Search

Accurately predicting individual antidepressant treatment response could expedite the lengthy trial-and-error process of finding an effective treatment for major depressive disorder (MDD). We tested and compared machine learning-based methods that predict individual-level pharmacotherapeutic treatment response using cortical morphometry from multisite longitudinal cohorts. We conducted an international analysis of pooled data from six sites of the ENIGMA-MDD consortium (n = 262 MDD patients; age = 36.5 ± 15.3 years; 154 (59%) female; mean response rate = 57%). Treatment response was defined as a ≥ 50% reduction in symptom severity score after 4-12 weeks post-initiation of antidepressant treatment. Structural MRI was acquired before, or < 14 days after, treatment initiation. The cortex was parcellated using FreeSurfer, from which cortical thickness and surface area were measured. We tested several machine learning pipeline configurations, which varied in (i) the way we presented the cortical data (i.e., average values per region of interest, as a vector containing voxel-wise cortical thickness and surface area measures, and as cortical thickness and surface area projections), (ii) whether we included clinical data, and the (iii) machine learning model (i.e., gradient boosting, support vector machine, and neural network classifiers) and (iv) cross-validation methods (i.e., k-fold and leave-one-site-out) we used. First, we tested if the overall predictive performance of the pipelines was better than chance, with a corrected 10-fold cross-validation permutation test. Second, we compared if some machine learning pipeline configurations outperformed others. In an exploratory analysis, we repeated our first analysis in three subpopulations, namely patients (i) from a single site, (ii) with comparable response rates, and (iii) showing the least (first quartile) and the most (fourth quartile) treatment response, which we call the extreme (non-)responders subpopulation. Finally, we explored the effect of including subcortical volumetric data on model performance. Overall, performance predicting antidepressant treatment response was not significantly better than chance (balanced accuracy = 50.5%; p = 0.66) and did not vary with alternative pipeline configurations. Exploratory analyses revealed that performance across models was only significantly better than chance in the extreme (non-)responders subpopulation (balanced accuracy = 63.9%, p = 0.001). Including subcortical data did not alter the observed model performance. Cortical structural MRI alone could not reliably predict individual pharmacotherapeutic treatment response in MDD. None of the used machine learning pipeline configurations outperformed the others. In exploratory analyses, we found that predicting response in the extreme (non-)responders subpopulation was feasible on both cortical data alone and combined with subcortical data, which suggests that specific MDD subpopulations may exhibit response-related patterns in structural data. Future work may use multimodal data to predict treatment response in MDD., (© 2025 The Author(s). Human Brain Mapping published by Wiley Periodicals LLC.)

Advances in functional brain imaging have improved the search for potential endophenotypic markers in schizophrenia. Here, we employed independent component analysis (ICA) and dynamic causal modeling (DCM) in resting state fMRI on a sample of 35 schizophrenia patients, 20 first-degree relatives and 35 control subjects. Analysis on ICA-derived networks revealed increased functional connectivity between the left frontoparietal network (FPN) and left temporal and parietal regions in schizophrenia patients (P < 0.001). First-degree relatives shared this hyperconnectivity, in particular in the supramarginal gyrus (SMG; P = 0.008). DCM analysis was employed to further explore underlying effective connectivity. Results showed increased inhibitory connections to the left angular gyrus (AG) in schizophrenia patients from all other nodes of the left FPN (P < 0.001), and in particular from the left SMG (P = 0.001). Relatives also showed a pattern of increased inhibitory connections to the left AG (P = 0.008). Furthermore, the patient group showed increased excitatory connectivity between the left fusiform gyrus and the left SMG (P = 0.002). This connection was negatively correlated to inhibitory afferents to the left AG (P = 0.005) and to the negative symptom score on the PANSS scale (P = 0.001, r = -0.51). Left frontoparietotemporal dysfunction in schizophrenia has been previously associated with a range of abnormalities, including formal thought disorder, working memory dysfunction and sensory hallucinations. Our analysis uncovered new potential endophenotypic markers of schizophrenia and shed light on the organization of the left FPN in patients and their first-degree relatives. Hum Brain Mapp 38:1741-1750, 2017. © 2017 Wiley Periodicals, Inc., (© 2016 Wiley Periodicals, Inc.)

Background: Misdiagnosing bipolar depression can lead to very deleterious consequences of mistreatment. Although depressive symptoms may be similarly expressed in unipolar and bipolar disorder, changes in specific brain networks could be very distinct, being therefore informative markers for the differential diagnosis. We aimed to characterize specific alterations in candidate large-scale networks (frontoparietal, cingulo-opercular, and default mode) in symptomatic unipolar and bipolar patients using resting state fMRI, a cognitively low demanding paradigm ideal to investigate patients., Methods: Networks were selected after independent component analysis, compared across 40 patients acutely depressed (20 unipolar, 20 bipolar), and 20 controls well-matched for age, gender, and education levels, and alterations were correlated to clinical parameters., Results: Despite comparable symptoms, patient groups were robustly differentiated by large-scale network alterations. Differences were driven in bipolar patients by increased functional connectivity in the frontoparietal network, a central executive and externally-oriented network. Conversely, unipolar patients presented increased functional connectivity in the default mode network, an introspective and self-referential network, as much as reduced connectivity of the cingulo-opercular network to default mode regions, a network involved in detecting the need to switch between internally and externally oriented demands. These findings were mostly unaffected by current medication, comorbidity, and structural changes. Moreover, network alterations in unipolar patients were significantly correlated to the number of depressive episodes., Conclusion: Unipolar and bipolar groups displaying similar symptomatology could be clearly distinguished by characteristic changes in large-scale networks, encouraging further investigation of network fingerprints for clinical use. Hum Brain Mapp 37:808-818, 2016. © 2015 Wiley Periodicals, Inc., (© 2015 Wiley Periodicals, Inc.)

In a temporal difference learning approach of classical conditioning, a theoretical error signal shifts from outcome deliverance to the onset of the conditioned stimulus. Omission of an expected outcome results in a negative prediction error signal, which is the initial step towards successful extinction and may therefore be relevant for fear extinction recall. As studies in rodents have observed a bidirectional relationship between fear extinction and rapid eye movement (REM) sleep, we aimed to test the hypothesis that REM sleep deprivation impairs recall of fear extinction through prediction error signaling in humans. In a three-day design with polysomnographically controlled REM sleep deprivation, 18 young, healthy subjects performed a fear conditioning, extinction and recall of extinction task with visual stimuli, and mild electrical shocks during combined functional magnetic resonance imaging (fMRI) and skin conductance response (SCR) measurements. Compared to the control group, the REM sleep deprivation group had increased SCR scores to a previously extinguished stimulus at early recall of extinction trials, which was associated with an altered fMRI time-course in the left middle temporal gyrus. Post-hoc contrasts corrected for measures of NREM sleep variability also revealed between-group differences primarily in the temporal lobe. Our results demonstrate altered prediction error signaling during recall of fear extinction after REM sleep deprivation, which may further our understanding of anxiety disorders in which disturbed sleep and impaired fear extinction learning coincide. Moreover, our findings are indicative of REM sleep related plasticity in regions that also show an increase in activity during REM sleep., (Copyright © 2011 Wiley Periodicals, Inc.)