A clinicotherapeutic analysis of Stevens-Johnson syndrome and toxic epidermal necrolysis with an emphasis on the predictive value and accuracy of SCORe of Toxic Epidermal Necrolysis

Background The SCORTEN scale (SCORe of Toxic Epidermal Necrolysis) is widely used to predict mortality in patients with Stevens-Johnson syndrome (SJS) or toxic epidermal necrolysis (TEN). Although it is largely a useful tool, the predictive ability of the scale is variable, and modifications to the existing scale have been suggested. In addition, there is controversy regarding the roles of active therapy and conservative management. Objectives This study was conducted to assess outcomes in SJS/TEN patients managed conservatively and to analyze the predictive performance of SCORTEN. Methods Sixty patients were studied prospectively from October 2008 to September 2011. The accuracy of SCORTEN in predicting mortality was analyzed on days 1, 3, and 5 of admission. All patients were managed conservatively. Results The discriminative power of SCORTEN was acceptable, being best on day 5. The agreement between actual and predicted mortality was poor, as indicated by a low P-value of the Hosmer-Lemeshow statistic. Only three parameters (heart rate, blood urea, and serum bicarbonate) were found to be significant on multivariate analysis, and all of these represented components within the original SCORTEN scale. The mortality rate was 16.7%. All deaths occurred within the first two weeks (8-12 days). Conclusions Serial analysis using SCORTEN is better than analysis performed only on day 1. Although the scale is largely useful, its performance is influenced by the demographic profile of the study population; minor modifications based on the population studied may increase the predictive accuracy of the original SCORTEN. In addition, conservative management is a valid therapeutic option, is preferable to treatment with steroids and immunosuppressants, and is highly recommended.