AUTHOR=Elrod Julia , Mohr Christoph , Wolff Ruben , Boettcher Michael , Reinshagen Konrad , Bartels Pia ,  German Burn Registry , Koenigs Ingo 

TITLE=Using Artificial Intelligence to Obtain More Evidence? Prediction of Length of Hospitalization in Pediatric Burn Patients

JOURNAL=Frontiers in Pediatrics

VOLUME=8

YEAR=2021

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2020.613736

DOI=10.3389/fped.2020.613736

ISSN=2296-2360

ABSTRACT=<p><bold>Background:</bold> It is not only important for counseling purposes and for healthcare management. This study investigates the prediction accuracy of an artificial intelligence (AI)-based approach and a linear model. The heuristic expecting 1 day of stay per percentage of total body surface area (TBSA) serves as the performance benchmark.</p><p><bold>Methods:</bold> The study is based on pediatric burn patient's data sets from an international burn registry (<italic>N</italic> = 8,542). Mean absolute error and standard error are calculated for each prediction model (rule of thumb, linear regression, and random forest). Factors contributing to a prolonged stay and the relationship between TBSA and the residual error are analyzed.</p><p><bold>Results:</bold> The random forest-based approach and the linear model are statistically superior to the rule of thumb (<italic>p</italic> &lt; 0.001, resp. <italic>p</italic> = 0.009). The residual error rises as TBSA increases for all methods. Factors associated with a prolonged LOS are particularly TBSA, depth of burn, and inhalation trauma.</p><p><bold>Conclusion:</bold> Applying AI-based algorithms to data from large international registries constitutes a promising tool for the purpose of prediction in medicine in the future; however, certain prerequisites concerning the underlying data sets and certain shortcomings must be considered.</p>