Predicting future depressive episodes from resting-state fMRI with generative embedding

• Published in: NeuroImage (Orlando, Fla.) Vol. 273; p. 119986
• Main Authors: Galioulline, Herman, Frässle, Stefan, Harrison, Samuel J., Pereira, Inês, Heinzle, Jakob, Stephan, Klaas Enno
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.06.2023; Elsevier Limited; Elsevier
• Subjects: Adult; Biobanks; Brain; Computational Psychiatry; Datasets; Depression; Depressive Disorder, Major; Early Detection; Embedding; Estimates; Feasibility studies; Functional magnetic resonance imaging; Generative Embedding; Humans; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Mental depression; Models, Neurological; Neuroimaging; Prediction; Predictions; Questionnaires; Support Vector Machine; Translational Neuromodeling; UK Biobank; United Kingdom > UK; Early Detection; Computational Psychiatry; Generative Embedding; Prediction; Translational Neuromodeling; Depression; UK Biobank
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2023.119986

•Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N = 906) of task-free ("resting state") fMRI data from the UK Biobank.•Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers.•We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best (and statistically significant) predictions, both on the training and the test set.•However, on the test set, rDCM (62% accuracy) was only slightly superior to SVM predictions based on FC (59% accuracy).•Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks; the biological interpretability of predictions was aggravated by the use of IC timeseries. After a first episode of major depressive disorder (MDD), there is substantial risk for a long-term remitting-relapsing course. Prevention and early interventions are thus critically important. Various studies have examined the feasibility of detecting at-risk individuals based on out-of-sample predictions about the future occurrence of depression. However, functional magnetic resonance imaging (fMRI) has received very little attention for this purpose so far. Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N = 906) of task-free ("resting state") fMRI data from the UK Biobank (UKB). Connectivity analyses were conducted using timeseries from pre-computed spatially independent components of different dimensionalities. Over a three-year period, 50% of selected participants showed indications of at least one depressive episode, while the other 50% did not. Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers. We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best predictions, both on the training set (0.63 accuracy, 0.66 area under the curve, AUC) and the test set (0.62 accuracy, 0.64 AUC; p < 0.001). However, on the test set, rDCM was only slightly superior to predictions based on FC (0.59 accuracy, 0.61 AUC). Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks. Overall, our analyses suggest (i) ways of improving future fMRI-based generative embedding approaches for the early detection of individuals at-risk for depression and that (ii) achieving accuracies of clinical utility may require combination of fMRI with other data modalities.