Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives

TL;DR

Anonpsy is a novel graph-based framework that enhances psychiatric narrative de-identification by preserving clinical structure while reducing re-identification risk through semantic graph-guided rewriting.

Contribution

It introduces a graph-guided semantic rewriting approach that maintains clinical structure and reduces identifiability better than existing text-level methods.

Findings

Anonpsy preserves diagnostic fidelity in psychiatric narratives.

It achieves lower re-identification risk compared to LLM-only rewriting.

The framework effectively balances clinical utility and privacy protection.

Abstract

Psychiatric narratives encode patient identity not only through explicit identifiers but also through idiosyncratic life events embedded in their clinical structure. Existing de-identification approaches, including PHI masking and LLM-based synthetic rewriting, operate at the text level and offer limited control over which semantic elements are preserved or altered. We introduce Anonpsy, a de-identification framework that reformulates the task as graph-guided semantic rewriting. Anonpsy (1) converts each narrative into a semantic graph encoding clinical entities, temporal anchors, and typed relations; (2) applies graph-constrained perturbations that modify identifying context while preserving clinically essential structure; and (3) regenerates text via graph-conditioned LLM generation. Evaluated on 90 clinician-authored psychiatric case narratives, Anonpsy preserves diagnostic fidelity while achieving consistently low re-identification risk under expert, semantic, and GPT-5-based evaluations. Compared with a strong LLM-only rewriting baseline, Anonpsy yields substantially lower semantic similarity and identifiability. These results demonstrate that explicit structural representations combined with constrained generation provide an effective approach to de-identification for psychiatric narratives.