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

LATEST ARTICLES
SEARCH INDEX
SUGGEST ARTICLE
THE OSI COLLECTIONS
ABOUT THE OSI

OSI STATISTICS

Total abstracts indexed:
534
Audio abstracts:
101
Open access articles:
474
Pending review:
115
Annotations added:
2
Countries represented:
91
No. of contributors:
10
Bookmarks made:
12
Specialities covered:
19

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


JournalFrontiers in Neurology
Publication date – Jan – 2020
Authors – Robson Luis Amorim, Louise Makarem Oliveira, Luis Marcelo Malbouisson, Marcia Mitie Nagumo, Marcela Simoes, Leandro Miranda, Edson Bor-Seng-Shu, Andre Beer-Furlan, Almir Ferreira De Andrade, Andres M. Rubiano,Manoel Jacobsen Teixeira,Angelos G. Kolias,Wellingson Silva Paiva
KeywordsLMICs, machine learning, mortality, prognostic, traumatic brain injury
Open access – Yes
SpecialityEmergency surgery, Neurosurgery, Trauma surgery
World region South America
Country: Brazil
Language – English
Submitted to the One Surgery Index on May 10, 2020 at 11:41 am
Abstract:

Background: In a time when the incidence of severe traumatic brain injury (TBI) is increasing in low- to middle-income countries (LMICs), it is important to understand the behavior of predictive variables in an LMIC’s population. There are few previous attempts to generate prediction models for TBI outcomes from local data in LMICs. 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 that require 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 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 LMICs. These models have the potential to inform treatment decisions and counsel family members.

OSI Number – 20348
PMID – 32038454

Public annotations on this article:
No public annotations yet