Comparison of a sleep item from the General Health Questionnaire-12 with the Jenkins Sleep Questionnaire as measures of sleep disturbance

Abstract

Background: The objective of this study was to examine whether a widely available single-item measure of sleep disturbances is an acceptable alternative to a multi-item sleep questionnaire.

Methods: Data were derived from Finnish Helsinki Health Study postal questionnaires administered in 2000-2002 (n = 7777, response rate 67%). The measures were the 4-item Jenkins Sleep Questionnaire (JSQ) on difficulties initiating and maintaining sleep, and nonrestorative sleep, and an item on sleep loss due to worry, from the General Health Questionnaire-12 (GHQ-12). Receiver operating characteristics (ROC) curve analyses were done to compare the predictive performance of the GHQ-12 item with the JSQ scale. Using the above 2 measures of sleep, logistic regression models were used to examine associations between sociodemographic factors, working conditions, health-related factors, and sleep disturbance.

Results: The estimated area under the ROC curve was 0.68 among both women and men, which suggests that the ability of the GHQ-12 item to discriminate true positives from false positives was modest. However, the associations of sleep disturbance with its key determinants were largely similar using the GHQ-12 and the JSQ.

Conclusions: A widely available, GHQ-12-based, single-item sleep measure was not an adequate substitute for a multi-item measure of overall sleep disturbance. Although the measures produced largely similar associations for key determinants of poor sleep, the discrepancies between responses must be considered when analyzing data from a measure that uses a single sleep item.

Figure 1.. ROC curve comparing a dichotomized JSQ (any sleep problem 15–28 times during 4 weeks vs others) and the 4 categories of the GHQ-12 sleep item (range 1–4).