A Systematic Review of the Single-Item Burnout Question: Its Reliability Depends on Your Purpose

Surveillance of burnout by the gold-standard Maslach Burnout Inventory (MBI) is hindered by cost and length. The validity and benchmarking of the commonly recommended and used single-item burnout question (SIBOQ) are unknown. We sought to (1) derive an equation for predicting the gold standard MBI from the SIBOQ and (2) measure the correlation of the SIBOQ with the full MBI and its subscales.

We sought studies in PubMed along with citations by and to included studies. We included studies that either correlated the SIBOQ and the MBI or reported the rates of burnout measured by both instruments. Two reviewers extracted data and CLARITY risk of bias. We used generalized linear mixed regression to separately quantify the predictive (benchmarking) and explanatory (hot-spotting) capabilities of the SIBOQ. We created a regression equation for converting SIBOQ scores to MBI scores. We meta-analyzed correlation coefficients (r) for the SIBOQ and MBI subscales. For all analyses, we considered an r of 0.7 as acceptable reliability for group-level comparisons.

We included 17 studies reporting 6788 respondents. All studies had a high risk of bias, as no study had a response rate over 75% and no study was able to examine non-responders. The correlations (r) of the SIBOQ with the overall MBI were explanatory r = 0.82 and predictive r = 0.56. Regarding MBI subscales, the correlations of the SIBOQ with emotional exhaustion were adequate with r = 0.71 (95% CI 0.67-0.74; I² = 89%), and depersonalization was r = 0.44 (95% CI 0.34-0.52; I² = 90%). However, in 8 of 15 comparisons, the r was less than 0.70.

The SIBOQ's usually adequate explanatory abilities allow "hot-spotting" to identify subgroups with high or low burnout within a single, homogenous survey fielding. However, the predictive ability of the SIBOQ indicates insufficient reliability in comparing local results to external benchmarks.