Improved metabolomic data-based prediction of depressive symptoms using nonlinear machine learning with feature selection
Open Access
- 19 May 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Translational Psychiatry
- Vol. 10 (1), 1-12
- https://doi.org/10.1038/s41398-020-0831-9
Abstract
To solve major limitations in algorithms for the metabolite-based prediction of psychiatric phenotypes, a novel prediction model for depressive symptoms based on nonlinear feature selection machine learning, the Hilbert–Schmidt independence criterion least absolute shrinkage and selection operator (HSIC Lasso) algorithm, was developed and applied to a metabolomic dataset with the largest sample size to date. In total, 897 population-based subjects were recruited from the communities affected by the Great East Japan Earthquake; 306 metabolite features (37 metabolites identified by nuclear magnetic resonance measurements and 269 characterized metabolites based on the intensities from mass spectrometry) were utilized to build prediction models for depressive symptoms as evaluated by the Center for Epidemiologic Studies-Depression Scale (CES-D). The nested fivefold cross-validation was used for developing and evaluating the prediction models. The HSIC Lasso-based prediction model showed better predictive power than the other prediction models, including Lasso, support vector machine, partial least squares, random forest, and neural network. l-leucine, 3-hydroxyisobutyrate, and gamma-linolenyl carnitine frequently contributed to the prediction. We have demonstrated that the HSIC Lasso-based prediction model integrating nonlinear feature selection showed improved predictive power for depressive symptoms based on metabolome data as well as on risk metabolites based on nonlinear statistics in the Japanese population. Further studies should use HSIC Lasso-based prediction models with different ethnicities to investigate the generality of each risk metabolite for predicting depressive symptoms.This publication has 46 references indexed in Scilit:
- Serum concentrations of phthalate metabolites are related to abdominal fat distribution two years later in elderly womenEnvironmental Health, 2012
- Multi-resolution independent component analysis for high-performance tumor classification and biomarker discoveryBMC Bioinformatics, 2011
- Sparse Partial Least Squares Classification for High Dimensional DataStatistical Applications in Genetics and Molecular Biology, 2010
- Vitamin D Status and the Risk of Cardiovascular Disease DeathAmerican Journal of Epidemiology, 2009
- Biological Variations in Depression and Anxiety Between East and WestCNS Neuroscience & Therapeutics, 2009
- Depression and body mass index, a u-shaped associationBMC Public Health, 2009
- Sure Independence Screening for Ultrahigh Dimensional Feature SpaceJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- Metabonomics, dietary influences and cultural differences: a 1H NMR-based study of urine samples obtained from healthy British and Swedish subjectsJournal of Pharmaceutical and Biomedical Analysis, 2004
- Small sample size effects in statistical pattern recognition: recommendations for practitionersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- The CES-D ScaleApplied Psychological Measurement, 1977