| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Moreno-Alcazar, A, et al.
(author)
-
Brain structural and functional substrates of ADGRL3 (latrophilin 3) haplotype in attention-deficit/hyperactivity disorder
- 2021
-
In: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 11:1, s. 2373-
-
Journal article (peer-reviewed)abstract
- Previous studies have shown that the gene encoding the adhesion G protein-coupled receptor L3 (ADGRL3; formerly latrophilin 3, LPHN3) is associated with Attention-Deficit/Hyperactivity Disorder (ADHD). Conversely, no studies have investigated the anatomical or functional brain substrates of ADGRL3 risk variants. We examined here whether individuals with different ADGRL3 haplotypes, including both patients with ADHD and healthy controls, showed differences in brain anatomy and function. We recruited and genotyped adult patients with combined type ADHD and healthy controls to achieve a sample balanced for age, sex, premorbid IQ, and three ADGRL3 haplotype groups (risk, protective, and others). The final sample (n = 128) underwent structural and functional brain imaging (voxel-based morphometry and n-back working memory fMRI). We analyzed the brain structural and functional effects of ADHD, haplotypes, and their interaction, covarying for age, sex, and medication. Individuals (patients or controls) with the protective haplotype showed strong, widespread hypo-activation in the frontal cortex extending to inferior temporal and fusiform gyri. Individuals (patients or controls) with the risk haplotype also showed hypo-activation, more focused in the right temporal cortex. Patients showed parietal hyper-activation. Disorder-haplotype interactions, as well as structural findings, were not statistically significant. To sum up, both protective and risk ADGRL3 haplotypes are associated with substantial brain hypo-activation during working memory tasks, stressing this gene’s relevance in cognitive brain function. Conversely, we did not find brain effects of the interactions between adult ADHD and ADGRL3 haplotypes.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Nunes, A, et al.
(author)
-
Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group
- 2020
-
In: Molecular psychiatry. - : Springer Science and Business Media LLC. - 1476-5578 .- 1359-4184. ; 25:9, s. 2130-2143
-
Journal article (peer-reviewed)abstract
- Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47–67.00, ROC-AUC = 71.49%, 95% CI = 69.39–73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70–60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen’s Kappa = 0.83, 95% CI = 0.829–0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.
|
|
