Eur J Trauma Emerg Surg (2017) 43:805–822 DOI 10.1007/s00068-016-0757-3 ORIGINAL ARTICLE Survival prediction of trauma patients: a study on US National Trauma Data Bank 1 2 3 4 5 I. Sefrioui · R. Amadini · J. Mauro · A. El Fallahi · M. Gabbrielli Received: 22 July 2016 / Accepted: 29 December 2016 / Published online: 22 February 2017 © Springer-Verlag Berlin Heidelberg 2017 Abstract Methods In this work we evaluate different approaches Background Exceptional circumstances like major inci- for predicting whether a patient will survive or not accord- dents or natural disasters may cause a huge number of ing to simple and easily measurable observations. We con- victims that might not be immediately and simultaneously ducted a rigorous, comparative study based on the most saved. In these cases it is important to define priorities important prediction techniques using real clinical data of avoiding to waste time and resources for not savable vic- the US National Trauma Data Bank. tims. Trauma and Injury Severity Score (TRISS) methodol- Results Empirical results show that well-known Machine ogy is the well-known and standard system usually used by Learning classifiers can outperform the TRISS meth- practitioners to predict the survival probability of trauma odology. Based on our findings, we can say
European Journal of Trauma and Emergency Surgery – Springer Journals
Published: Feb 22, 2017
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud