Machine learning classification of functional neurological disorder using structural brain MRI features.

BACKGROUND: Brain imaging studies investigating grey matter in functional neurological disorder (FND) have used univariate approaches to report group-level differences compared with healthy controls (HCs). However, these findings have limited translatability because they do not differentiate patients from controls at the individual-level. METHODS: 183 participants were prospectively recruited across three groups: 61 patients with mixed FND (FND-mixed), 61 age-matched and sex-matched HCs and 61 age, sex, depression and anxiety-matched psychiatric controls (PCs). Radial basis function support vector machine classifiers with cross-validation were used to distinguish individuals with FND from HCs and PCs using 134 FreeSurfer-derived grey matter MRI features. RESULTS: Patients with FND-mixed were differentiated from HCs with an accuracy of 0.66 (p=0.005; area under the receiving operating characteristic (AUROC)=0.74); this sample was also distinguished from PCs with an accuracy of 0.60 (p=0.038; AUROC=0.56). When focusing on the functional motor disorder subtype (FND-motor, n=46), a classifier robustly differentiated these patients from HCs (accuracy=0.72; p=0.002; AUROC=0.80). FND-motor could not be distinguished from PCs, and the functional seizures subtype (n=23) could not be classified against either control group. Important regions contributing to statistically significant multivariate classifications included the cingulate gyrus, hippocampal subfields and amygdalar nuclei. Correctly versus incorrectly classified participants did not differ across a range of tested psychometric variables. CONCLUSIONS: These findings underscore the interconnection of brain structure and function in the pathophysiology of FND and demonstrate the feasibility of using structural MRI to classify the disorder. Out-of-sample replication and larger-scale classifier efforts incorporating psychiatric and neurological controls are needed.

Improving the study of brain-behavior relationships by revisiting basic assumptions.

Neuroimaging research has been at the forefront of concerns regarding the failure of experimental findings to replicate. In the study of brain-behavior relationships, past failures to find replicable and robust effects have been attributed to methodological shortcomings. Methodological rigor is important, but there are other overlooked possibilities: most published studies share three foundational assumptions, often implicitly, that may be faulty. In this paper, we consider the empirical evidence from human brain imaging and the study of non-human animals that calls each foundational assumption into question. We then consider the opportunities for a robust science of brain-behavior relationships that await if scientists ground their research efforts in revised assumptions supported by current empirical evidence.

Allostasis, Action, and Affect in Depression: Insights from the Theory of Constructed Emotion.

The theory of constructed emotion is a systems neuroscience approach to understanding the nature of emotion. It is also a general theoretical framework to guide hypothesis generation for how actions and experiences are constructed as the brain continually anticipates metabolic needs and attempts to meet those needs before they arise (termed allostasis). In this review, we introduce this framework and hypothesize that allostatic dysregulation is a trans-disorder vulnerability for mental and physical illness. We then review published findings consistent with the hypothesis that several symptoms in major depressive disorder (MDD), such as fatigue, distress, context insensitivity, reward insensitivity, and motor retardation, are associated with persistent problems in energy regulation. Our approach transforms the current understanding of MDD as resulting from enhanced emotional reactivity combined with reduced cognitive control and, in doing so, offers novel hypotheses regarding the development, progression, treatment, and prevention of MDD.

Variation is the Norm: Brain State Dynamics Evoked By Emotional Video Clips.

For the last several decades, emotion research has attempted to identify a "biomarker" or consistent pattern of brain activity to characterize a single category of emotion (e.g., fear) that will remain consistent across all instances of that category, regardless of individual and context. In this study, we investigated variation rather than consistency during emotional experiences while people watched video clips chosen to evoke instances of specific emotion categories. Specifically, we developed a sequential probabilistic approach to model the temporal dynamics in a participant's brain activity during video viewing. We characterized brain states during these clips as distinct state occupancy periods between state transitions in blood oxygen level dependent (BOLD) signal patterns. We found substantial variation in the state occupancy probability distributions across individuals watching the same video, supporting the hypothesis that when it comes to the brain correlates of emotional experience, variation may indeed be the norm.

Comparing supervised and unsupervised approaches to emotion categorization in the human brain, body, and subjective experience.

Machine learning methods provide powerful tools to map physical measurements to scientific categories. But are such methods suitable for discovering the ground truth about psychological categories? We use the science of emotion as a test case to explore this question. In studies of emotion, researchers use supervised classifiers, guided by emotion labels, to attempt to discover biomarkers in the brain or body for the corresponding emotion categories. This practice relies on the assumption that the labels refer to objective categories that can be discovered. Here, we critically examine this approach across three distinct datasets collected during emotional episodes-measuring the human brain, body, and subjective experience-and compare supervised classification solutions with those from unsupervised clustering in which no labels are assigned to the data. We conclude with a set of recommendations to guide researchers towards meaningful, data-driven discoveries in the science of emotion and beyond.