Machine Learning-Based Alexithymia Assessment Using Resting-State Default Mode Network Functional Connectivity

A machine-learning model using resting-state electroencephalogram (EEG) signals can assess alexithymia severity with moderate accuracy. Functional connectivity in brain regions related to the default mode network, estimated via source localization, served as explanatory variables. The model classified individuals as having low or high alexithymia severity, achieving a maximum ROC-AUC score of 0.70. Analysis using explainable artificial intelligence revealed that functional connectivity in the theta and gamma frequency bands, particularly in the Left Hippocampus, was most effective for assessment. The findings suggest EEG and machine learning offer a potential objective method for evaluating alexithymia, a risk factor for several mental disorders.

Study at a glance

Abstract

Alexithymia is regarded as one of the risk factors for several prevalent mental disorders, and there is a growing need for convenient and objective methods to assess alexithymia. Therefore, this study proposes a method for constructing models to assess alexithymia using machine learning and electroencephalogram (EEG) signals. The explanatory variables for the models were functional connectivity calculated from resting-state EEG data, reflecting the default mode network (DMN). The functional connectivity was computed for each frequency band in brain regions estimated by source localization. The objective variable was defined as either low or high alexithymia severity. Explainable artificial intelligence (XAI) was used to analyze which features the models relied on for their assessments. The results indicated that the classification model suggested effective assessment depending on the threshold used to define low and high alexithymia. The maximum receiver operating characteristic area under the curve (ROC-AUC) score was 0.70. Furthermore, analysis of the classification model indicated that functional connectivity in the theta and gamma frequency bands, and specifically in the Left Hippocampus, was effective for alexithymia assessment. This study demonstrates the potential applicability of EEG signals and machine learning in alexithymia assessment.