Predicting individual clinical trajectories of depression with generative embedding

Highlights • Patients with major depressive disorder (MDD) show variable clinical trajectories.• Generative embedding (GE) is used to predict clinical trajectories in MDD patients.• GE classifies patients with chronic depression vs. fast remission with 79% accuracy.• GE provides mechanistic interpretability and outperforms conventional measures.• Proof-of-concept that illustrates the potential of GE for clinical prediction.

[1]  S. Clarke,et al.  Occipital cortex in man: Organization of callosal connections, related myelo‐ and cytoarchitecture, and putative boundaries of functional visual areas , 1990, The Journal of comparative neurology.

[2]  Karl J. Friston,et al.  Nonlinear Responses in fMRI: The Balloon Model, Volterra Kernels, and Other Hemodynamics , 2000, NeuroImage.

[3]  Joachim M. Buhmann,et al.  Regression DCM for fMRI , 2017, NeuroImage.

[4]  Joachim M. Buhmann,et al.  Generative Embedding for Model-Based Classification of fMRI Data , 2011, PLoS Comput. Biol..

[5]  Stefan Haufe,et al.  On the interpretation of weight vectors of linear models in multivariate neuroimaging , 2014, NeuroImage.

[6]  P. Cowen,et al.  Short-term SSRI treatment normalises amygdala hyperactivity in depressed patients , 2012, Psychological Medicine.

[7]  M. Catani,et al.  A diffusion tensor imaging tractography atlas for virtual in vivo dissections , 2008, Cortex.

[8]  Stephanie Clarke,et al.  Architecture, Connectivity, and Transmitter Receptors of Human Auditory Cortex , 2012 .

[9]  M. Phillips,et al.  Neural correlates of dysfunctional emotion regulation in major depressive disorder. A systematic review of neuroimaging studies , 2013, Neuroscience & Biobehavioral Reviews.

[10]  P. Cowen,et al.  Why do antidepressants take so long to work? A cognitive neuropsychological model of antidepressant drug action , 2009, British Journal of Psychiatry.

[11]  P. Fox,et al.  Altered Brain Activity in Unipolar Depression Revisited: Meta-analyses of Neuroimaging Studies , 2017, JAMA psychiatry.

[12]  S. Rauch,et al.  Response and Habituation of the Human Amygdala during Visual Processing of Facial Expression , 1996, Neuron.

[13]  Tianxi Cai,et al.  Testing a machine-learning algorithm to predict the persistence and severity of major depressive disorder from baseline self-reports , 2015, Molecular Psychiatry.

[14]  Eduardo A. Aponte,et al.  Generative models for clinical applications in computational psychiatry. , 2018, Wiley interdisciplinary reviews. Cognitive science.

[15]  Blaise Hanczar,et al.  Accuracy-Rejection Curves (ARCs) for Comparing Classification Methods with a Reject Option , 2009, MLSB.

[16]  Michele T. Diaz,et al.  Effect of bupropion extended release on negative emotion processing in major depressive disorder: a pilot functional magnetic resonance imaging study. , 2007, The Journal of clinical psychiatry.

[17]  Karl J. Friston,et al.  Variational free energy and the Laplace approximation , 2007, NeuroImage.

[18]  Abraham Z. Snyder,et al.  Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion , 2012, NeuroImage.

[19]  M. Mintun,et al.  Increased amygdala response to masked emotional faces in depressed subjects resolves with antidepressant treatment: an fMRI study , 2001, Biological Psychiatry.

[20]  A. Aleman,et al.  Regional brain volume in depression and anxiety disorders. , 2010, Archives of general psychiatry.

[21]  S. Zeki Interhemispheric connections of prestriate cortex in monkey. , 1970, Brain research.

[22]  M. Weissman,et al.  Statistical harmonization corrects site effects in functional connectivity measurements from multi‐site fMRI data , 2018, Human brain mapping.

[23]  H. Mayberg Limbic-cortical dysregulation: a proposed model of depression. , 1997, The Journal of neuropsychiatry and clinical neurosciences.

[24]  P. Fox,et al.  Cingulate function in depression: a potential predictor of treatment response , 1997, Neuroreport.

[25]  R. Turner,et al.  Event-Related fMRI: Characterizing Differential Responses , 1998, NeuroImage.

