Adaptive LLM-Generated Questionnaires for Suicide Risk Assessment: A Clinical Pilot in Greece

Read full text Summarise with VIRAT
Authors: Dimitrios Georgiou, Akis Makrigiannis, Andreas Kanavos
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project presents an early-stage clinical pilot of an adaptive questionnaire system that integrates large language models (LLMs) with fuzzy logic and clinician-defined constraints to support suicide risk assessment within a preventive therapeutic context. The system generates weekly personalized questionnaires that evolve based on prior responses, emotional tone, and patient history, under continuous clinician supervision. The pilot was conducted at KLIMAKA Suicide Prevention Center, Athens, Greece, in collaboration with the Greek Ministry of Health. Ethical approval was granted by the Scientific Committee of KLIMAKA (Protocol Number: KL-2025-07/ETH, July 2025). All data were fully anonymized and de-identified. This registration is retrospective, as the pilot was integrated into routine clinical care prior to formal registration.

Fields of Study & Subjects

Suicide and Self-Harm Studies Mental Health via Writing Artificial Intelligence in Healthcare and Education

Publication details

Publication date
1 January 2026
Language
EN
Document type
Preprint