Mapping OCD Symptom Triggers with Large Language Models

preprint OA: closed
View at publisher

Abstract

Recent advancements in natural language processing (NLP) and large language models (LLMs) offer new avenues for exploring previously under-researched areas in mental health. Their capacity to automatically and meaningfully analyze large-scale text data makes them particularly valuable for studying highly individualized clinical phenomena, such as triggers of obsessive-compulsive symptoms (OCS), where pattern identification is often challenging. To address this gap, we asked 1,495 individuals to identify their most common triggers, rate their intensity, and report the severity of their contamination-related OCS. Using LLM-based embeddings, we generated a map of key trigger categories, revealing their diversity across ecological domains and varying degrees of semantic similarity. Monte Carlo simulations further showed that individuals frequently reported semantically similar trigger pairs that differed in intensity. These findings are clinically significant, providing a foundation for a more fine-grained understanding of OCS treatment mechanisms and paving the way for novel therapeutic approaches.

My notes (saved in your browser only)

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00