Application of machine learning classification for structural brain MRI in mood disorders: Critical review from a clinical perspective

Yong Ku Kim, Kyoung Sae Na

Research output: Contribution to journalReview article

15 Citations (Scopus)

Abstract

Mood disorders are a highly prevalent group of mental disorders causing substantial socioeconomic burden. There are various methodological approaches for identifying the underlying mechanisms of the etiology, symptomatology, and therapeutics of mood disorders; however, neuroimaging studies have provided the most direct evidence for mood disorder neural substrates by visualizing the brains of living individuals. The prefrontal cortex, hippocampus, amygdala, thalamus, ventral striatum, and corpus callosum are associated with depression and bipolar disorder. Identifying the distinct and common contributions of these anatomical regions to depression and bipolar disorder have broadened and deepened our understanding of mood disorders. However, the extent to which neuroimaging research findings contribute to clinical practice in the real-world setting is unclear. As traditional or non-machine learning MRI studies have analyzed group-level differences, it is not possible to directly translate findings from research to clinical practice; the knowledge gained pertains to the disorder, but not to individuals. On the other hand, a machine learning approach makes it possible to provide individual-level classifications. For the past two decades, many studies have reported on the classification accuracy of machine learning-based neuroimaging studies from the perspective of diagnosis and treatment response. However, for the application of a machine learning-based brain MRI approach in real world clinical settings, several major issues should be considered. Secondary changes due to illness duration and medication, clinical subtypes and heterogeneity, comorbidities, and cost-effectiveness restrict the generalization of the current machine learning findings. Sophisticated classification of clinical and diagnostic subtypes is needed. Additionally, as the approach is inevitably limited by sample size, multi-site participation and data-sharing are needed in the future.

Original languageEnglish
Pages (from-to)71-80
Number of pages10
JournalProgress in Neuro-Psychopharmacology and Biological Psychiatry
Volume80
DOIs
Publication statusPublished - 2018 Jan 3

Fingerprint

Mood Disorders
Neuroimaging
Brain
Bipolar Disorder
Depression
Information Dissemination
Corpus Callosum
Amygdala
Prefrontal Cortex
Thalamus
Research
Mental Disorders
Sample Size
Cost-Benefit Analysis
Comorbidity
Hippocampus
Learning
Machine Learning
Therapeutics

Keywords

  • Bipolar disorder
  • Depression
  • Machine learning
  • MRI
  • Neuroimaging

ASJC Scopus subject areas

  • Pharmacology
  • Biological Psychiatry

Cite this

@article{3dbd714279fc49a398f3a85f5195d886,
title = "Application of machine learning classification for structural brain MRI in mood disorders: Critical review from a clinical perspective",
abstract = "Mood disorders are a highly prevalent group of mental disorders causing substantial socioeconomic burden. There are various methodological approaches for identifying the underlying mechanisms of the etiology, symptomatology, and therapeutics of mood disorders; however, neuroimaging studies have provided the most direct evidence for mood disorder neural substrates by visualizing the brains of living individuals. The prefrontal cortex, hippocampus, amygdala, thalamus, ventral striatum, and corpus callosum are associated with depression and bipolar disorder. Identifying the distinct and common contributions of these anatomical regions to depression and bipolar disorder have broadened and deepened our understanding of mood disorders. However, the extent to which neuroimaging research findings contribute to clinical practice in the real-world setting is unclear. As traditional or non-machine learning MRI studies have analyzed group-level differences, it is not possible to directly translate findings from research to clinical practice; the knowledge gained pertains to the disorder, but not to individuals. On the other hand, a machine learning approach makes it possible to provide individual-level classifications. For the past two decades, many studies have reported on the classification accuracy of machine learning-based neuroimaging studies from the perspective of diagnosis and treatment response. However, for the application of a machine learning-based brain MRI approach in real world clinical settings, several major issues should be considered. Secondary changes due to illness duration and medication, clinical subtypes and heterogeneity, comorbidities, and cost-effectiveness restrict the generalization of the current machine learning findings. Sophisticated classification of clinical and diagnostic subtypes is needed. Additionally, as the approach is inevitably limited by sample size, multi-site participation and data-sharing are needed in the future.",
keywords = "Bipolar disorder, Depression, Machine learning, MRI, Neuroimaging",
author = "Kim, {Yong Ku} and Na, {Kyoung Sae}",
year = "2018",
month = "1",
day = "3",
doi = "10.1016/j.pnpbp.2017.06.024",
language = "English",
volume = "80",
pages = "71--80",
journal = "Progress in Neuro-Psychopharmacology and Biological Psychiatry",
issn = "0278-5846",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Application of machine learning classification for structural brain MRI in mood disorders

