CoChat

The DOI matches its Crossref record; the references it cites are not checked yet.

Systematic review of machine learning in PTSD studies for automated diagnosis evaluation

Open access
Wu, Yuqi, Mao, Kaining, Dennett, Liz, Zhang, Yanbo, Chen, Jie · 2023 · npj Mental Health Research

Abstract

Post-traumatic stress disorder (PTSD) is frequently underdiagnosed due to its clinical and biological heterogeneity. Worldwide, many people face barriers to accessing accurate and timely diagnoses. Machine learning (ML) techniques have been utilized for early assessments and outcome prediction to address these challenges. This paper aims to conduct a systematic review to investigate if ML is a promising approach for PTSD diagnosis. In this review, statistical methods were employed to synthesize the outcomes of the included research and provide guidance on critical considerations for ML task implementation. These included (a) selection of the most appropriate ML model for the available dataset, (b) identification of optimal ML features based on the chosen diagnostic method, (c) determination of appropriate sample size based on the distribution of the data, and (d) implementation of suitable validation tools to assess the performance of the selected ML models. We screened 3186 studies and included 41 articles based on eligibility criteria in the final synthesis. Here we report that the analysis of the included studies highlights the potential of artificial intelligence (AI) in PTSD diagnosis. However, implementing AI-based diagnostic systems in real clinical settings requires addressing several limitations, including appropriate regulation, ethical considerations, and protection of patient privacy.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1038/s44184-023-00035-w

Cites

Statistics

Figures

Fig. 1 Machine learning model types. This figure introduced typical types of machine learning, including supervised learning, unsupervised learning, and reinforcement learning. In addition, most used models were listed based on specific tasks. For reinforcement learning, since it was not used in any included study, we did not explicitly introduce common models. Abbreviations: NB Naïve Bayes classifier, LR Logistic Regression classifier, SVM Support Vector Machine, DT Decision Tree classifier, RF Random Forest classifier, GB Gradient Boosting classifier, DL Deep Learning models, SVD Singular Value Decomposition, t-SNE t-Distributed Stochastic Neighbor Embedding, UANP Uniform Manifold Approximation and Projection, PCA Principal Component Analysis.
Fig. 1 Machine learning model types. This figure introduced typical types of machine learning, including supervised learning, unsupervised learning, and reinforcement learning. In addition, most used models were listed based on specific tasks. For reinforcement learning, since it was not used in any included study, we did not explicitly introduce common models. Abbreviations: NB Naïve Bayes classifier, LR Logistic Regression classifier, SVM Support Vector Machine, DT Decision Tree classifier, RF Random Forest classifier, GB Gradient Boosting classifier, DL Deep Learning models, SVD Singular Value Decomposition, t-SNE t-Distributed Stochastic Neighbor Embedding, UANP Uniform Manifold Approximation and Projection, PCA Principal Component Analysis.CC BY · PubMed Central
Fig. 2 PRISMA flowchart of study selection and review process. This figure described the entire procedure of study selection based on the PRISMA systematic review guideline. We started with 3186 studies from six different databases. After duplication removal, abstract and title screening, and full-text screening, we finally ended up with 41 studies for this review. Detail selection process can refer to the Methods section.
Fig. 2 PRISMA flowchart of study selection and review process. This figure described the entire procedure of study selection based on the PRISMA systematic review guideline. We started with 3186 studies from six different databases. After duplication removal, abstract and title screening, and full-text screening, we finally ended up with 41 studies for this review. Detail selection process can refer to the Methods section.CC BY · PubMed Central
Fig. 3 Histogram of various ML models with system accuracy. This figure counted the occurrence of each ML model the authors reported as the best model from the included studies. The blue bar represents model accuracy between 70–80%, the orange bar represents model accuracy between 80–90%, and the green bar represents model accuracy above 90%. Abbreviations: EN Elastic Net, SL SuperLearner, PCA Principal Component Analysis, Cust. Customized Model, LGB light GB, MM Multiple Models.
Fig. 3 Histogram of various ML models with system accuracy. This figure counted the occurrence of each ML model the authors reported as the best model from the included studies. The blue bar represents model accuracy between 70–80%, the orange bar represents model accuracy between 80–90%, and the green bar represents model accuracy above 90%. Abbreviations: EN Elastic Net, SL SuperLearner, PCA Principal Component Analysis, Cust. Customized Model, LGB light GB, MM Multiple Models.CC BY · PubMed Central
Fig. 4 Sample distribution box plot of different PTSD diagnostic methods. This figure visualized the distribution of database sample size the authors adopted for ML training in log scale for different PTSD diagnostic tools. Outliers were indicated by the black solid diamond symbol. In each individual box, the upper horizontal line represented maximum sample size (excluding the outliers) while the bottom horizontal line represented minimum sample size (excluding the outliers). The “whiskers” are lines that extend from the box to the minimum and maximum values in the dataset. For the box, it represented the region where the majority sample size distribution (fist quartile to third quartile) with the central line representing median sample size. Different color represented different PTSD diagnostic method.
Fig. 4 Sample distribution box plot of different PTSD diagnostic methods. This figure visualized the distribution of database sample size the authors adopted for ML training in log scale for different PTSD diagnostic tools. Outliers were indicated by the black solid diamond symbol. In each individual box, the upper horizontal line represented maximum sample size (excluding the outliers) while the bottom horizontal line represented minimum sample size (excluding the outliers). The “whiskers” are lines that extend from the box to the minimum and maximum values in the dataset. For the box, it represented the region where the majority sample size distribution (fist quartile to third quartile) with the central line representing median sample size. Different color represented different PTSD diagnostic method.CC BY · PubMed Central
Fig. 5 ML model counts in different PTSD diagnostic methods. This figure was the heatmap representation of ML model types vs. PTSD diagnostic methods. Each cell represented a ML model and diagnostic method pair with number indicating the occurrence in the included studies. In terms of color scales, darker blue indicated higher occurrence while brighter blue indicated lower occurrence.
Fig. 5 ML model counts in different PTSD diagnostic methods. This figure was the heatmap representation of ML model types vs. PTSD diagnostic methods. Each cell represented a ML model and diagnostic method pair with number indicating the occurrence in the included studies. In terms of color scales, darker blue indicated higher occurrence while brighter blue indicated lower occurrence.CC BY · PubMed Central

