An Agentic LLM-Based Framework for Population-Scale Mental Health Screening

TL;DR

This paper introduces an agentic LLM-based framework for scalable, adaptable mental health screening using clinical data, emphasizing stability, cost-efficiency, and trustworthy AI practices.

Contribution

It presents a novel, modular pipeline architecture with explicit policies and validation mechanisms for robust population-scale mental health assessment.

Findings

Framework converges to stable configurations like cosine similarity and Top-k

Controls evaluation costs and prevents regressions during adaptation

Demonstrates potential for large-scale mental health screening using clinical data

Abstract

Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from electronic records, telemedicine platforms, and population-level screening programs. At the same time, the emergence of novel AI-based approaches in healthcare calls for intelligent frameworks capable of processing domain-specific unstructured clinical information while adapting to patient-specific needs. This paper proposes an agentic framework for building robust LLM-based pipelines, where each stage is encapsulated as a LangChain agent governed by explicit policies and proxy-guided evaluation. Stages are incrementally locked once validated, ensuring that later adaptations cannot overwrite configurations without demonstrated improvement. The proposed framework evolves from feature-level exploration, through proxy-based tuning and freeze/rollback mechanisms, to full orchestration by an Orchestrator Agent that coordinates preprocessing, retrieval, selection, diversity, threshold optimization, and decoding. A proof-of-concept in transcript-based depression detection demonstrates that the framework converges to stable configurations, such as cosine similarity, dynamic Top-k, and threshold 0.75, while controlling evaluation costs and avoiding regressions. These results highlight the potential of agentic AI to enable population-level mental health screening over large clinical datasets, addressing critical challenges in trustworthiness, reproducibility, and adaptability required in healthcare environments.