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.
Objective
Mitochondrial dysfunction and energy metabolism impairment are key components in the pathophysiology of bipolar disorder (BD) and may involve a shift from aerobic to anaerobic metabolism. Measurement of brain lactate in vivo using proton magnetic resonance spectroscopy (1H-MRS) represents an important tool to evaluate mitochondrial and metabolic dysfunction during mood episodes as well as to monitor treatment response. To date, very few studies have quantified brain lactate in BD. In addition, no study has longitudinally evaluated lactate using 1H-MRS during depressive episodes or its association with mood stabilizer therapy. This study aimed to evaluate cingulate cortex (CC) lactate using 3T 1H-MRS during acute depressive episodes in BD and the possible effects induced by lithium monotherapy. The association between brain lactate with mitochondrial activity and antidepressant efficacy were also assessed.
Methods
Twenty medication-free outpatients with short length of illness BD (80% drug-naive) in a current major depressive episode were matched with healthy controls. Patients were treated for 6 weeks with lithium monotherapy at therapeutic doses in an open-label trial (blood levels 0.48±0.19mmL). CC lactate was measured before (week 0) and after lithium therapy (week 6) using 1H-MRS. Antidepressant efficacy was assessed with the 21-item Hamilton Depression Rating Scale as the primary outcome.
Results
Subjects with BD depression showed a significantly higher CC lactate in comparison to healthy controls. Furthermore, a significant decrease in CC lactate was observed after 6 weeks of lithium treatment compared to baseline (p=0.002). No association between reduction in CC lactate levels over time and remission at week 6 was observed.
Conclusions
This is the first report of increased CC lactate in patients with bipolar depression and lower levels after lithium monotherapy for 6 weeks. These findings indicate a shift to anaerobic metabolism and a role for lactate as a state marker during mood episodes. Energy and redox dysfunction may represent key targets for lithium’s therapeutic actions.
Clinical trial number NCT01919892
Major depressive disorder (MDD) is associated with a significant burden and costs to the society. As remission of depressive symptoms is achieved in only one-third of the MDD patients after the first antidepressant trial, unsuccessful treatments contribute largely to the observed suffering and social costs of MDD. The present article provides a summary of the therapeutic strategies that have been tested for treatment-resistant depression (TRD). A computerized search on MedLine/PubMed database from 1975 to September 2014 was performed, using the keywords "treatment-resistant depression", "major depressive disorder", "adjunctive", "refractory" and "augmentation". From the 581 articles retrieved, two authors selected 79 papers. A manual searching further considered relevant articles of the reference lists. The evidence found supports adding or switching to another antidepressant from a different class is an effective strategy in more severe MDD after failure to an initial antidepressant trial. Also, in subjects resistant to two or more classes of antidepressants, some augmentation strategies and antidepressant combinations should be considered, although the overall response and remission rates are relatively low, except for fast acting glutamatergic modulators. The wide range of available treatments for TRD reflects the complexity of MDD, which does not underlie diverse key features of the disorder. Larger and well-designed studies applying dimensional approaches to measure efficacy and effectiveness are warranted.
With the advent of Big Data Imaging Analytics applied to neuroimaging, datasets from multiple sites need to be pooled into larger samples. However, heterogeneity across different scanners, protocols and populations, renders the task of finding underlying disease signatures challenging. The current work investigates the value of multi-task learning in finding disease signatures that generalize across studies and populations. Herein, we present a multi-task learning type of formulation, in which different tasks are from different studies and populations being pooled together. We test this approach in an MRI study of the neuroanatomy of schizophrenia (SCZ) by pooling data from 3 different sites and populations: Philadelphia, Sao Paulo and Tianjin (50 controls and 50 patients from each site), which posed integration challenges due to variability in disease chronicity, treatment exposure, and data collection. Some existing methods are also tested for comparison purposes. Experiments show that classification accuracy of multi-site data outperformed that of single-site data and pooled data using multi-task feature learning, and also outperformed other comparison methods. Several anatomical regions were identified to be common discriminant features across sites. These included prefrontal, superior temporal, insular, anterior cingulate cortex, temporo-limbic and striatal regions consistently implicated in the pathophysiology of schizophrenia, as well as the cerebellum, precuneus, and fusiform, middle temporal, inferior parietal, postcentral, angular, lingual and middle occipital gyri. These results indicate that the proposed multi-task learning method is robust in finding consistent and reliable structural brain abnormalities associated with SCZ across different sites, in the presence of multiple sources of heterogeneity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.