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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?

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

The citation lists are queued

They are fetched later and appear here then.

References 69 · Cited by 30

Research works printed but not linked: 11

  1. Bishop, C. M. & Nasrabadi, N. M. Pattern Recognition and Machine Learning, vol. 4 (Springer, 2006).
  2. Kleinbaum, D. G., Dietz, K., Gail, M., Klein, M. & Klein, M. Logistic Regression (Springer, 2002).
  3. O’Shea, K. & Nash, R. An introduction to convolutional neural networks. arXiv 1511, 08458 (2015).
  4. Medsker, L. R. & Jain, L. Recurrent neural networks. Design Appl. 5, 64–67 (2001).
  5. Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems 30 (NIPS, 2017).
  6. Botchkarev, A. Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology. arXiv 1809, 03006 (2018).
  7. Longadge, R. & Dongre, S. Class imbalance problem in data mining review. arXiv 1305, 1707 (2013).
  8. Meingast, M., Roosta, T. & Sastry, S. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. 5453–5458 (IEEE, 2006).
  9. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv 1810, 04805 (2018).
  10. Mohammed, R., Rawashdeh, J. & Abdullah, M. in 2020 11th international conference on information and communication systems (ICICS). 243–248 (IEEE, 2020). · DOI · Paper page
  11. Ojala, M. & Garriga, G. C. Permutation tests for studying classifier performance. J. Mach. Learn. Res. 11, 1833–1863 (2010).

Metadata

Authors
Wu, Y., Mao, K., Dennett, L., Zhang, Y., & Chen, J.
Affiliations
University of Alberta (CA)
Corresponding author
  • Zhang, Yanbo
  • Chen, Jie
Venue
npj Mental Health Research
Published
2023-09-27
Volume
2
Issue
1
Pages
16-16
ISSN
2731-4251 (ISSN-L)
OpenAlex
W4387100013
Cited by
30
References
69
Citations by year
2026: 9 · 2025: 16 · 2024: 5
FWCI
1.51
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Mental Health Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
China Scholarship Council (202308180002, 202000810031)
Topics
  • Social Sciences › Psychology › Clinical Psychology › Posttraumatic Stress Disorder Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Clinical Neurology › Traumatic Brain Injury Research
Keywords
post-traumatic stress disorder, automated diagnosis, machine learning, artificial intelligence in mental health, diagnostic accuracy, feature selection, model validation, sample size determination, clinical implementation of AI, ethical considerations, patient privacy

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: Systematic review of machine learning in PTSD studies for automated diagnosis evaluation. https://app.cochat.ai/papers/10.1038/s44184-023-00035-w
The paper
Wu, Y., Mao, K., Dennett, L., Zhang, Y., & Chen, J. (2023). Systematic review of machine learning in PTSD studies for automated diagnosis evaluation. npj Mental Health Research. https://doi.org/10.1038/s44184-023-00035-w

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.