Not Logged In

Accuracy of Automated Classification of Major Depressive Disorder as a Function of Symptom Severity

Full Text: 1-s2.0-S2213158216301322-main.pdf PDF

Background: Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-Control diagnostic classifiers.

Methods: Forty-five medication-free patients with DSM-IV defined MDD and 19 healthy controls participated in the study. Based on depression severity as determined by the Hamilton Rating Scale for Depression (HRSD), MDD patients were sorted into three groups: mild to moderate depression (HRSD 14-19), severe depression (HRSD 20-23), and very severe depression (HRSD ≥ 24). We collected functional magnetic resonance imaging (fMRI) data during both resting state and an emotional-face matching task. Patients in each of the three severity groups were compared against controls in separate analyses, using either the resting state or task-based fMRI data. We use each of these six datasets to train regularized logistic binary classifier and linear support vector machine (SVM) binary classifier.

Results: The resting state fMRI data showed statistically significant classification accuracy only for the very severe depression group (accuracy 67%, p=0.03), while mild to moderate (accuracy 56%, p=1.0) and severe depression (accuracy 45%, p=1.0) were only at chance. With task-based fMRI data, the automated classifier performed at chance in all three severity groups.

Conclusions: Binary linear classifiers achieved significant classification of very severe depression with resting state fMRI, but the contribution of brain measurements may have limited potential in differentiating patients with less severe depression from healthy controls.

Citation

R. Ramasubbu, M. Brown, F. Cortese, I. Gaxiola, A. Greenshaw, S. Dursun, B. Goodyear, R. Greiner. "Accuracy of Automated Classification of Major Depressive Disorder as a Function of Symptom Severity". NeuroImage: Clinical, 12, pp 320-331, July 2016.

Keywords: major depression, severity of symptoms, diagnosis, functional magnetic resonance imaging, machine learning, classification, support vector machine, fMRI, brain imaging, computational psychiatry
Category: In Journal
Web Links: Elsevier
  DOI (journal)

BibTeX

@article{Ramasubbu+al:NeuroImageClinical16,
  author = {Rajamannar Ramasubbu and Matt Brown and Filmeno Cortese and Ismael
    Gaxiola and Andrew J. Greenshaw and Serdar M Dursun and Bradley Goodyear
    and Russ Greiner},
  title = {Accuracy of Automated Classification of Major Depressive Disorder as
    a Function of Symptom Severity},
  Volume = "12",
  Pages = {320-331},
  journal = {NeuroImage: Clinical},
  year = 2016,
}

Last Updated: February 10, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo