Agaz H Wani1, Allison E Aiello2, Grace S Kim3, Fei Xue4, Chantel L Martin2, Andrew Ratanatharathorn5, Annie Qu6, Karestan Koenen7, Sandro Galea8, Derek E Wildman1, Monica Uddin9. 1. Genomics Program, College of Public Health, University of South Florida, Tampa, FL, United States. 2. Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina at Chapel Hill and Carolina Population Center, University of North Carolina at Chapel Hill, United States. 3. Medical Scholars Program, University of Illinois College of Medicine, United States. 4. Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, United States. 5. Department of Epidemiology, Columbia University, United States. 6. Department of Statistics, University of California Irvine, United States. 7. Department of Epidemiology, Harvard T.H. Chan School of Public Health, United States; Psychiatric and Neurodevelopmental Genetics Unit & Department of Psychiatry, Massachusetts General Hospital, United States. 8. Boston University School of Public Health, United States. 9. Genomics Program, College of Public Health, University of South Florida, Tampa, FL, United States. Electronic address: monica43@usf.edu.
Abstract
BACKGROUND: A range of factors have been identified that contribute to greater incidence, severity, and prolonged course of post-traumatic stress disorder (PTSD), including: comorbid and/or prior psychopathology; social adversity such as low socioeconomic position, perceived discrimination, and isolation; and biological factors such as genomic variation at glucocorticoid receptor regulatory network (GRRN) genes. This complex etiology and clinical course make identification of people at higher risk of PTSD challenging. Here we leverage machine learning (ML) approaches to identify a core set of factors that may together predispose persons to PTSD. METHODS: We used multiple ML approaches to assess the relationship among DNA methylation (DNAm) at GRRN genes, prior psychopathology, social adversity, and prospective risk for PTS severity (PTSS). RESULTS: ML models predicted prospective risk of PTSS with high accuracy. The Gradient Boost approach was the top-performing model with mean absolute error of 0.135, mean square error of 0.047, root mean square error of 0.217, and R2 of 95.29%. Prior PTSS ranked highest in predicting the prospective risk of PTSS, accounting for >88% of the prediction. The top ranked GRRN CpG site was cg05616442, in AKT1, and the top ranked social adversity feature was loneliness. CONCLUSION: Multiple factors including prior PTSS, social adversity, and DNAm play a role in predicting prospective risk of PTSS. ML models identified factors accounting for increased PTSS risk with high accuracy, which may help to target risk factors that reduce the likelihood or course of PTSD, potentially pointing to approaches that can lead to early intervention. LIMITATION: One of the limitations of this study is small sample size.
BACKGROUND: A range of factors have been identified that contribute to greater incidence, severity, and prolonged course of post-traumatic stress disorder (PTSD), including: comorbid and/or prior psychopathology; social adversity such as low socioeconomic position, perceived discrimination, and isolation; and biological factors such as genomic variation at glucocorticoid receptor regulatory network (GRRN) genes. This complex etiology and clinical course make identification of people at higher risk of PTSD challenging. Here we leverage machine learning (ML) approaches to identify a core set of factors that may together predispose persons to PTSD. METHODS: We used multiple ML approaches to assess the relationship among DNA methylation (DNAm) at GRRN genes, prior psychopathology, social adversity, and prospective risk for PTS severity (PTSS). RESULTS: ML models predicted prospective risk of PTSS with high accuracy. The Gradient Boost approach was the top-performing model with mean absolute error of 0.135, mean square error of 0.047, root mean square error of 0.217, and R2 of 95.29%. Prior PTSS ranked highest in predicting the prospective risk of PTSS, accounting for >88% of the prediction. The top ranked GRRN CpG site was cg05616442, in AKT1, and the top ranked social adversity feature was loneliness. CONCLUSION: Multiple factors including prior PTSS, social adversity, and DNAm play a role in predicting prospective risk of PTSS. ML models identified factors accounting for increased PTSS risk with high accuracy, which may help to target risk factors that reduce the likelihood or course of PTSD, potentially pointing to approaches that can lead to early intervention. LIMITATION: One of the limitations of this study is small sample size.
Authors: O Troyanskaya; M Cantor; G Sherlock; P Brown; T Hastie; R Tibshirani; D Botstein; R B Altman Journal: Bioinformatics Date: 2001-06 Impact factor: 6.937
Authors: Luis Francisco Ramos-Lima; Paulo Ricardo Assis de Souza; Stefania Pigatto Teche; Lucia Helena Machado Freitas Journal: Psychiatry Res Date: 2019-08-18 Impact factor: 3.222
Authors: Panagiota Pervanidou; Gerasimos Kolaitis; Stella Charitaki; Alexandra Margeli; Spyros Ferentinos; Chrysa Bakoula; Christina Lazaropoulou; Ioannis Papassotiriou; John Tsiantis; George P Chrousos Journal: Psychoneuroendocrinology Date: 2007-09-07 Impact factor: 4.905
Authors: James R Occean; Agaz H Wani; Janelle Donglasan; Allison E Aiello; Sandro Galea; Karestan C Koenen; Annie Qu; Derek E Wildman; Monica Uddin Journal: Psychiatry Res Date: 2022-03-19 Impact factor: 11.225
Authors: Zhenhua Zhang; Freerk van Dijk; Niek de Klein; Mariëlle E van Gijn; Lude H Franke; Richard J Sinke; Morris A Swertz; K Joeri van der Velde Journal: Sci Rep Date: 2021-05-19 Impact factor: 4.379