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

Author:

Wani Agaz1,Katrinli Seyma2,Zhao Xiang3,Daskalakis Nikolaos4,Zannas Anthony5,Aiello Allison6,Baker Dewleen7,Boks Marco8,Brick Leslie9,Chen Chia-Yen10,Dalvie Shareefa11,Fortier Catherine12,Geuze Elbert13,Hayes Jasmeet14,Kessler Ronald15,King Anthony16,Koen Nastassja17,Liberzon Israel18,Lori Adriana19,Luykx Jurjen20,Maihofer Adam21,Milberg William22,Miller Mark23,Mufford Mary24,Nugent Nicole25,Rauch Sheila26,Ressler Kerry12,Risbrough Victoria7,Rutten Bart27,Stein Dan17,Stein Murrary7,Ursano Robert28,Verfaellie Mieke23,Ware Erin29,Wildman Derek1,Wolf Erika30,Nievergelt Caroline7,Logue Mark3,Smith Alicia2,Uddin Monica1,Vermetten Eric31,Vinkers Christiaan32

Affiliation:

1. University of South Florida College of Public Health, Genomics Program

2. Emory University Department of Gynecology and Obstetrics

3. Boston University School of Public Health

4. Broad Institute of MIT and Harvard, Stanley Center for Psychiatric Research

5. University of North Carolina at Chapel Hill, Carolina Stress Initiative

6. Robert N Butler Columbia Aging Center, Columbia University

7. University of California San Diego, Department of Psychiatry

8. Brain Center University Medical Center Utrecht, Department of Psychiatry

9. Alpert University, Brown University

10. Biogen Inc., Translational Sciences

11. University of Cape Town, Department of Pathology

12. Harvard Medical School, Department of Psychiatry

13. Netherlands Ministry of Defence, Brain Research and Innovation Centre

14. The Ohio State University, Department of Psychology

15. Harvard Medical School, Department of Health Care Policy

16. The Ohio State University, College of Medicine, Institute for Behavioral Medicine Research

17. University of Cape Town, Department of Psychiatry & Mental Health

18. Texas A&M University College of Medicine, Department of Psychiatry and Behavioral Sciences

19. Emory University, Department of Psychiatry and Behavioral Sciences

20. UMC Utrecht Brain Center Rudolf Magnus, Department of Psychiatry

21. University of California, San Diego

22. VA Boston Healthcare System, TRACTS/GRECC

23. Boston University School of Medicine, Psychiatry

24. University of Cape Town, Neuroscience Institute

25. Alpert Brown Medical School, Department of Emergency Medicine

26. Emory University, Department of Psychiatry & Behavioral Sciences

27. Maastricht Universitair Medisch Centrum, School for Mental Health and Neuroscience, Department of Psychiatry and Neuropsychology

28. Uniformed Services University, Department of Psychiatry

29. University of Michigan, Population Studies Center

30. VA Boston Healthcare System, National Center for PTSD

31. Leiden University Medical Center, Department of Psychiatry

32. Amsterdam Neuroscience, Mood, Anxiety, Psychosis, Sleep & Stress Program

Abstract

Abstract Background Incorporating genomic data into risk prediction has become an increasingly useful 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-0.003), 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 Results, especially those from the eMRS, reinforce earlier findings that methylation and trauma are interconnected and can be leveraged to increase the correct classification of those with vs. without PTSD. Moreover, our models can potentially be a valuable tool in predicting the future risk of developing PTSD. As more data become available, including additional molecular, environmental, and psychosocial factors in these scores may enhance their accuracy in predicting the condition and, relatedly, improve their performance in independent cohorts.

Publisher

Research Square Platform LLC

Reference65 articles.

1. Post-traumatic stress disorder;Yehuda R;Nat Reviews Disease Primers,2015

2. Posttraumatic stress disorder in the National Comorbidity Survey;Kessler RC;Arch Gen Psychiatry,1995

3. 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, PA, US: Brunner/Mazel; 1990. xxix, 322-xxix, p.

4. Comorbidity of psychiatric disorders and posttraumatic stress disorder;Brady KT;J Clin Psychiatry,2000

5. The Descriptive Epidemiology of Commonly Occurring Mental Disorders in the United States;Kessler RC,2008

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3