Predicting intensive care outcomes in traumatic brain injury using heart rate variability measures with feature extraction strategies

Abstract

Prediction of patient outcome in medical intensive care units (ICU) may help for development of early interventional strategies. Several ICU scoring systems have been developed and are used to predict clinical deterioration of ICU patients. These scores are calculated from characteristics of patients and clinical records. Heart rate variability (HRV) is a correlate of cardiac autonomic regulation and has been evident as a marker in many critical diseases. It can be measured based on electrocardiogram (ECG) which is non-invasive and can be real time monitored. HRV has been identified as a promising ‘electronic biomarker’ of disease severity. Traumatic brain injury (TBI) is a subset of critically ill patients, admitted to ICU. Changes of HRV for brain injured patients have been reported in several studies. This study aimed to utilize the continuous HRV collection from admission for the first 24 hours in the ICU in severe TBI patients, and develop a patient outcome prediction system. A feature extraction strategy was applied to measure the HRV fluctuation during time. A prediction model was developed based on HRV measures collected for the first day of patient admission to the ICU. The result was compared with current evaluated ones, and showed promising result for further development and potential for practical application.