AUTHOR=Amorim Robson Luis , Oliveira Louise Makarem , Malbouisson Luis Marcelo , Nagumo Marcia Mitie , Simoes Marcela , Miranda Leandro , Bor-Seng-Shu Edson , Beer-Furlan Andre , De Andrade Almir Ferreira , Rubiano Andres M. , Teixeira Manoel Jacobsen , Kolias Angelos G. , Paiva Wellingson Silva 

TITLE=Prediction of Early TBI Mortality Using a Machine Learning Approach in a LMIC Population

JOURNAL=Frontiers in Neurology

VOLUME=Volume 10 - 2019

YEAR=2020

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2019.01366

DOI=10.3389/fneur.2019.01366

ISSN=1664-2295

ABSTRACT=Background: In a time where severe traumatic brain injury (TBI) is decreasing in developed countries and increasing in low-to-middle-income countries (LMIC’s), it’s important to understand the behavior of predictive variables in such population. There are few previous attempts to generate prediction models for TBI outcomes from local data in developing countries. Our study aim is to design and compare a series of predictive models for mortality on a new cohort in TBI patients in Brazil using Machine Learning.
Methods: A prospective registry was set in São Paulo, Brazil, enrolling all patients with a diagnosis of TBI requiring admission to the intensive care unit. We evaluated the following predictors: gender, age, pupil reactivity at admission, Glasgow Coma Scale (GCS), presence of hypoxia and hypotension, computed tomography (CT) findings, trauma severity score, and laboratory results.
Results: Overall mortality at 14 days was 22.8%. Models had a high prediction performance, with the best prediction for overall mortality achieved through Naive Bayes (area under the curve = 0.906). The most significant predictors were the GCS at admission and prehospital GCS, age, and pupil reaction. When predicting the length of stay at the intensive care unit, the Conditional Inference Tree model had the best performance (root-mean-square error = 1.011), with the most important variable across all models being the GCS at scene.
Conclusions: Models for early mortality and hospital length of stay using Machine Learning can achieve high performance when based on registry data even in developing countries, with potential to enhance quality of care.