GWAS-based machine learning approach to predict duloxetine response in major depressive disorder. (April 2018)

• Record Type: Journal Article
• Authors: Maciukiewicz, Malgorzata; Marshe, Victoria S.; Hauschild, Anne-Christin; Foster, Jane A.; Rotzinger, Susan; Kennedy, James L.; Kennedy, Sidney H.; Müller, Daniel J.; Geraci, Joseph
• Is Part Of: Journal of psychiatric research. Volume 99(2018)
• Page Start: 62
• Page End: 68
• Publication Date: 2018-04
• Subjects: Psychiatry -- Periodicals; Mental Disorders -- Periodicals; Maladies mentales -- Périodiques; Psychiatry; Electronic journals; Periodicals; 616.89005
• DOI: 10.1016/j.jpsychires.2017.12.009
• Languages: English
• ISSNs: 0022-3956

Abstract

Abstract: Major depressive disorder (MDD) is one of the most prevalent psychiatric disorders and is commonly treated with antidepressant drugs. However, large variability is observed in terms of response to antidepressants. Machine learning (ML) models may be useful to predict treatment outcomes. A sample of 186 MDD patients received treatment with duloxetine for up to 8 weeks were categorized as "responders" based on a MADRS change >50% from baseline; or "remitters" based on a MADRS score ≤10 at end point. The initial dataset (N = 186) was randomly divided into training and test sets in a nested 5-fold cross-validation, where 80% was used as a training set and 20% made up five independent test sets. We performed genome-wide logistic regression to identify potentially significant variants related to duloxetine response/remission and extracted the most promising predictors using LASSO regression. Subsequently, classification-regression trees (CRT) and support vector machines (SVM) were applied to construct models, using ten-fold cross-validation. With regards to response, none of the pairs performed significantly better than chance (accuracy p > .1). For remission, SVM achieved moderate performance with an accuracy = 0.52, a sensitivity = 0.58, and a specificity = 0.46, and 0.51 for all coefficients for CRT. The best performing SVM fold was characterized by an accuracy = 0.66 (p = .071), sensitivity = 0.70 and a sensitivity = 0.61. In this study, the potential of using GWAS data to predict duloxetine outcomes was examined using ML models. The models were characterized by a promising sensitivity, but specificity remained moderate at best. The inclusion of additional non-genetic variables to create integrated models may improve prediction. Highlights: Antidepressant medications are usually selected on a "trial-and-error" basis until an appropriate medication is found. Biomarker research has yet to establish models that predict outcomes with an accuracy acceptable for clinical use. Supervised machine learning (ML) methods enable multivariate analyses in order to build predictive models to effectively classify observations (e.g., patients) into known, predefined classes (e.g., response status). A nested 5-fold cross-validation was used to evaluate the predictive potential of genetic and clinical characteristics. A standard genome-wide association approach was followed by LASSO regression to select the best features for ML models. The best performing SVM fold was characterized by an accuracy of 0.66 (p = .071), sensitivity of 0.70 and a sensitivity of 0.61. The combination of variant prioritization and LASSO regression produced the most robust models. However, further validation and replication is required in external samples.