Machine learning increases diagnosticity in psychometric evaluation of alexithymia in fibromyalgia

Here, we report an investigation on the accuracy of the Toronto Alexithymia Scale, a measure to assess alexithymia, a multidimensional construct often associate to fibromyalgia. Two groups of participants, patients with fibromyalgia (n = 38), healthy controls (n = 38) were administered the Toronto Alexithymia Scale and background tests. Machine learning models achieved an overall accuracy higher than 80% in detecting both patients with fibromyalgia and healthy controls. The parameter which alone has demonstrated maximum efficiency in classifying the single subject within the two groups has been the item 3 of the alexithymia scale. The analysis of the most informative features, based on all scales administered, revealed that item 3 and 13 of the alexithymia questionnaire and the visual analog scale scores were the most informative attributes in correctly classifying participants (accuracy above 85%). An additional analyses using only the alexithymia scale subset of items and the visual analog scale scores has shown that the predictors which efficiently classified patients with fibromyalgia and controls were the item 3 and 7 (accuracy = 85.53%). Our findings suggest that machine learning models analysis based on the Toronto Alexithymia Scale subset of items scores accurately distinguish patients with fibromyalgia from healthy controls.