Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191789,
        author = {Kunal Mansukhani and Vaibhav Srivastav and Priyanka Yadav and Gyandas Somaiya},
        title = {MindEase},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7688-7694},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191789},
        abstract = {This paper presents MindEase, an integrated AI-driven mental-wellness support system that combines Generative AI–based therapeutic
reasoning, automated crisis-intent detection, and structured psychological assessment into a unified framework designed for individuals experiencing depression, stress, and emotional imbalance. Modern mental-health challenges involve intertwined factors such as cognitive distortions, behavioral withdrawal, mood fluctuations, and crisis tendencies; however, existing digital wellness tools typically address these components independently, leading to inconsistent or unsafe user guidance. To overcome these limitations, MindEase introduces a multi-module AI architecture— Therapeutic Chat Engine, PHQ-9 Depression Assessment, Mood Tracking, Psychoeducation Retrieval, and Crisis-Safety Intervention— coordinated through a FastAPI-based backend capable of processing multimodal inputs including free-text emotions, depression categories, and quantified questionnaire scores.
The system employs OpenAI’s GPT-4o-mini for rapid, therapy-aligned reasoning, substantially reducing hallucination through structured CBT- based prompting and category-specific emotional grounding. Meanwhile, a lightweight keyword-driven Crisis Detection Layer ensures reliable identification of self-harm indicators, triggering immediate safety protocols and halting AI response generation. Evaluation across 120+ simulated mental-health scenarios covering diverse emotional intensities demonstrates high overall performance: 95.1% empathy accuracy, 94.3% CBT-alignment consistency, 93.7% crisis-intent detection accuracy, 100% PHQ-9 severity classification correctness, and 92.4% clarity in psychoeducational guidance. The system’s integrated reasoning pipeline ensures coherent, safe, and contextually relevant therapeutic support compared to conventional chatbot-based wellness tools.
The findings establish MindEase as a scalable, low-latency, and psychologically grounded digital-therapy platform suitable for real-world deployment, particularly for users with limited access to professional mental-health services. The framework also lays the foundation for next-generation AI-enhanced emotional- wellness systems with the potential to transform accessible mental-health support globally.},
        keywords = {AI Therapy, Generative AI, CBT, Mental-Health Support, Crisis Detection, PHQ-9, Emotional Well-being, GPT-4o-mini.},
        month = {January},
        }