[26]  A. Aleman,et al.  Neural correlates of perception of emotional facial expressions in out-patients with mild-to-moderate depression and anxiety. A multicenter fMRI study , 2011, Psychological Medicine.

[27]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[28]  Thomas R. Insel,et al.  Pharmacogenomics and Personalized Medicine in Neuropsychiatry , 2012, Neuron.

[29]  Klaas E. Stephan,et al.  Mechanisms of hemispheric lateralization: Asymmetric interhemispheric recruitment in the face perception network , 2016, NeuroImage.

[30]  Karl J. Friston,et al.  Ion channels in EEG: isolating channel dysfunction in NMDA receptor antibody encephalitis , 2018, Brain : a journal of neurology.

[31]  Catherine J. Harmer,et al.  Effect of a single dose of citalopram on amygdala response to emotional faces , 2009, British Journal of Psychiatry.

[32]  Thomas G. Dietterich Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[33]  R. Graaf,et al.  Prevalence of mental disorders and trends from 1996 to 2009. Results from the Netherlands Mental Health Survey and Incidence Study-2 , 2012, Social Psychiatry and Psychiatric Epidemiology.

[34]  D. V. van Essen,et al.  The pattern of interhemispheric connections and its relationship to extrastriate visual areas in the macaque monkey , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[35]  I. Hickie,et al.  A systematic review of resting-state functional-MRI studies in major depression. , 2012, Journal of affective disorders.

[36]  Klaas E. Stephan,et al.  Dynamic causal modelling: A critical review of the biophysical and statistical foundations , 2011, NeuroImage.

[37]  Robert A. Schoevers,et al.  Predicting the naturalistic course of depression from a wide range of clinical, psychological, and biological data: a machine learning approach , 2018, European Neuropsychopharmacology.

[38]  Marta I Garrido,et al.  An afferent white matter pathway from the pulvinar to the amygdala facilitates fear recognition , 2019, eLife.

[39]  Karl J. Friston,et al.  Comparing Families of Dynamic Causal Models , 2010, PLoS Comput. Biol..

[40]  Karl J. Friston,et al.  Computational neuroimaging strategies for single patient predictions , 2017, NeuroImage.

[41]  Chris Petty,et al.  Attenuation of Frontostriatal Connectivity During Reward Processing Predicts Response to Psychotherapy in Major Depressive Disorder , 2017, Neuropsychopharmacology.

[42]  Philippe Fortemps,et al.  Towards interpretable machine learning models for diagnosis aid: A case study on attention deficit/hyperactivity disorder , 2019, PloS one.

[43]  A. Ishai,et al.  Effective connectivity within the distributed cortical network for face perception. , 2007, Cerebral cortex.

[44]  Karl J. Friston,et al.  Bayesian model selection for group studies — Revisited , 2014, NeuroImage.

[45]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[46]  Katia M. Harlé,et al.  Bayesian neural adjustment of inhibitory control predicts emergence of problem stimulant use. , 2015, Brain : a journal of neurology.

[47]  M. Brammer,et al.  Pattern Classification of Sad Facial Processing: Toward the Development of Neurobiological Markers in Depression , 2008, Biological Psychiatry.

[48]  J. Haxby,et al.  The distributed human neural system for face perception , 2000, Trends in Cognitive Sciences.

[49]  Daniel S Pine,et al.  Ventral Striatum Functional Connectivity as a Predictor of Adolescent Depressive Disorder in a Longitudinal Community-Based Sample. , 2017, The American journal of psychiatry.

[50]  Martin Keller,et al.  The epidemiology of major depressive episodes: results from the International Consortium of Psychiatric Epidemiology (ICPE) surveys , 2003, International journal of methods in psychiatric research.

[51]  Pienie Zwitserlood,et al.  Mood-congruent amygdala responses to subliminally presented facial expressions in major depression: associations with anhedonia. , 2013, Journal of psychiatry & neuroscience : JPN.

[52]  Y. Kang,et al.  Pharmacogenomics and Personalized Medicine , 2008, Methods in Pharmacology and Toxicology.

[53]  Martha Sajatovic,et al.  Strategies for Addressing Adherence Problems in Patients with Serious and Persistent Mental Illness: Recommendations From the Expert Consensus Guidelines , 2010, Journal of psychiatric practice.

