Machine Learning Prediction of Estimated Risk for Bipolar Disorders Using Hippocampal Subfield and Amygdala Nuclei Volumes

The pathophysiology of bipolar disorder (BD) remains mostly unclear. Yet, a valid biomarker is necessary to improve upon the early detection of this serious disorder. Patients with manifest BD display reduced volumes of the hippocampal subfields and amygdala nuclei. In this pre-registered analysis, we used structural MRI (n = 271, 7 sites) to compare volumes of hippocampus, amygdala and their subfields/nuclei between help-seeking subjects divided into risk groups for BD as estimated by BPSS-P, BARS and EPIbipolar. We performed between-group comparisons using linear mixed effects models for all three risk assessment tools. Additionally, we aimed to differentiate the risk groups using a linear support vector machine. We found no significant volume differences between the risk groups for all limbic structures during the main analysis. However, the SVM could still classify subjects at risk according to BPSS-P criteria with a balanced accuracy of 66.90% (95% CI 59.2–74.6) for 10-fold cross-validation and 61.9% (95% CI 52.0–71.9) for leave-one-site-out. Structural alterations of the hippocampus and amygdala may not be as pronounced in young people at risk; nonetheless, machine learning can predict the estimated risk for BD above chance. This suggests that neural changes may not merely be a consequence of BD and may have prognostic clinical value.

[1]  G. Juckel,et al.  Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features. , 2023, Psychological medicine.

[2]  D. Ville,et al.  Dynamic functional hippocampal markers of residual depressive symptoms in euthymic bipolar disorder , 2023, Brain and behavior.

[3]  J. Hendrikse,et al.  Psychosocial factors and hippocampal subfields: The Medea‐7T study , 2022, Human brain mapping.

[4]  S. Schwab,et al.  Evidence for postnatal neurogenesis in the human amygdala , 2022, Communications Biology.

[5]  Kamyar Keramatian,et al.  Transitioning to bipolar disorder: A systematic review of prospective high-risk studies , 2021, Current opinion in psychiatry.

[6]  P. Vuilleumier,et al.  Mood disorders disrupt the functional dynamics, not spatial organization of brain resting state networks , 2021, NeuroImage: Clinical.

[7]  G. Juckel,et al.  Individuals at increased risk for development of bipolar disorder display structural alterations similar to people with manifest disease , 2021, Translational Psychiatry.

[8]  Vijay Mago,et al.  Role of machine learning in medical research: A survey , 2021, Comput. Sci. Rev..

[9]  A. Dayer,et al.  Inflammation, anxiety, and stress in bipolar disorder and borderline personality disorder: A narrative review , 2021, Neuroscience & Biobehavioral Reviews.

[10]  P. Vuilleumier,et al.  Dynamics of amygdala connectivity in bipolar disorders: a longitudinal study across mood states , 2021, Neuropsychopharmacology.

[11]  Tilo Kircher,et al.  The German research consortium for the study of bipolar disorder (BipoLife): a magnetic resonance imaging study protocol , 2021, International Journal of Bipolar Disorders.

[12]  K. Heekeren,et al.  Multimodal Machine Learning Workflows for Prediction of Psychosis in Patients With Clinical High-Risk Syndromes and Recent-Onset Depression , 2020, JAMA psychiatry.

[13]  Erick Jorge Canales-Rodríguez,et al.  In vivo hippocampal subfield volumes in bipolar disorder—A mega‐analysis from The Enhancing Neuro Imaging Genetics through Meta‐Analysis Bipolar Disorder Working Group , 2020, Human brain mapping.

[14]  O. Andreassen,et al.  In Vivo Amygdala Nuclei Volumes in Schizophrenia and Bipolar Disorders , 2020, medRxiv.

[15]  D. Denys,et al.  Investigating the causal nature of the relationship of subcortical brain volume with smoking and alcohol use , 2020, The British Journal of Psychiatry.

[16]  J. E. Iglesias,et al.  FreeSurfer‐based segmentation of hippocampal subfields: A review of methods and applications, with a novel quality control procedure for ENIGMA studies and other collaborative efforts , 2020, Human brain mapping.

[17]  M. A. Shchedrina,et al.  Amygdala: Neuroanatomical and Morphophysiological Features in Terms of Neurological and Neurodegenerative Diseases , 2020, Brain sciences.

[18]  Erick Jorge Canales-Rodríguez,et al.  What we learn about bipolar disorder from large‐scale neuroimaging: Findings and future directions from the ENIGMA Bipolar Disorder Working Group , 2020, Human brain mapping.

