Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 27;17(1):235.
doi: 10.1186/s12920-024-02002-6.

Blood-based DNA methylation and exposure risk scores predict PTSD with high accuracy in military and civilian cohorts

Affiliations

Blood-based DNA methylation and exposure risk scores predict PTSD with high accuracy in military and civilian cohorts

Agaz H Wani et al. BMC Med Genomics. .

Abstract

Background: Incorporating genomic data into risk prediction has become an increasingly popular approach for rapid identification of individuals most at risk for complex disorders such as PTSD. Our goal was to develop and validate Methylation Risk Scores (MRS) using machine learning to distinguish individuals who have PTSD from those who do not.

Methods: Elastic Net was used to develop three risk score models using a discovery dataset (n = 1226; 314 cases, 912 controls) comprised of 5 diverse cohorts with available blood-derived DNA methylation (DNAm) measured on the Illumina Epic BeadChip. The first risk score, exposure and methylation risk score (eMRS) used cumulative and childhood trauma exposure and DNAm variables; the second, methylation-only risk score (MoRS) was based solely on DNAm data; the third, methylation-only risk scores with adjusted exposure variables (MoRSAE) utilized DNAm data adjusted for the two exposure variables. The potential of these risk scores to predict future PTSD based on pre-deployment data was also assessed. External validation of risk scores was conducted in four independent cohorts.

Results: The eMRS model showed the highest accuracy (92%), precision (91%), recall (87%), and f1-score (89%) in classifying PTSD using 3730 features. While still highly accurate, the MoRS (accuracy = 89%) using 3728 features and MoRSAE (accuracy = 84%) using 4150 features showed a decline in classification power. eMRS significantly predicted PTSD in one of the four independent cohorts, the BEAR cohort (beta = 0.6839, p=0.006), but not in the remaining three cohorts. Pre-deployment risk scores from all models (eMRS, beta = 1.92; MoRS, beta = 1.99 and MoRSAE, beta = 1.77) displayed a significant (p < 0.001) predictive power for post-deployment PTSD.

Conclusion: The inclusion of exposure variables adds to the predictive power of MRS. Classification-based MRS may be useful in predicting risk of future PTSD in populations with anticipated trauma exposure. As more data become available, including additional molecular, environmental, and psychosocial factors in these scores may enhance their accuracy in predicting PTSD and, relatedly, improve their performance in independent cohorts.

Keywords: DNA methylation; Machine learning; PTSD; Risk scores.

PubMed Disclaimer

Conflict of interest statement

Murray B. Stein has in the past 3 years received consulting income from Acadia Pharmaceuticals, Aptinyx, atai Life Sciences, BigHealth, Biogen, Bionomics, BioXcel Therapeutics, Boehringer Ingelheim, Clexio, Delix Therapeutics, Eisai, EmpowerPharm, Engrail Therapeutics, Janssen, Jazz Pharmaceuticals, NeuroTrauma Sciences, PureTech Health, Sage Therapeutics, Sumitomo Pharma, and Roche/Genentech. Dr. Stein has stock options in Oxeia Biopharmaceuticals and EpiVario. He has been paid for his editorial work on Depression and Anxiety (Editor-in-Chief), Biological Psychiatry (Deputy Editor), and UpToDate (Co-Editor-in-Chief for Psychiatry). He has also received research support from NIH, Department of Veterans Affairs, and the Department of Defense. He is on the scientific advisory board for the Brain and Behavior Research Foundation and the Anxiety and Depression Association of America. Dr. Chia-Yen Chen is an employee of Biogen. Dr. Nikolaos P. Daskalakis has served on scientific advisory boards for BioVie Pharma, Circular Genomics and Sentio Solutions for unrelated work. Dr. Nicole R. Nugent is a member of the scientific advisory board for Ilumivu. Dr. Sheila Rauch support from Wounded Warrior Project (WWP), Department of Veterans Affairs (VA), National Institute of Health (NIH), McCormick Foundation, Tonix Pharmaceuticals, Woodruff Foundation, and Department of Defense (DOD). Dr. Rauch also receives royalties from Oxford University Press and American Psychological Association Press. Dr Ressler reported receiving personal consulting fees from Sage Therapeutics, Senseye, Boerhinger Ingelheim, Jazz Pharmaceuticals, and Acer, Inc. and a sponsored research grant from Alto Neuroscience outside the submitted work.

