Linguistic markers for identifying post-traumatic stress disorder and associated symptoms: a systematic literature review
Abstract
Objectives: Diagnosing post-traumatic stress disorder (PTSD) remains a challenge due to symptom variability and comorbidities. Linguistic analysis offers an innovative approach to identify PTSD symptoms and severity. This systematic review aimed at identifying linguistic features associated with PTSD, assessing the quality and limitations of existing studies, summarizing the predictive performance of identified models, and describing the clinical utility of these models.
Materials: A comprehensive search was conducted across multiple databases, resulting in the identification of 593 articles. After screening and eligibility assessment, 58 studies were included.
Methods: Data extraction focused on study characteristics, methodology, and performance metrics. We assessed the risk of bias using the PROBAST and conducted both a narrative synthesis and a meta-analysis.
Results: Linguistic features such as pronoun use, emotional valence, cognitive processing words, narrative length, discourse disorganization, temporal orientation, specific lexical fields (death, anxiety, sensory-perception details), and disfluencies were commonly investigated. The meta-analysis revealed a pooled area under the curve of 0.81, indicating the high performance of classification models. However, significant publication bias and heterogeneity were noted. Only 8 studies were rated with a low risk of bias, highlighting common issues such as inadequate control groups, unvalidated linguistic tools,…
How strong is the evidence?
Evidence Hub reads this as a meta-analysis, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.