Towards person-centered neuroimaging markers for resilience and vulnerability in Bipolar Disorder

Abstract

Improved clinical care for Bipolar Disorder (BD) relies on the identification of diagnostic markers that can reliably detect disease-related signals in clinically heterogeneous populations. At the very least, diagnostic markers should be able to differentiate patients with BD from healthy individuals and from individuals at familial risk for BD who either remain well or develop other psychopathology, most commonly Major Depressive Disorder (MDD). These issues are particularly pertinent to the development of translational applications of neuroimaging as they represent challenges for which clinical observation alone is insufficient. We therefore applied pattern classification to task-based functional magnetic resonance imaging (fMRI) data of the n-back working memory task, to test their predictive value in differentiating patients with BD (n=30) from healthy individuals (n=30) and from patients’ relatives who were either diagnosed with MDD (n=30) or were free of any personal lifetime history of psychopathology (n=30). Diagnostic stability in these groups was confirmed with 4-year prospective follow-up. Task-based activation patterns from the fMRI data were analyzed with Gaussian Process Classifiers (GPC), a machine learning approach to detecting multivariate patterns in neuroimaging datasets. Consistent significant classification results were only obtained using data from the 3-back versus 0-back contrast. Using contrast, patients with BD were correctly classified compared to unrelated healthy individuals with an accuracy of 83.5%, sensitivity of 84.6% and specificity of 92.3%. Classification accuracy, sensitivity and specificity when comparing patients with BD to their relatives with MDD, were respectively 73.1%, 53.9% and 94.5%. Classification accuracy, sensitivity and specificity when comparing patients with BD to their healthy relatives were respectively 81.8%, 72.7% and 90.9%. We show that significant individual classification can be achieved using whole brain pattern analysis of task-based working memory fMRI data. The high accuracy and specificity achieved by all three classifiers suggest that multivariate pattern recognition analyses can aid clinicians in the clinical care of BD in situations of true clinical uncertainty regarding the diagnosis and prognosis.

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions

“…Eight functional studies were found, 1 used arterial spin labelling (ASL) of anterior cingulate cortex reaching 52.8% ACC, 55 3 used resting‐state fMRI reaching between 61.7, 56 81% 57 and 82.22% ACC 58 and 4 used task‐based fMRI reaching between 59.72% and 83.5% ACC 59‐62 …”

Neuroimaging Correlates of Emotional Response-Inhibition Discriminate Between Young Depressed Adults With and Without Sub-threshold Bipolar Symptoms

“…Next multivariate machine learning was applied to investigate the individual-level classification accuracy of the Go-No-go task for subjects in each group (Frangou, Dima et al 2017).…”

“…Although several studies have used close relatives of bipolar subjects to identify high risk endophenotypes (Piguet, Fodoulian et al 2015, Vierck, Porter et al 2015, Frangou, Dima et al 2017), MDD+ subjects have not yet been used to identify clinically applicable activation patterns, with the ultimate goal of applying these patterns in clinical work to identify at-risk individuals.…”

“…Typical fMRI studies in this area employ univariate analyses to find group-related differences. Though information gained via these methods provides valuable insights into possible BDD pathophysiology, they have less individual-level-clinical utility for differentiating between groups (Frangou, Dima et al 2017, Amit Etkin 2019. In comparison, multivariate Cha Page 5 machine learning techniques, such as support vector machines (SVM) or Gaussian Process Classifiers (GPC), can be to provide individual-level classification accuracy of an fMRI task.…”

“…For example, Frangou and colleagues used GPC to classify BD and relatives of BD at-risk for developing BD, using a 3-back working memory task (Frangou, Dima et al 2017). Such individual level analyses could have utility in clinical situations which require correctly e.g.…”