T2 - Critical review from a clinical perspective

AU - Kim, Yong Ku

AU - Na, Kyoung Sae

PY - 2018/1/3

Y1 - 2018/1/3

N2 - Mood disorders are a highly prevalent group of mental disorders causing substantial socioeconomic burden. There are various methodological approaches for identifying the underlying mechanisms of the etiology, symptomatology, and therapeutics of mood disorders; however, neuroimaging studies have provided the most direct evidence for mood disorder neural substrates by visualizing the brains of living individuals. The prefrontal cortex, hippocampus, amygdala, thalamus, ventral striatum, and corpus callosum are associated with depression and bipolar disorder. Identifying the distinct and common contributions of these anatomical regions to depression and bipolar disorder have broadened and deepened our understanding of mood disorders. However, the extent to which neuroimaging research findings contribute to clinical practice in the real-world setting is unclear. As traditional or non-machine learning MRI studies have analyzed group-level differences, it is not possible to directly translate findings from research to clinical practice; the knowledge gained pertains to the disorder, but not to individuals. On the other hand, a machine learning approach makes it possible to provide individual-level classifications. For the past two decades, many studies have reported on the classification accuracy of machine learning-based neuroimaging studies from the perspective of diagnosis and treatment response. However, for the application of a machine learning-based brain MRI approach in real world clinical settings, several major issues should be considered. Secondary changes due to illness duration and medication, clinical subtypes and heterogeneity, comorbidities, and cost-effectiveness restrict the generalization of the current machine learning findings. Sophisticated classification of clinical and diagnostic subtypes is needed. Additionally, as the approach is inevitably limited by sample size, multi-site participation and data-sharing are needed in the future.

AB - Mood disorders are a highly prevalent group of mental disorders causing substantial socioeconomic burden. There are various methodological approaches for identifying the underlying mechanisms of the etiology, symptomatology, and therapeutics of mood disorders; however, neuroimaging studies have provided the most direct evidence for mood disorder neural substrates by visualizing the brains of living individuals. The prefrontal cortex, hippocampus, amygdala, thalamus, ventral striatum, and corpus callosum are associated with depression and bipolar disorder. Identifying the distinct and common contributions of these anatomical regions to depression and bipolar disorder have broadened and deepened our understanding of mood disorders. However, the extent to which neuroimaging research findings contribute to clinical practice in the real-world setting is unclear. As traditional or non-machine learning MRI studies have analyzed group-level differences, it is not possible to directly translate findings from research to clinical practice; the knowledge gained pertains to the disorder, but not to individuals. On the other hand, a machine learning approach makes it possible to provide individual-level classifications. For the past two decades, many studies have reported on the classification accuracy of machine learning-based neuroimaging studies from the perspective of diagnosis and treatment response. However, for the application of a machine learning-based brain MRI approach in real world clinical settings, several major issues should be considered. Secondary changes due to illness duration and medication, clinical subtypes and heterogeneity, comorbidities, and cost-effectiveness restrict the generalization of the current machine learning findings. Sophisticated classification of clinical and diagnostic subtypes is needed. Additionally, as the approach is inevitably limited by sample size, multi-site participation and data-sharing are needed in the future.

KW - Bipolar disorder

KW - Depression

KW - Machine learning

KW - MRI

KW - Neuroimaging

UR - http://www.scopus.com/inward/record.url?scp=85021855478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021855478&partnerID=8YFLogxK

U2 - 10.1016/j.pnpbp.2017.06.024

DO - 10.1016/j.pnpbp.2017.06.024

M3 - Review article

C2 - 28648568

AN - SCOPUS:85021855478

VL - 80

SP - 71

EP - 80

JO - Progress in Neuro-Psychopharmacology and Biological Psychiatry

JF - Progress in Neuro-Psychopharmacology and Biological Psychiatry

SN - 0278-5846

ER -