Objective. Alexithymia, as a fundamental notion in the diagnosis of psychiatric disorders, is characterized by deficits in emotional processing and, consequently, difficulties in emotion recognition. Traditional tools for assessing alexithymia, which include interviews and self-report measures, have led to inconsistent results due to some limitations as insufficient insight. Therefore, the purpose of the present study was to propose a new screening tool that utilizes machine learning models based on the scores of facial emotion recognition task. Method. In a cross-sectional study, 55 students of the University of Tabriz were selected based on the inclusion and exclusion criteria and their scores in the Toronto Alexithymia Scale (TAS-20). Then, they completed the somatization subscale of Symptom Checklist-90 Revised (SCL-90-R), Beck Anxiety Inventory (BAI) and Beck Depression Inventory-II (BDI-II), and the facial emotion recognition (FER) task. Afterwards, support vector machine (SVM) and feedforward neural network (FNN) classifiers were implemented using K-fold cross validation to predict alexithymia, and the model performance was assessed with the area under the curve (AUC), accuracy, sensitivity, specificity, and F1-measure. Results. The models yielded an accuracy range of 72.7–81.8% after feature selection and optimization. Our results suggested that ML models were able to accurately distinguish alexithymia and determine the most informative items for predicting alexithymia. Conclusion. Our results show that machine learning models using FER task, SCL-90-R, BDI-II, and BAI could successfully diagnose alexithymia and also represent the most influential factors of predicting it and can be used as a clinical instrument to help clinicians in diagnosis process and earlier detection of the disorder.

Objective: The study of factors affecting anxiety and depression as the most common emotional disorders has always been at the forefront of psychological research. Among different factors, alexithymia and somatization have considerable importance due to their emotional nature with makes them more integrated with anxiety and depression. Several studies have demonstrated a link between these four concepts, but as far as we know, the quality of the relationship has not been addressed yet. The present paper aims to investigate the mediating role of somatization in the structural relationship of alexithymia with anxiety and depression. Method: A total of 334 college students were recruited through cluster sampling and were asked to complete the Toronto Alexithymia Scale (TAS), Beck Depression Inventory – Second Edition (BDI-II), Beck Anxiety Inventory (BAI), and Somatization Subscale from the Symptom Checklist-90-Revised Questionnaire. Data were analyzed using correlational as well as structural equation modeling. Results: Based on the correlation analysis, there was significant relationship between alexithymia, somatization, anxiety, and depression. According to the results of regression weights, there is a moderate relationship between alexithymia and somatization (regression weight = 0.44). The relationship between somatization and depression is at moderate level (regression weight = 0.42) and the relationship of somatization with anxiety is at strong level (regression weight = 0.85). the goodness of fit indices for the hypothetical model showed significant coefficients at P < 0.05 (CFI = 0.98, RMSEA = 0.059). Conclusion: Findings indicated the important and influential role of somatization in explaining the relationship of alexithymia with anxiety and depression. Therefore, it seems that emotional components such as difficulty in identifying and expressing emotions as well as regulating mood states are important in the psychopathology of emotional disorders.