Figures

Fig. 1
Fig. 1
The confusion matrix for Model 1 displays an accuracy of 92% on test data (N = 307), while the ROC curve indicates an AUC of 96% during the tenfold cross-validation using all data (N = 1226)
Fig. 2
Fig. 2
Distribution and variation of risk scores between cases and controls in test data (N = 307) in figure legend, 0 is No PTSD and 1 is PTSD. A) The distribution of risk scores for Models 1, 2, and 3 is shown for both cases and controls. B) The difference in risk scores, and associated p value, between cases and controls is displayed. Model 1 calculates exposure and methylation risk scores (eMRS), while Model 2 calculates risk scores based only on methylation variables (MoRS). Model 3 calculates risk scores based on methylation variables adjusted for exposure variables (MoRSAE). The risk scores are higher in PTSD cases compared to controls. The Wilcoxon test confirms a significant difference in risk scores between cases and controls with p < 0.001 for all models (1, 2, and 3)
Fig. 3
Fig. 3
The confusion matrix for Model 2 displays an accuracy of 89% on test data (N = 307), while the ROC curve indicates an AUC of 95% during the tenfold cross-validation using all data (N = 1226)
Fig. 4
Fig. 4
The confusion matrix for Model 3 displays an accuracy of 84% on test data (N = 307), while the ROC curve exhibits an AUC of 89% during the tenfold cross-validation process using all data (N = 1226)
Fig. 5
Fig. 5
Distribution and difference in risk scores (eMRS) between PTSD cases and controls pre- and post-deployment (N = 262) — in figure legend, 0 is No PTSD and 1 is PTSD. A) The distribution of risk scores revealed that individuals who developed PTSD post-deployment had higher scores compared to those who did not, both before and after deployment. B) The difference in risk scores showed there was a significant (p < 0.001) difference in risk scores in those with PTSD post-deployment using Wilcoxon test
Fig. 6
Fig. 6
Distribution and difference in risk scores (MoRS) between cases and controls pre- and post-deployment (N = 262) — in figure legend, 0 is No PTSD and 1 is PTSD. A) Distribution of risk scores between cases and controls. Risk scores are higher in those who developed PTSD post-deployment than who didn't in both pre and post deployment. B) Difference in risk scores between cases and controls. Wilcoxon test showed a significant difference (p < 0.001) in risk scores between cases and controls
Fig. 7
Fig. 7
Distribution and difference in risk scores (MoRSAE) between cases and controls pre- and post-deployment (N = 262) — in figure legend, 0 is No PTSD and 1 is PTSD. A) The distribution of MoRSAE is higher in those who developed PTSD post-deployment B) The difference in risk scores showed there was a significant (p < 0.001) difference in risk scores in those with PTSD post-deployment using Wilcoxon test

Update of

References

    1. Kessler RC, Aguilar-Gaxiola S, Alonso J, Benjet C, Bromet EJ, Cardoso G, et al. Trauma and PTSD in the WHO world mental health surveys. Eur J Psychotraumatol. 2017;8(sup5):1353383. - PMC - PubMed
    1. Yehuda R, Hoge CW, McFarlane AC, Vermetten E, Lanius RA, Nievergelt CM, et al. Post-traumatic stress disorder. Nat Rev Dis Primers. 2015;1(1):15057. - PubMed
    1. Kessler RC, Sonnega A, Bromet E, Hughes M, Nelson CB. Posttraumatic stress disorder in the National Comorbidity Survey. Arch Gen Psychiatry. 1995;52(12):1048–60. - PubMed
    1. Kulka RA, Schlenger WE, Fairbank JA, Hough RL, Jordan BK, Marmar CR, et al. Trauma and the Vietnam war generation: Report of findings from the National Vietnam Veterans Readjustment Study. Philadelphia: Brunner/Mazel; 1990. xxix, 322-xxix, p.
    1. Brady KT, Killeen TK, Brewerton T, Lucerini S. Comorbidity of psychiatric disorders and posttraumatic stress disorder. J Clin Psychiatry. 2000;61(Suppl 7):22–32. - PubMed