TY  - INPR
A1  - Winter, Nils R.
A1  - Blanke, Julian
A1  - Leenings, Ramona
A1  - Ernsting, Jan
A1  - Fisch, Lukas
A1  - Sarink, Kelvin
A1  - Barkhau, Carlotta
A1  - Thiel, Katharina
A1  - Flinkenflügel, Kira
A1  - Winter, Alexandra
A1  - Goltermann, Janik
A1  - Meinert, Susanne
A1  - Dohm, Katharina
A1  - Repple, Jonathan
A1  - Gruber, Marius
A1  - Leehr, Elisabeth Johanna
A1  - Opel, Nils
A1  - Grotegerd, Dominik
A1  - Redlich, Ronny
A1  - Nitsch, Robert
A1  - Bauer, Jochen
A1  - Heindel, Walter
A1  - Groß, Joachim
A1  - Andlauer, Till
A1  - Forstner, Andreas Josef
A1  - Nöthen, Markus Maria
A1  - Rietschel, Marcella
A1  - Hofmann, Stefan G.
A1  - Pfarr, Julia-Katharina
A1  - Teutenberg, Lea
A1  - Usemann, Paula
A1  - Thomas-Odenthal, Florian
A1  - Wroblewski, Adrian
A1  - Brosch, Katharina
A1  - Stein, Frederike
A1  - Jansen, Andreas
A1  - Jamalabadi, Hamidreza
A1  - Alexander, Nina
A1  - Straube, Benjamin
A1  - Nenadić, Igor
A1  - Kircher, Tilo
A1  - Dannlowski, Udo
A1  - Hahn, Tim
T1  - A systematic evaluation of machine learning-based biomarkers for major depressive disorder across modalities
T2  - medRxiv
N2  - Background: Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one of the most prevalent and disabling mental disorders, Major Depressive Disorder (MDD), patients only marginally differ from healthy individuals on the group-level. Whether Precision Psychiatry can solve this discrepancy and provide specific, reliable biomarkers remains unclear as current Machine Learning (ML) studies suffer from shortcomings pertaining to methods and data, which lead to substantial over-as well as underestimation of true model accuracy.
Methods: Addressing these issues, we quantify classification accuracy on a single-subject level in N=1,801 patients with MDD and healthy controls employing an extensive multivariate approach across a comprehensive range of neuroimaging modalities in a well-curated cohort, including structural and functional Magnetic Resonance Imaging, Diffusion Tensor Imaging as well as a polygenic risk score for depression.
Findings Training and testing a total of 2.4 million ML models, we find accuracies for diagnostic classification between 48.1% and 62.0%. Multimodal data integration of all neuroimaging modalities does not improve model performance. Similarly, training ML models on individuals stratified based on age, sex, or remission status does not lead to better classification. Even under simulated conditions of perfect reliability, performance does not substantially improve. Importantly, model error analysis identifies symptom severity as one potential target for MDD subgroup identification.
Interpretation: Although multivariate neuroimaging markers increase predictive power compared to univariate analyses, single-subject classification – even under conditions of extensive, best-practice Machine Learning optimization in a large, harmonized sample of patients diagnosed using state-of-the-art clinical assessments – does not reach clinically relevant performance. Based on this evidence, we sketch a course of action for Precision Psychiatry and future MDD biomarker research.
Y1  - 2023
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/73540
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-735402
IS  - 2023.02.27.23286311
ER  -