Validation of the Korean version of the Metacognitions Questionnaire-Insomnia (MCQ-I) scale and development of shortened versions using the random forest approach

Abstract

We aimed to validate a Korean version of the Metacognitions Questionnaire-Insomnia (MCQ-I) and develop two shortened versions of the MCQ-I by applying the Random Forest (RF) algorithm. A total of 310 participants responded through an online survey, during April 3-6, 2021, which included rating scales such as the Insomnia Severity Index (ISI), Pittsburgh Sleep Quality Index (PSQI), Patient Health Questionnaire-9 (PHQ-9), and the Hospital Anxiety and Depression Scale (HADS), as well as the MCQ-I. After validating the scale, we developed two shortened versions by applying the RF. Finally, we explored the psychometric properties of the shortened versions. The Korean version of the MCQ-I showed good internal consistency based on a Cronbach's alpha of 0.96. Factor analyses showed good model fits for the single structure of the MCQ-I. From the results of the RF, 6 of the 60 items of the MCQ-I were sufficient to distinguish between people with MCQ-I scores above the cut-off value and the rest with high accuracy (AUC>0.97), leading to the 6-item (MCQI-6) version of the MCQ-I. Furthermore, we have also developed a 14-item (MCQI-14) version of the MCQ-I with higher accuracy (AUC>0.98). Both versions were reliable based on their internal consistency (alpha = 0.843 and 0.912), and confirmatory factor analysis showed good model fits for both shortened versions. In addition, good convergent validity of both shortened versions with insomnia, sleep quality, depression, and anxiety were observed. The Korean version of the MCQ-I and two shortened versions (MCQI-6, and MCQI-14) were useful, reliable, and valid tools to evaluate the role of metacognitive beliefs in sleep problems among the Korean population.

Keywords: Insomnia; MCQ-I; Machine learning; Metacognition; Random forest; Validation.