Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.

Interdisciplinary approach to identify language markers for post-traumatic stress disorder using machine learning and deep learning

Open access

Abstract

Post-traumatic stress disorder (PTSD) lacks clear biomarkers in clinical practice. Language as a potential diagnostic biomarker for PTSD is investigated in this study. We analyze an original cohort of 148 individuals exposed to the November 13, 2015, terrorist attacks in Paris. The interviews, conducted 5–11 months after the event, include individuals from similar socioeconomic backgrounds exposed to the same incident, responding to identical questions and using uniform PTSD measures. Using this dataset to collect nuanced insights that might be clinically relevant, we propose a three-step interdisciplinary methodology that integrates expertise from psychiatry, linguistics, and the Natural Language Processing (NLP) community to examine the relationship between language and PTSD. The first step assesses a clinical psychiatrist's ability to diagnose PTSD using interview transcription alone. The second step uses statistical analysis and machine learning models to create language features based on psycholinguistic hypotheses and evaluate their predictive strength. The third step is the application of a hypothesis-free deep learning approach to the classification of PTSD in our cohort. Results show that the clinical psychiatrist achieved a diagnosis of PTSD with an AUC of 0.72. This is comparable to a gold standard questionnaire (Area Under Curve (AUC) ≈ 0.80). The machine learning model achieved a diagnostic AUC of 0.69. The deep learning approach achieved an AUC of 0.64. An examination of model error informs our discussion. Importantly, the study controls for confounding factors, establishes associations between language and DSM-5 subsymptoms, and integrates automated methods with qualitative analysis. This study provides a direct and methodologically robust description of the relationship between PTSD and language. Our work lays the groundwork for advancing early and accurate diagnosis and using linguistic markers to assess the effectiveness of pharmacological treatments and psychotherapies.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-024-61557-7

Cites

67 of 67 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Graphical abstract that summarizes our methodological approach and contributions (A1: Direct Exposure, A2: Witnessing Trauma).
Figure 1 Graphical abstract that summarizes our methodological approach and contributions (A1: Direct Exposure, A2: Witnessing Trauma).CC BY · PubMed Central
Figure 2 Description of the research mindset adopted in this article. The evidence presented is the result of an interdisciplinary workflow applied to an original dataset.
Figure 2 Description of the research mindset adopted in this article. The evidence presented is the result of an interdisciplinary workflow applied to an original dataset.CC BY · PubMed Central
Figure 3 Description of the process of building the Deep Learning Dataset to avoid data leakage and ensure representative distribution.
Figure 3 Description of the process of building the Deep Learning Dataset to avoid data leakage and ensure representative distribution.CC BY · PubMed Central
Figure 4 Description of the Inference process for a new document, using the CNN model.
Figure 4 Description of the Inference process for a new document, using the CNN model.CC BY · PubMed Central
Figure 5 Features Importances of the diagnosis and all the criteria. The Feature importance is the average over 100 random runs for the model achieving the best results.
Figure 5 Features Importances of the diagnosis and all the criteria. The Feature importance is the average over 100 random runs for the model achieving the best results.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

4 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 63 references

Research works printed but not linked: 6

  1. Auxéméry, Y. & Gayraud, F. Identification des marques du traumatisme psychique dans le langage parlé : définition de l’échelle diagnostique « SPLIT-10 ». Ann. Méd.-Psychol. Rev. Psychiatr. 179, 869–888 (2021).
  2. Gayraud, F. & Auxéméry, Y. Identification of the marks of psychic trauma in spoken language: Definition of the “SPLIT-10” diagnostic scale. Ann. Méd.-Psychol. Rev. Psychiatr. 180, 195–212 (2022).
  3. Gupta, A., Kaur, M., Bajaj, A. & Khanna, A. Entailment and spectral clustering based single and multiple document summarization. Int. J. Intell. Syst. Appl. 11, 39–51 (2019).
  4. da Rocha, D. et al. Programme 13-Novembre, un an après. Rev. Neuropsychol. 8, 227–232 (2016).
  5. Piolat, A., Booth, R. J., Chung, C. K., Davids, M. & La Pennebaker, J. W. version française du dictionnaire pour le LIWC: modalités de construction et exemples d’utilisation. Psychol. Fr. 56, 145–159 (2011).
  6. Pranckevičius, T. & Marcinkevičius, V. Comparison of Naive Bayes, random forest, decision tree, support vector machines, and logistic regression classifiers for text reviews classification. Balt. J. Mod. Comput. 5, 221 (2017).

Cited by

See all 24

Metadata

Authors
Quillivic, R., Gayraud, F., Auxéméry, Y., Vanni, L., Peschanski, D., Eustache, F., Dayan, J., & Mesmoudi, S.
Affiliations
  • École Pratique des Hautes Études (FR)
  • Centre National de la Recherche Scientifique (FR)
  • Inserm (FR)
Corresponding author
Quillivic, Robin
Venue
Scientific Reports
Published
2024-05-30
Volume
14
Issue
1
Pages
12468-12468
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4399155231
Cited by
24
References
63
Citations by year
2026: 10 · 2025: 12 · 2024: 2
FWCI
11.36
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • HAL (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • Region île-de-France (CP2021-297)
  • Centre National de la Recherche Scientifique
  • French General Secretariat for Investment (ANR-10-EQPX-0021-01)
Topics
  • Social Sciences › Psychology › Social Psychology › Mental Health via Writing
  • Social Sciences › Psychology › Clinical Psychology › Posttraumatic Stress Disorder Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
post-traumatic stress disorder, linguistic markers, psycholinguistics, PTSD diagnosis, natural language processing, deep learning classification, interview transcription, 2015 Paris attacks, linguistic biomarkers
MeSH terms
Machine Learning, Deep Learning, Adult, Female, Humans, Language, Male, Middle Aged, Natural Language Processing, Stress Disorders, Post-Traumatic, Biomarkers

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Interdisciplinary approach to identify language markers for post-traumatic stress disorder using machine learning and deep learning. https://app.cochat.ai/papers/10.1038/s41598-024-61557-7
The paper
Quillivic, R., Gayraud, F., Auxéméry, Y., Vanni, L., Peschanski, D., Eustache, F., Dayan, J., & Mesmoudi, S. (2024). Interdisciplinary approach to identify language markers for post-traumatic stress disorder using machine learning and deep learning. Scientific Reports. https://doi.org/10.1038/s41598-024-61557-7

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.