Designing Trustworthy AI Systems for PTSD Follow-Up
Open Access
- 15 August 2025
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 13 (8) , 361
Abstract
Post-Traumatic Stress Disorder (PTSD) poses complex clinical challenges due to its emotional volatility, contextual sensitivity, and need for personalized care. Conventional AI systems often fall short in therapeutic contexts due to lack of explainability, ethical safeguards, and narrative understanding. We propose a hybrid neuro-symbolic architecture that combines Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), symbolic controllers, and ensemble classifiers to support clinicians in PTSD follow-up. The proposal integrates real-time anonymization, session memory through patient-specific RAG, and a Human-in-the-Loop (HITL) interface. It ensures clinical safety via symbolic logic rules derived from trauma-informed protocols. The proposed architecture enables safe, personalized AI-driven responses by combining statistical language modeling with explicit therapeutic constraints. Through modular integration, it supports affective signal adaptation, longitudinal memory, and ethical traceability. A comparative evaluation against state-of-the-art approaches highlights improvements in contextual alignment, privacy protection, and clinician supervision.Keywords
This publication has 16 references indexed in Scilit:
- A scoping review of large language models for generative tasks in mental health carenpj Digital Medicine, 2025
- Large Language Models and Empathy: Systematic ReviewJournal of Medical Internet Research, 2024
- Benefits and Risks of AI in Health Care: Narrative ReviewInteractive Journal of Medical Research, 2024
- From “Human in the Loop” to a Participatory System of Governance for AI in HealthcareThe American Journal of Bioethics, 2024
- Neurosymbolic AI: the 3rd waveArtificial Intelligence Review, 2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- Explainability for artificial intelligence in healthcare: a multidisciplinary perspectiveBMC Medical Informatics and Decision Making, 2020
- Clinical Decision Support in the Era of Artificial IntelligenceJAMA, 2018
- AI4People—An Ethical Framework for a Good AI Society: Opportunities, Risks, Principles, and RecommendationsMinds and Machines, 2018
- DEAP: A Database for Emotion Analysis ;Using Physiological SignalsIEEE Transactions on Affective Computing, 2011