbot designed to support individuals expe- riencing mild psychological distress. Leveraging fine-tuned large language models (LLMs), MindCare employs a mod- ular architecture with dedicated agents for intent recogni- tion, compliance checking, psychiatric response generation, memory management, correction, and empathetic interac- tion. The system is trained on curated, anonymized datasets from mental health forums and authoritative sources to ensure contextual accuracy and emotional sensitivity. Comparative evaluations show that MindCare outperforms generic conversational agents in emotional responsiveness, relevance, and user satisfaction. This study outlines the system design, data strategy, and evaluation methodology, positioning MindCare as a scalable and ethical digital tool for mental health support. Future work will focus on adding multilingual, voice-based interaction and real-time escalation to human counselors for enhanced accessibility and personalization.

Suggested Citation

  • Vishal Pattar & Tanishk Patil & Bhaskar Dhuri & Amanullah Karel & Aboli Deole & Sampada Kulkarni, 2025. "Mindcare: A Multi-Agent AI Architecture for Personalized and Responsible Mental Health Support," International Journal of Research and Scientific Innovation, International Journal of Research and Scientific Innovation (IJRSI), vol. 12(5), pages 2006-2021, May.
  • Handle: RePEc:bjc:journl:v:12:y:2025:i:5:p:2006-2021
    as

    Download full text from publisher

    File URL: https://www.rsisinternational.org/journals/ijrsi/digital-library/volume-12-issue-5/2006-2021.pdf
    Download Restriction: no

    File URL: https://rsisinternational.org/journals/ijrsi/articles/mindcare-a-multi-agent-ai-architecture-for-personalized-and-responsible-mental-health-support/
    Download Restriction: no
    ---><---

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:bjc:journl:v:12:y:2025:i:5:p:2006-2021. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Dr. Renu Malsaria (email available below). General contact details of provider: https://rsisinternational.org/journals/ijrsi/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.