[19]  Lachlan T. Strike,et al.  Region-specific sex differences in the hippocampus , 2020, NeuroImage.

[20]  Jun Lyu,et al.  Trends in the incidence and DALYs of bipolar disorder at global, regional, and national levels: Results from the global burden of Disease Study 2017. , 2020, Journal of psychiatric research.

[21]  E. Duchesnay,et al.  Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions , 2020, Bipolar disorders.

[22]  I. Melle,et al.  Hippocampal subfield and amygdala nuclei volumes in schizophrenia patients with a history of violence , 2020, Biological Psychiatry.

[23]  G. Juckel,et al.  Improving early recognition and intervention in people at increased risk for the development of bipolar disorder: study protocol of a prospective-longitudinal, naturalistic cohort study (Early-BipoLife) , 2019, International Journal of Bipolar Disorders.

[24]  L. Tozzi,et al.  Effects of early life adversity and FKBP5 genotype on hippocampal subfields volume in major depression. , 2019, Journal of affective disorders.

[25]  Colm G. Connolly,et al.  Interactive impact of childhood maltreatment, depression, and age on cortical brain structure: mega-analytic findings from a large multi-site cohort , 2019, Psychological Medicine.

[26]  Fabio Sambataro,et al.  Neural signatures of the risk for bipolar disorder: A meta‐analysis of structural and functional neuroimaging studies , 2018, Bipolar disorders.

[27]  Erick Jorge Canales-Rodríguez,et al.  Using structural MRI to identify bipolar disorders – 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group , 2018, Molecular Psychiatry.

[28]  T. Suppes,et al.  Multigenerational transmission of liability to psychiatric illness in offspring of parents with bipolar disorder , 2018, Bipolar disorders.

[29]  I. Falkenberg,et al.  Semistructured Interview for Bipolar At Risk States (SIBARS) , 2018, Psychiatry Research.

[30]  P. Falkai,et al.  Machine Learning Approaches for Clinical Psychology and Psychiatry. , 2018, Annual review of clinical psychology.

[31]  F. Piras,et al.  Association between duration of lithium exposure and hippocampus/amygdala volumes in type I bipolar disorder. , 2018, Journal of affective disorders.

[32]  L. Tozzi,et al.  Epigenetic Changes of FKBP5 as a Link Connecting Genetic and Environmental Risk Factors with Structural and Functional Brain Changes in Major Depression , 2018, Neuropsychopharmacology.

[33]  Sonia J. Lupien,et al.  The effects of chronic stress on the human brain: From neurotoxicity, to vulnerability, to opportunity , 2018, Frontiers in Neuroendocrinology.

[34]  Krzysztof J. Gorgolewski,et al.  MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites , 2016, bioRxiv.

[35]  D. Kupfer,et al.  Assessment of a Person-Level Risk Calculator to Predict New-Onset Bipolar Spectrum Disorder in Youth at Familial Risk , 2017, JAMA psychiatry.

[36]  B Fischl,et al.  High-resolution magnetic resonance imaging reveals nuclei of the human amygdala: manual segmentation to automatic atlas , 2017, NeuroImage.

[37]  Erick Jorge Canales-Rodríguez,et al.  Cortical abnormalities in bipolar disorder: an MRI analysis of 6503 individuals from the ENIGMA Bipolar Disorder Working Group , 2017, Molecular Psychiatry.

[38]  T. Schulze,et al.  Aims and structure of the German Research Consortium BipoLife for the study of bipolar disorder , 2016, International Journal of Bipolar Disorders.

[39]  Koenraad Van Leemput,et al.  Bayesian longitudinal segmentation of hippocampal substructures in brain MRI using subject-specific atlases , 2016, NeuroImage.

[40]  Aaron S. Heller,et al.  Cortical-Subcortical Interactions in Depression: From Animal Models to Human Psychopathology , 2016, Front. Syst. Neurosci..

[41]  O. Andreassen,et al.  Subcortical volumetric abnormalities in bipolar disorder , 2016, Molecular Psychiatry.

[42]  A. Zalesky,et al.  Hippocampal harms, protection and recovery following regular cannabis use , 2016, Translational psychiatry.

[43]  B. Czéh,et al.  Regulation of Adult Neurogenesis and Plasticity by (Early) Stress, Glucocorticoids, and Inflammation. , 2015, Cold Spring Harbor perspectives in biology.

[44]  Koenraad Van Leemput,et al.  A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: Application to adaptive segmentation of in vivo MRI , 2015, NeuroImage.

