Machine Learning Algorithms to Predict In-Hospital Mortality in Patients with Traumatic Brain Injury.

Hsiang-Yun Lan,Hui-Hsun Chiang,Dueng-Yuan Hueng,Sheng-Der Hsu,En Chao,Sy-Jou Chen

doi:10.3390/jpm11111144

Abstract

Traumatic brain injury (TBI) can lead to severe adverse clinical outcomes, including death and disability. Early detection of in-hospital mortality in high-risk populations may enable early treatment and potentially reduce mortality using machine learning. However, there is limited information on in-hospital mortality prediction models for TBI patients admitted to emergency departments. The aim of this study was to create a model that successfully predicts, from clinical measures and demographics, in-hospital mortality in a sample of TBI patients admitted to the emergency department. Of the 4881 TBI patients who were screened at the emergency department at a high-level first aid duty hospital in northern Taiwan, 3331 were assigned in triage to Level I or Level II using the Taiwan Triage and Acuity Scale from January 2008 to June 2018. The most significant predictors of in-hospital mortality in TBI patients were the scores on the Glasgow coma scale, the injury severity scale, and systolic blood pressure in the emergency department admission. This study demonstrated the effective cutoff values for clinical measures when using machine learning to predict in-hospital mortality of patients with TBI. The prediction model has the potential to further accelerate the development of innovative care-delivery protocols for high-risk patients.

Highlights

Traumatic brain injury (TBI) creates an enormous health and economic burden for the visitors to an emergency department (ED) [1]
Of the 4881 TBI patients who were screened at the ED, 3331 were admitted and assigned to Level I, “resuscitation” or Level II “emergent” in triage, using the five-level Taiwan triage and acuity scale (TTAS) [39]
The results from our algorithm for predicting mortality of patients with TBI treated in the ED provide clinical professionals with effective cutoff values for the relevant clinical measures at ED admission

Summary

Introduction

The very process of decision making is characterized by both a lack of objective criteria and absence of a validated prognostic model that can predict the relevant outcome [5]. It is crucial for patients, proxies, and medical professionals to make shared treatment decisions based on accurate long-term predictions from a validated prognostic model informed by clinical measures at ED admission following the acute phase of TBI. Previous study indicates that when given at arrival to the hospital, GCS is the most significant predictor of overall mortality among TBI patients [8]. A single GCS score may not be a reliable indicator of mortality, but GCS scores obtained both on arrival and prior to arrival have been found to be highly correlated with mortality and symptom severity in TBI patients [8]

Objectives

Methods

Results

Conclusion