| 1. |
- Belov, Vladimir, et al.
(author)
-
Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures
- 2024
-
In: Scientific Reports. - : NATURE PORTFOLIO. - 2045-2322. ; 14:1
-
Journal article (peer-reviewed)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.
|
|
| 2. |
- Hilbert, Kevin, et al.
(author)
-
Cortical and Subcortical Brain Alterations in Specific Phobia and Its Animal and Blood-Injection-Injury Subtypes: A Mega-Analysis From the ENIGMA Anxiety Working Group.
- 2024
-
In: The American Journal of Psychiatry. - 1535-7228.
-
Journal article (peer-reviewed)abstract
- Specific phobia is a common anxiety disorder, but the literature on associated brain structure alterations exhibits substantial gaps. The ENIGMA Anxiety Working Group examined brain structure differences between individuals with specific phobias and healthy control subjects as well as between the animal and blood-injection-injury (BII) subtypes of specific phobia. Additionally, the authors investigated associations of brain structure with symptom severity and age (youths vs. adults).Data sets from 31 original studies were combined to create a final sample with 1,452 participants with phobia and 2,991 healthy participants (62.7% female; ages 5-90). Imaging processing and quality control were performed using established ENIGMA protocols. Subcortical volumes as well as cortical surface area and thickness were examined in a preregistered analysis.Compared with the healthy control group, the phobia group showed mostly smaller subcortical volumes, mixed surface differences, and larger cortical thickness across a substantial number of regions. The phobia subgroups also showed differences, including, as hypothesized, larger medial orbitofrontal cortex thickness in BII phobia (N=182) compared with animal phobia (N=739). All findings were driven by adult participants; no significant results were observed in children and adolescents.Brain alterations associated with specific phobia exceeded those of other anxiety disorders in comparable analyses in extent and effect size and were not limited to reductions in brain structure. Moreover, phenomenological differences between phobia subgroups were reflected in diverging neural underpinnings, including brain areas related to fear processing and higher cognitive processes. The findings implicate brain structure alterations in specific phobia, although subcortical alterations in particular may also relate to broader internalizing psychopathology.
|
|
| 3. |
- McWhinney, Sean R, et al.
(author)
-
Principal component analysis as an efficient method for capturing multivariate brain signatures of complex disorders-ENIGMA study in people with bipolar disorders and obesity.
- 2024
-
In: Human brain mapping. - 1097-0193. ; 45:8
-
Journal article (peer-reviewed)abstract
- Multivariate techniques better fit the anatomy of complex neuropsychiatric disorders which are characterized not by alterations in a single region, but rather by variations across distributed brain networks. Here, we used principal component analysis (PCA) to identify patterns of covariance across brain regions and relate them to clinical and demographic variables in a large generalizable dataset of individuals with bipolar disorders and controls. We then compared performance of PCA and clustering on identical sample to identify which methodology was better in capturing links between brain and clinical measures. Using data from the ENIGMA-BD working group, we investigated T1-weighted structural MRI data from 2436 participants with BD and healthy controls, and applied PCA to cortical thickness and surface area measures. We then studied the association of principal components with clinical and demographic variables using mixed regression models. We compared the PCA model with our prior clustering analyses of the same data and also tested it in a replication sample of 327 participants with BD or schizophrenia and healthy controls. The first principal component, which indexed a greater cortical thickness across all 68 cortical regions, was negatively associated with BD, BMI, antipsychotic medications, and age and was positively associated with Li treatment. PCA demonstrated superior goodness of fit to clustering when predicting diagnosis and BMI. Moreover, applying the PCA model to the replication sample yielded significant differences in cortical thickness between healthy controls and individuals with BD or schizophrenia. Cortical thickness in the same widespread regional network as determined by PCA was negatively associated with different clinical and demographic variables, including diagnosis, age, BMI, and treatment with antipsychotic medications or lithium. PCA outperformed clustering and provided an easy-to-use and interpret method to study multivariate associations between brain structure and system-level variables. PRACTITIONER POINTS: In this study of 2770 Individuals, we confirmed that cortical thickness in widespread regional networks as determined by principal component analysis (PCA) was negatively associated with relevant clinical and demographic variables, including diagnosis, age, BMI, and treatment with antipsychotic medications or lithium. Significant associations of many different system-level variables with the same brain network suggest a lack of one-to-one mapping of individual clinical and demographic factors to specific patterns of brain changes. PCA outperformed clustering analysis in the same data set when predicting group or BMI, providing a superior method for studying multivariate associations between brain structure and system-level variables.
|
|