[45]  Anders M. Dale,et al.  In Vivo Hippocampal Subfield Volumes in Schizophrenia and Bipolar Disorder , 2015, Biological Psychiatry.

[46]  T. Kishimoto,et al.  The Bipolar Prodrome Symptom Interview and Scale–Prospective (BPSS‐P): description and validation in a psychiatric sample and healthy controls , 2014, Bipolar disorders.

[47]  Godfrey D Pearlson,et al.  Medial temporal lobe structures and hippocampal subfields in psychotic disorders: findings from the Bipolar-Schizophrenia Network on Intermediate Phenotypes (B-SNIP) study. , 2014, JAMA psychiatry.

[48]  B. Kerner The Application of Clinical Genetics Dovepress Genetics of Bipolar Disorder , 2022 .

[49]  Yi-Yu Chou,et al.  Global and regional alterations of hippocampal anatomy in long‐term meditation practitioners , 2013, Human brain mapping.

[50]  A. Dale,et al.  Critical ages in the life course of the adult brain: nonlinear subcortical aging , 2013, Neurobiology of Aging.

[51]  M. Leboyer,et al.  Duration of untreated bipolar disorder: missed opportunities on the long road to optimal treatment , 2013, Acta psychiatrica Scandinavica.

[52]  M. Alda,et al.  Brain Structural Signature of Familial Predisposition for Bipolar Disorder: Replicable Evidence For Involvement of the Right Inferior Frontal Gyrus , 2013, Biological Psychiatry.

[53]  Hilleke E. Hulshoff Pol,et al.  Classification of schizophrenia patients and healthy controls from structural MRI scans in two large independent samples , 2012, NeuroImage.

[54]  A. Mechelli,et al.  Using Support Vector Machine to identify imaging biomarkers of neurological and psychiatric disease: A critical review , 2012, Neuroscience & Biobehavioral Reviews.

[55]  G. Juckel,et al.  Risk constellations prior to the development of bipolar disorders: rationale of a new risk assessment tool. , 2012, Journal of affective disorders.

[56]  Elmar Brähler,et al.  [The German Version of the Childhood Trauma Questionnaire (CTQ): psychometric characteristics in a representative sample of the general population]. , 2012, Psychotherapie, Psychosomatik, medizinische Psychologie.

[57]  Klaus-Robert Müller,et al.  Introduction to machine learning for brain imaging , 2011, NeuroImage.

[58]  R. Kessler,et al.  Prevalence and correlates of bipolar spectrum disorder in the world mental health survey initiative. , 2011, Archives of general psychiatry.

[59]  E. Bullmore,et al.  A quantitative meta-analysis of fMRI studies in bipolar disorder. , 2011, Bipolar disorders.

[60]  Klaus P. Ebmeier,et al.  Magnetic resonance imaging studies in bipolar disorder and schizophrenia: meta-analysis. , 2009, The British journal of psychiatry : the journal of mental science.

[61]  Y. Hirayasu,et al.  Smaller amygdala is associated with anxiety in patients with panic disorder , 2009, Psychiatry and clinical neurosciences.

[62]  Polina Golland,et al.  Automated segmentation of hippocampal subfields from ultra‐high resolution in vivo MRI , 2009, Hippocampus.

[63]  Tom M. Mitchell,et al.  Machine learning classifiers and fMRI: A tutorial overview , 2009, NeuroImage.

[64]  H. Lôo [On bipolar disorder]. , 2008, L'Encephale.

[65]  B. Bogerts,et al.  Volume deficits of subcortical nuclei in mood disorders , 2005, European Archives of Psychiatry and Clinical Neuroscience.

[66]  Olga V. Demler,et al.  Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the National Comorbidity Survey Replication. , 2005, Archives of general psychiatry.

[67]  Anders M. Dale,et al.  Sequence-independent segmentation of magnetic resonance images , 2004, NeuroImage.

[68]  P. Brambilla,et al.  Stress and hippocampal abnormalities in psychiatric disorders , 2004, European Neuropsychopharmacology.

[69]  J. Gore,et al.  Amygdala and hippocampal volumes in adolescents and adults with bipolar disorder. , 2003, Archives of general psychiatry.

[70]  H. Pincus,et al.  Bipolar Disorder , 2002, The Lancet.

[71]  G. Juckel,et al.  [Mental health of children, adolescents and young adults--part 1: prevalence, illness persistence, adversities, service use, treatment delay and consequences]. , 2013, Fortschritte der Neurologie-Psychiatrie.

[72]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[73]  A. Dale,et al.  High‐resolution intersubject averaging and a coordinate system for the cortical surface , 1999, Human brain mapping.

[74]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .