Validation of two predictive models designed to aid clinicians in identifying Stevens-Johnson syndrome/toxic epidermal necrolysis: A single institution retrospective review
“…Lack of standardized triage guidelines and access to dermatologist evaluation contribute to inappropriate transfer of patients who do not have SJS/TEN and do not require burn unit care 2,3 . Two predictive models to aid in differentiation of SJS/TEN from clinical mimickers have been developed and externally validated with good discriminative ability 4,5 . These models were developed and validated based on physical examination data from experienced inpatient dermatologists.…”
“…2,3 Two predictive models to aid in differentiation of SJS/TEN from clinical mimickers have been developed and externally validated with good discriminative ability. 4,5 These models were developed and validated based on physical examination data from experienced inpatient dermatologists. Here, we sought to assess the performance of these models in the context of patient assessments by nondermatologists.…”
“…The poor discriminative ability of models evidenced here is in contrast to good discriminative ability of models when applied to data collected by dermatologists, where models were previously shown to yield AUROC of 0.9451 (mucosal involvement model) and 0.9251 (lymphopenia model). 5 This discrepancy in model performance may be due to difficulty in non-dermatologists recognising important model variables including mucosal involvement, atypical target lesions, and Nikolsky sign, three of the four variables in the mucosal involvement model. Additionally, Nikolsky sign has the largest impact in both models' predictions.…”
This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
“…Lack of standardized triage guidelines and access to dermatologist evaluation contribute to inappropriate transfer of patients who do not have SJS/TEN and do not require burn unit care 2,3 . Two predictive models to aid in differentiation of SJS/TEN from clinical mimickers have been developed and externally validated with good discriminative ability 4,5 . These models were developed and validated based on physical examination data from experienced inpatient dermatologists.…”
“…2,3 Two predictive models to aid in differentiation of SJS/TEN from clinical mimickers have been developed and externally validated with good discriminative ability. 4,5 These models were developed and validated based on physical examination data from experienced inpatient dermatologists. Here, we sought to assess the performance of these models in the context of patient assessments by nondermatologists.…”
“…The poor discriminative ability of models evidenced here is in contrast to good discriminative ability of models when applied to data collected by dermatologists, where models were previously shown to yield AUROC of 0.9451 (mucosal involvement model) and 0.9251 (lymphopenia model). 5 This discrepancy in model performance may be due to difficulty in non-dermatologists recognising important model variables including mucosal involvement, atypical target lesions, and Nikolsky sign, three of the four variables in the mucosal involvement model. Additionally, Nikolsky sign has the largest impact in both models' predictions.…”
This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.