The effects of co-morbidity in defining major depression subtypes associated with long-term course and severity.
Journal: Psychological medicine
Volume: 44
Issue: 15
Year of Publication: 2015
Affiliated Institutions:
Department of Psychiatry,University of Groningen, University Medical Center Groningen,The Netherlands.
Department of Biostatistics,Harvard School of Public Health,Boston, MA,USA.
Department of Psychiatry,MGH Clinical Trials Network and Institute,Depression Clinical and Research Program, Massachusetts General Hospital, Boston, MA,USA.
Department of Health Care Policy,Harvard Medical School,Boston, MA,USA.
Depression Clinical and Research Program and the Bipolar Clinic and Research Program,Massachusetts General Hospital and Harvard Medical School,Boston, MA,USA.
Johnson & Johnson Pharmaceutical Research and Development,Titusville, NJ,USA.
IMIM-Hospital del Mar Research Institute, Parc de Salut Mar,Pompeu Fabra University (UPF), andCIBER en Epidemiología y Salud Pública (CIBERESP), Barcelona,Spain.
Department of Psychiatry and Behavioral Science, Stony Brook School of Medicine,State University of New York at Stony Brook,Stony Brook, NY,USA.
Psychology Research Institute,University of Ulster,Londonderry,UK.
National School of Public Health,Management and Professional Development, Bucharest,Romania.
Department of Public Health,Yamagata University School of Medicine,Japan.
University College Hospital,Ibadan,Nigeria.
Shenzhen Institute of Mental Health and Shenzhen Kangning Hospital,Guangdong Province,People's Republic of China.
Institute of Mental Health, Peking University,Beijing,People's Republic of China.
Department of Psychiatry and Clinical Psychology,St George Hospital University Medical Center,Department of Psychiatry and Clinical Psychology, Faculty of Medicine, Balamand University Medical School, andInstitute for Development Research Advocacy and Applied Care (IDRAAC), Beirut,Lebanon.
Research and Planning,Mental Health Services,Ministry of Health, Jerusalem,Israel.
National Institute of Psychiatry,Calzada Mexico Xochimilco, Mexico City,Mexico.
Universidad Colegio Mayor de Cundinamarca,Bogota,Colombia.
Department of Psychological Medicine,University of Otago,Dunedin,New Zealand.
Mental Health Center-Duhok,Kurdistan Region,Iraq.
Department of Social Medicine,Federal University of Espirito Santo,Vitoria,Brazil.
Department of Mental Health,Universidade Nova de Lisboa,Lisbon,Portugal.
National Center of Public Health and Analyses,Department of Mental Health, Sofia,Bulgaria.
Abstract summary
Although variation in the long-term course of major depressive disorder (MDD) is not strongly predicted by existing symptom subtype distinctions, recent research suggests that prediction can be improved by using machine learning methods. However, it is not known whether these distinctions can be refined by added information about co-morbid conditions. The current report presents results on this question.Data came from 8261 respondents with lifetime DSM-IV MDD in the World Health Organization (WHO) World Mental Health (WMH) Surveys. Outcomes included four retrospectively reported measures of persistence/severity of course (years in episode; years in chronic episodes; hospitalization for MDD; disability due to MDD). Machine learning methods (regression tree analysis; lasso, ridge and elastic net penalized regression) followed by k-means cluster analysis were used to augment previously detected subtypes with information about prior co-morbidity to predict these outcomes.Predicted values were strongly correlated across outcomes. Cluster analysis of predicted values found three clusters with consistently high, intermediate or low values. The high-risk cluster (32.4% of cases) accounted for 56.6-72.9% of high persistence, high chronicity, hospitalization and disability. This high-risk cluster had both higher sensitivity and likelihood ratio positive (LR+; relative proportions of cases in the high-risk cluster versus other clusters having the adverse outcomes) than in a parallel analysis that excluded measures of co-morbidity as predictors.Although the results using the retrospective data reported here suggest that useful MDD subtyping distinctions can be made with machine learning and clustering across multiple indicators of illness persistence/severity, replication with prospective data is needed to confirm this preliminary conclusion.
Authors & Co-authors:
Wardenaar K J KJ
van Loo H M HM
Cai T T
Fava M M
Gruber M J MJ
Li J J
de Jonge P P
Nierenberg A A AA
Petukhova M V MV
Rose S S
Sampson N A NA
Schoevers R A RA
Wilcox M A MA
Alonso J J
Bromet E J EJ
Bunting B B
Florescu S E SE
Fukao A A
Gureje O O
Hu C C
Huang Y Q YQ
Karam A N AN
Levinson D D
Medina Mora M E ME
Posada-Villa J J
Scott K M KM
Taib N I NI
Viana M C MC
Xavier M M
Zarkov Z Z
Kessler R C RC
Study Outcome
Source Link: Visit source