Decoding reappraisal and suppression from neural circuits: A combined supervised and unsupervised machine learning approach

Abstract

Emotion regulation is a core construct of mental health and deficits in emotion regulation abilities lead to psychological disorders. Reappraisal and suppression are two widely studied emotion regulation strategies but, possibly due to methodological limitations in previous studies, a consistent picture of the neural correlates related to the individual differences in their habitual use remains elusive. To address these issues, the present study applied a combination of unsupervised and supervised machine learning algorithms to the structural MRI scans of 128 individuals. First, unsupervised machine learning was used to separate the brain into naturally grouping grey matter circuits. Then, supervised machine learning was applied to predict individual differences in the use of different strategies of emotion regulation. Two predictive models, including structural brain features and psychological ones, were tested. Results showed that a temporo-parahippocampal-orbitofrontal network successfully predicted the individual differences in the use of reappraisal. Differently, insular and fronto-temporo-cerebellar networks successfully predicted suppression. In both predictive models, anxiety, the opposite strategy, and specific emotional intelligence factors played a role in predicting the use of reappraisal and suppression. This work provides new insights regarding the decoding of individual differences from structural features and other psychologically relevant variables while extending previous observations on the neural bases of emotion regulation strategies.

Clustering Electrophysiological Predisposition to Binge Drinking: An Unsupervised Machine Learning analysis

“…Furthermore, we can find unsupervised ML (UML), a set of techniques that allows us to analyse raw data without pre-existing labels, not predicting any outcome, but grouping data by its similarities or reducing dimensionality of the general dataset by eliminating redundancy. The application of UML has increased as novel technologies have been refined, influencing several lines of research, like disease identification [5, 6, 7] and differential analyses of traits of interest in healthy population [8, 9, 10] .…”

Narcissus reflected: gray and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

“…Accordingly, the current investigation aimed to characterize the joint GM and WM contributions to narcissistic personality traits, to assess their specificity in predicting narcissistic traits versus other personality traits, and build a predictive model to predict new individuals. Machine learning (ML) approaches have gained increasing public and academic traction in neuroimaging research, showcasing promising outcomes in predicting cognition and behavioral patterns in mental disorders (Caria & Grecucci, 2023; Ghomroudi et al, 2023; Grecucci, Rastelli, et al, 2023; Grecucci, Sorella, et al, 2023). Among the diverse ML techniques available, Independent Component Analysis (ICA) stands out as a valuable tool for unsupervised blind source separation (Douglas et al, 2013).…”

“…Among the diverse ML techniques available, Independent Component Analysis (ICA) stands out as a valuable tool for unsupervised blind source separation (Douglas et al, 2013). The ICA demonstrates its ability to unveil distinct neural circuits throughout the entire brain by leveraging structural MRI data from individual subjects (Ghomroudi et al, 2023; Lapomarda et al, 2021; Sorella et al, 2019). Unsupervised ML methods excel in revealing concealed structures within image collections or identifying sub-populations in extensive cohorts.…”

Narcissus reflected: Grey and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

“…Opposed to univariate methods, machine learning (ML) approaches have gained increasing public and academic traction in neuroimaging research, showcasing promising outcomes in predicting cognition and behavioural patterns in mental disorders (Caria & Grecucci, 2023;Ghomroudi et al, 2023;Grecucci, Rastelli, et al, 2023;Grecucci, Sorella, & Consolini, 2023). Unsupervised ML methods excel in revealing concealed structures within image collections or identifying sub-populations in extensive cohorts (Abraham et al, 2014).…”