Cross-Lingual Mental Health Ontologies for Indian Languages: Bridging Patient Expression and Clinical Understanding through Explainable AI and Human-in-the-Loop Validation

2025-10-06

AI Summary

India’s mental health communication faces dual challenges of linguistic fragmentation and insufficient cultural adaptation; existing NLP-based health ontologies and resources are overwhelmingly English-centric, failing to capture locally grounded expressions of psychological distress. To address this, we propose CL-PDE—a Cross-Lingual Psychological Distress Expression framework—that constructs, for the first time, a multilingual psychological stress expression graph. CL-PDE integrates graph neural networks for relational modeling, cross-lingual embedding alignment, clinical terminology mapping, and human-in-the-loop validation to automatically build and align a culturally sensitive, multilingual mental health ontology for India. This work bridges a critical gap in culturally embedded psychological state representation outside English-dominant contexts. It significantly improves both accuracy and interpretability of psychological state identification and establishes a methodological paradigm for multilingual mental health AI in the Global South.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Ontologies

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Mental health communication in India is linguistically fragmented, culturally diverse, and often underrepresented in clinical NLP. Current health ontologies and mental health resources are dominated by diagnostic frameworks centered on English or Western culture, leaving a gap in representing patient distress expressions in Indian languages. We propose cross-linguistic graphs of patient stress expressions (CL-PDE), a framework for building cross-lingual mental health ontologies through graph-based methods that capture culturally embedded expressions of distress, align them across languages, and link them with clinical terminology. Our approach addresses critical gaps in healthcare communication by grounding AI systems in culturally valid representations, allowing more inclusive and patient-centric NLP tools for mental health care in multilingual contexts.

Problem

• Addressing linguistic fragmentation in Indian mental health communication
• Bridging cultural gaps between patient expressions and clinical terminology
• Developing cross-lingual ontologies for culturally valid AI healthcare systems

Innovation

• Cross-linguistic graphs capture culturally embedded distress expressions
• Graph-based methods align patient expressions across languages
• Human-in-the-loop validation ensures culturally valid AI representations