[54]  Karl J. Friston,et al.  Comparing hemodynamic models with DCM , 2007, NeuroImage.

[55]  J. Buhmann,et al.  Dissecting psychiatric spectrum disorders by generative embedding☆☆☆ , 2013, NeuroImage: Clinical.

[56]  Joachim M. Buhmann,et al.  A generative model of whole-brain effective connectivity , 2018, NeuroImage.

[57]  Robert A Schoevers,et al.  Inflammatory and Metabolic Dysregulation and the 2-Year Course of Depressive Disorders in Antidepressant Users , 2014, Neuropsychopharmacology.

[58]  Glenda M MacQueen,et al.  Magnetic resonance imaging and prediction of outcome in patients with major depressive disorder. , 2009, Journal of psychiatry & neuroscience : JPN.

[59]  B. Muthén,et al.  Growth modeling with nonignorable dropout: alternative analyses of the STAR*D antidepressant trial. , 2011, Psychological methods.

[60]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[61]  Thomas V. Wiecki,et al.  A Computational Cognitive Biomarker for Early-Stage Huntington’s Disease , 2016, PloS one.

[62]  P. Good,et al.  Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses , 1995 .

[63]  P. Cuijpers,et al.  Two-year course of depressive and anxiety disorders: results from the Netherlands Study of Depression and Anxiety (NESDA). , 2011, Journal of affective disorders.

[64]  Jens Frahm,et al.  Topography of the human corpus callosum revisited—Comprehensive fiber tractography using diffusion tensor magnetic resonance imaging , 2006, NeuroImage.

[65]  D. Kupfer,et al.  Abnormal Amygdala-Prefrontal Effective Connectivity to Happy Faces Differentiates Bipolar from Major Depression , 2009, Biological Psychiatry.

[66]  D. Pitcher,et al.  The role of the occipital face area in the cortical face perception network , 2011, Experimental Brain Research.

[67]  Gemma C. Garriga,et al.  Permutation Tests for Studying Classifier Performance , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[68]  F. Zitman,et al.  Salivary cortisol levels and the 2-year course of depressive and anxiety disorders , 2013, Psychoneuroendocrinology.

[69]  T. Insel,et al.  Why has it taken so long for biological psychiatry to develop clinical tests and what to do about it? , 2012, Molecular Psychiatry.

[70]  Yang Wang,et al.  Reciprocal effects of antidepressant treatment on activity and connectivity of the mood regulating circuit: an FMRI study. , 2007, The Journal of neuropsychiatry and clinical neurosciences.

[71]  T. Insel,et al.  Toward the future of psychiatric diagnosis: the seven pillars of RDoC , 2013, BMC Medicine.

[72]  John Suckling,et al.  Neural responses to happy facial expressions in major depression following antidepressant treatment. , 2007, The American journal of psychiatry.

[73]  Jack L. Gallant,et al.  Encoding and decoding in fMRI , 2011, NeuroImage.

[74]  Constantine G. Lyketsos,et al.  The Life Chart Interview: A standardized method to describe the course of psychopathology. , 1994 .

[75]  R. Buxton,et al.  Dynamics of blood flow and oxygenation changes during brain activation: The balloon model , 1998, Magnetic resonance in medicine.

[76]  Anat Brunstein Klomek,et al.  Stressful life events and major depressive disorders , 2008, Psychiatry Research.

[77]  William W Eaton,et al.  Heterogeneity in 10-Year Course Trajectories of Moderate to Severe Major Depressive Disorder: A Danish National Register-Based Study. , 2016, JAMA psychiatry.

[78]  Luke J. Chang,et al.  Building better biomarkers: brain models in translational neuroimaging , 2017, Nature Neuroscience.

[79]  R. de Graaf,et al.  Course trajectories of unipolar depressive disorders identified by latent class growth analysis , 2011, Psychological Medicine.

[80]  Greg J Siegle,et al.  Toward clinically useful neuroimaging in depression treatment: prognostic utility of subgenual cingulate activity for determining depression outcome in cognitive therapy across studies, scanners, and patient characteristics. , 2012, Archives of general psychiatry.

[81]  Chih-Jen Lin,et al.  Working Set Selection Using Second Order Information for Training Support Vector Machines , 2005, J. Mach. Learn. Res..

