Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 11;14(1):1084.
doi: 10.1038/s41598-023-47934-8.

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Vladimir Belov  1 Tracy Erwin-Grabner  1 Moji Aghajani  2   3 Andre Aleman  4 Alyssa R Amod  5 Zeynep Basgoze  6 Francesco Benedetti  7 Bianca Besteher  8 Robin Bülow  9 Christopher R K Ching  10 Colm G Connolly  11 Kathryn Cullen  6 Christopher G Davey  12 Danai Dima  13   14 Annemiek Dols  2 Jennifer W Evans  15 Cynthia H Y Fu  16   17 Ali Saffet Gonul  18 Ian H Gotlib  19 Hans J Grabe  20 Nynke Groenewold  5 J Paul Hamilton  21   22 Ben J Harrison  12 Tiffany C Ho  23   24 Benson Mwangi  25   26 Natalia Jaworska  27 Neda Jahanshad  10 Bonnie Klimes-Dougan  28 Sheri-Michelle Koopowitz  5 Thomas Lancaster  29   30 Meng Li  8 David E J Linden  29   30   31   32 Frank P MacMaster  33 David M A Mehler  29   30   34 Elisa Melloni  7 Bryon A Mueller  6 Amar Ojha  35   36 Mardien L Oudega  2 Brenda W J H Penninx  2 Sara Poletti  7 Edith Pomarol-Clotet  37 Maria J Portella  38 Elena Pozzi  39   40 Liesbeth Reneman  41 Matthew D Sacchet  42 Philipp G Sämann  43 Anouk Schrantee  41 Kang Sim  44   45   46 Jair C Soares  26 Dan J Stein  47 Sophia I Thomopoulos  10 Aslihan Uyar-Demir  18 Nic J A van der Wee  48 Steven J A van der Werff  48   49 Henry Völzke  50 Sarah Whittle  51 Katharina Wittfeld  20   52 Margaret J Wright  53   54 Mon-Ju Wu  25   26 Tony T Yang  23 Carlos Zarate  55 Dick J Veltman  2 Lianne Schmaal  39   40 Paul M Thompson  10 Roberto Goya-Maldonado  56 ENIGMA Major Depressive Disorder working group
Affiliations

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Vladimir Belov et al. Sci Rep. .

Abstract

Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.

PubMed Disclaimer

Conflict of interest statement

PMT and NJ received a research grant from Biogen, Inc., for research unrelated to this manuscript. HJG has received travel grants and speakers honoraria from Fresenius Medical Care, Neuraxpharm, Servier and Janssen Cilag as well as research funding from Fresenius Medical Care unrelated to this manuscript. JCS has served as a consultant for Pfizer,Sunovion, Sanofi, Johnson & Johnson, Livanova, and Boehringer Ingelheim. The remaining authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Feature weights of support vector machines (SVM) with the linear kernel. To assess the decision-making of SVM to differentiate subjects with major depressive disorder (MDD) from healthy controls (HC), we investigate the importance of the structural brain features by looking at the corresponding feature weights for the regional cortical surface areas, cortical thicknesses and subcortical volumes. The horizontal bars indicate the 95% confidence interval calculated using percentile method via bootstrapping.
Figure 2
Figure 2
The most informative features for classification including regional cortical surface areas, thicknesses and subcortical volumes, trained on the whole data set without and with ComBat harmonization. Increased and decreased feature weight values in the major depressive disorder (MDD) group are represented by red and blue colormap, respectively.
Figure 3
Figure 3
Detailed analysis pipeline. Initial data from all cohorts is split into training and test sets according to splitting strategies (Splitting by Age/Sex and Splitting by Site) after removing subjects with more than 75% missing data and data imputation steps. The corresponding training folds are then residualized directly to remove ICV, age and sex related effects and fed to the classification algorithms. In case of harmonization by ComBat, the residualization step takes place after the harmonization step is conducted. If training folds were harmonized by ComBat, the test fold was harmonized as well by using ComBat estimates from the training folds. Next, the test fold was residualized by using estimates obtained from the training folds. We estimated classification performance on the residualized test fold. This routine was performed iteratively for each combination of training and test folds.

Similar articles

Cited by

References

    1. Kessler RC, Bromet EJ. The epidemiology of depression across cultures. Annu. Rev. Public Health. 2013;34:119–138. doi: 10.1146/annurev-publhealth-031912-114409. - DOI - PMC - PubMed
    1. Cho Y, et al. Factors associated with quality of life in patients with depression: A nationwide population-based study. PLOS ONE. 2019;14:e0219455. doi: 10.1371/journal.pone.0219455. - DOI - PMC - PubMed
    1. Cai, H. et al. Prevalence of suicidality in major depressive disorder: A systematic review and meta-analysis of comparative studies. Front. Psychiatry12, (2021). - PMC - PubMed
    1. Cleare AFSWCDKMBMLPAJ. A multidimensional tool to quantify treatment resistance in depression: The Maudsley staging method. J. Clin. Psychiatry. 2009;70:12363. - PubMed
    1. Han LKM, et al. Brain aging in major depressive disorder: Results from the ENIGMA major depressive disorder working group. Mol. Psychiatry. 2020 doi: 10.1038/s41380-020-0754-0. - DOI - PMC - PubMed

MeSH terms