MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory

2025-08-10

AI Summary

To address the high user burden, low efficiency, and difficulty in multi-dimensional assessment inherent in conventional mental health screening, this paper proposes the first adaptive, multi-dimensional psychological screening framework integrating large language models (LLMs) with Item Response Theory (IRT). Methodologically, it innovatively unifies multi-output language modeling with factor analysis to enable simultaneous, dynamic assessment across diagnostic dimensions—including depression, anxiety, eating disorders, and substance use disorders. It further introduces an information-theoretic question selection strategy and early termination mechanism to minimize response burden. Experimental evaluation on a newly curated dataset demonstrates that, compared to random item administration, the framework reduces total item count by 50%–87%: stable depression assessment requires only 29% of the original items, while eating disorder screening achieves reliable results with merely 15%. The approach thus achieves a favorable trade-off among diagnostic accuracy, administrative efficiency, and scalability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Recent advances in large language models (LLMs) offer new opportunities for scalable, interactive mental health assessment, but excessive querying by LLMs burdens users and is inefficient for real-world screening across transdiagnostic symptom profiles. We introduce MAQuA, an adaptive question-asking framework for simultaneous, multidimensional mental health screening. Combining multi-outcome modeling on language responses with item response theory (IRT) and factor analysis, MAQuA selects the questions with most informative responses across multiple dimensions at each turn to optimize diagnostic information, improving accuracy and potentially reducing response burden. Empirical results on a novel dataset reveal that MAQuA reduces the number of assessment questions required for score stabilization by 50-87% compared to random ordering (e.g., achieving stable depression scores with 71% fewer questions and eating disorder scores with 85% fewer questions). MAQuA demonstrates robust performance across both internalizing (depression, anxiety) and externalizing (substance use, eating disorder) domains, with early stopping strategies further reducing patient time and burden. These findings position MAQuA as a powerful and efficient tool for scalable, nuanced, and interactive mental health screening, advancing the integration of LLM-based agents into real-world clinical workflows.

Problem

• Reducing user burden in mental health screening via adaptive questioning
• Optimizing diagnostic accuracy across multiple symptom dimensions simultaneously
• Integrating LLMs with psychometrics for efficient clinical assessment

Innovation

• Combines multi-outcome modeling with IRT
• Adaptively selects most informative questions
• Reduces assessment questions by 50-87%