[82]  M. Stone Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[83]  Helen S Mayberg,et al.  Functional Connectivity of the Subcallosal Cingulate Cortex And Differential Outcomes to Treatment With Cognitive-Behavioral Therapy or Antidepressant Medication for Major Depressive Disorder. , 2017, The American journal of psychiatry.

[84]  A. Farmer,et al.  The Composite International Diagnostic Interview. An epidemiologic Instrument suitable for use in conjunction with different diagnostic systems and in different cultures. , 1988, Archives of general psychiatry.

[85]  Philipp Sterzer,et al.  Differences between chronic and nonchronic depression: Systematic review and implications for treatment , 2018, Depression and anxiety.

[86]  John Suckling,et al.  Attenuation of the neural response to sad faces in major depression by antidepressant treatment: a prospective, event-related functional magnetic resonance imaging study. , 2004, Archives of general psychiatry.

[87]  Chris Petty,et al.  Resting-State Connectivity Predictors of Response to Psychotherapy in Major Depressive Disorder , 2015, Neuropsychopharmacology.

[88]  M. Trivedi,et al.  Identifying predictors, moderators, and mediators of antidepressant response in major depressive disorder: neuroimaging approaches. , 2015, The American journal of psychiatry.

[89]  N. Kanwisher,et al.  The Fusiform Face Area: A Module in Human Extrastriate Cortex Specialized for Face Perception , 1997, The Journal of Neuroscience.

[90]  S. Costafreda,et al.  Emotional valence modulates brain functional abnormalities in depression: Evidence from a meta-analysis of fMRI studies , 2013, Neuroscience & Biobehavioral Reviews.

[91]  Ragini Verma,et al.  Harmonization of multi-site diffusion tensor imaging data , 2017, NeuroImage.

[92]  D. Kupfer,et al.  Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: a STAR*D report. , 2006, The American journal of psychiatry.

[93]  Y. Benjamini,et al.  THE CONTROL OF THE FALSE DISCOVERY RATE IN MULTIPLE TESTING UNDER DEPENDENCY , 2001 .

[94]  Karl J. Friston,et al.  Dynamic causal modelling , 2003, NeuroImage.

[95]  J. Krystal,et al.  Trajectories of depression severity in clinical trials of duloxetine: insights into antidepressant and placebo responses. , 2011, Archives of general psychiatry.

[96]  Stephen Pilling,et al.  Neural predictors of treatment response to brain stimulation and psychological therapy in depression: a double-blind randomized controlled trial , 2019, Neuropsychopharmacology.

[97]  Russell A. Poldrack,et al.  Large-scale automated synthesis of human functional neuroimaging data , 2011, Nature Methods.

[98]  Fariba Bahrami,et al.  Deep Temporal Organization of fMRI Phase Synchrony Modes Promotes Large-Scale Disconnection in Schizophrenia , 2020, Frontiers in Neuroscience.

[99]  Dick J. Veltman,et al.  Longitudinal brain changes in MDD during emotional encoding: effects of presence and persistence of symptomatology , 2019, Psychological Medicine.

[100]  Lei Zhang,et al.  Sub‐hubs of baseline functional brain networks are related to early improvement following two‐week pharmacological therapy for major depressive disorder , 2015, Human brain mapping.

[101]  P. Cuijpers,et al.  The Netherlands Study of Depression and Anxiety (NESDA): rationale, objectives and methods , 2008, International journal of methods in psychiatric research.

[102]  E. Mohammadi,et al.  Barriers and facilitators related to the implementation of a physiological track and trigger system: A systematic review of the qualitative evidence , 2017, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[103]  Dick J. Veltman,et al.  Predicting the Naturalistic Course of Major Depressive Disorder Using Clinical and Multimodal Neuroimaging Information: A Multivariate Pattern Recognition Study , 2015, Biological Psychiatry.

[104]  T. Allison,et al.  Differential Sensitivity of Human Visual Cortex to Faces, Letterstrings, and Textures: A Functional Magnetic Resonance Imaging Study , 1996, The Journal of Neuroscience.

[105]  Gavin C. Cawley,et al.  On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation , 2010, J. Mach. Learn. Res..

[106]  G. Glover,et al.  Resting-State Functional Connectivity in Major Depression: Abnormally Increased Contributions from Subgenual Cingulate Cortex and Thalamus , 2007, Biological Psychiatry.