Yena Lee1, Renee-Marie Ragguett2, Rodrigo B Mansur3, Justin J Boutilier4, Joshua D Rosenblat5, Alisson Trevizol6, Elisa Brietzke7, Kangguang Lin8, Zihang Pan1, Mehala Subramaniapillai2, Timothy C Y Chan4, Dominika Fus2, Caroline Park1, Natalie Musial2, Hannah Zuckerman2, Vincent Chin-Hung Chen9, Roger Ho10, Carola Rong2, Roger S McIntyre11. 1. Institute of Medical Science, University of Toronto, Toronto, Canada; Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Brain and Cognition Discovery Foundation, Toronto, Canada. 2. Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Brain and Cognition Discovery Foundation, Toronto, Canada. 3. Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, Canada; Brain and Cognition Discovery Foundation, Toronto, Canada. 4. Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada. 5. Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, Canada. 6. Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada. 7. Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Department of Psychiatry, Federal University of Sao Paulo, Sao Paulo, Brazil. 8. Laboratory of Emotion and Cognition, Department of Affective Disorders, Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, China; Department of Neuropsychology, University of Hong Kong, Hong Kong, China. 9. School of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Psychiatry, Chang Gung Memorial Hospital, Chiayi, Taiwan. 10. Department of Psychological Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore. 11. Institute of Medical Science, University of Toronto, Toronto, Canada; Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, Canada; Brain and Cognition Discovery Foundation, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, Canada; Department of Pharmacology, University of Toronto, Toronto, Canada. Electronic address: Roger.McIntyre@uhn.ca.
Abstract
BACKGROUND: No previous study has comprehensively reviewed the application of machine learning algorithms in mood disorders populations. Herein, we qualitatively and quantitatively evaluate previous studies of machine learning-devised models that predict therapeutic outcomes in mood disorders populations. METHODS: We searched Ovid MEDLINE/PubMed from inception to February 8, 2018 for relevant studies that included adults with bipolar or unipolar depression; assessed therapeutic outcomes with a pharmacological, neuromodulatory, or manual-based psychotherapeutic intervention for depression; applied a machine learning algorithm; and reported predictors of therapeutic response. A random-effects meta-analysis of proportions and meta-regression analyses were conducted. RESULTS: We identified 639 records: 75 full-text publications were assessed for eligibility; 26 studies (n=17,499) and 20 studies (n=6325) were included in qualitative and quantitative review, respectively. Classification algorithms were able to predict therapeutic outcomes with an overall accuracy of 0.82 (95% confidence interval [CI] of [0.77, 0.87]). Pooled estimates of classification accuracy were significantly greater (p < 0.01) in models informed by multiple data types (e.g., composite of phenomenological patient features and neuroimaging or peripheral gene expression data; pooled proportion [95% CI] = 0.93[0.86, 0.97]) when compared to models with lower-dimension data types (pooledproportion=0.68[0.62,0.74]to0.85[0.81,0.88]). LIMITATIONS: Most studies were retrospective; differences in machine learning algorithms and their implementation (e.g., cross-validation, hyperparameter tuning); cannot infer importance of individual variables fed into learning algorithm. CONCLUSIONS: Machine learning algorithms provide a powerful conceptual and analytic framework capable of integrating multiple data types and sources. An integrative approach may more effectively model neurobiological components as functional modules of pathophysiology embedded within the complex, social dynamics that influence the phenomenology of mental disorders.
BACKGROUND: No previous study has comprehensively reviewed the application of machine learning algorithms in mood disorders populations. Herein, we qualitatively and quantitatively evaluate previous studies of machine learning-devised models that predict therapeutic outcomes in mood disorders populations. METHODS: We searched Ovid MEDLINE/PubMed from inception to February 8, 2018 for relevant studies that included adults with bipolar or unipolar depression; assessed therapeutic outcomes with a pharmacological, neuromodulatory, or manual-based psychotherapeutic intervention for depression; applied a machine learning algorithm; and reported predictors of therapeutic response. A random-effects meta-analysis of proportions and meta-regression analyses were conducted. RESULTS: We identified 639 records: 75 full-text publications were assessed for eligibility; 26 studies (n=17,499) and 20 studies (n=6325) were included in qualitative and quantitative review, respectively. Classification algorithms were able to predict therapeutic outcomes with an overall accuracy of 0.82 (95% confidence interval [CI] of [0.77, 0.87]). Pooled estimates of classification accuracy were significantly greater (p < 0.01) in models informed by multiple data types (e.g., composite of phenomenological patient features and neuroimaging or peripheral gene expression data; pooled proportion [95% CI] = 0.93[0.86, 0.97]) when compared to models with lower-dimension data types (pooledproportion=0.68[0.62,0.74]to0.85[0.81,0.88]). LIMITATIONS: Most studies were retrospective; differences in machine learning algorithms and their implementation (e.g., cross-validation, hyperparameter tuning); cannot infer importance of individual variables fed into learning algorithm. CONCLUSIONS: Machine learning algorithms provide a powerful conceptual and analytic framework capable of integrating multiple data types and sources. An integrative approach may more effectively model neurobiological components as functional modules of pathophysiology embedded within the complex, social dynamics that influence the phenomenology of mental disorders.
Authors: Amin Zandvakili; Noah S Philip; Stephanie R Jones; Audrey R Tyrka; Benjamin D Greenberg; Linda L Carpenter Journal: J Affect Disord Date: 2019-03-30 Impact factor: 4.839