Utilizing heart rate variability to predict ICU patient outcome in traumatic brain injury

Abstract

Background: Prediction of patient outcome in medical intensive care units (ICU) may help for development and investigation of early interventional strategies. Several ICU scoring systems have been developed and are used to predict clinical outcome of ICU patients. These scores are calculated from clinical physiological and biochemical characteristics of patients. Heart rate variability (HRV) is a correlate of cardiac autonomic regulation and has been evident as a marker of poor clinical prognosis. HRV can be measured from the electrocardiogram non-invasively and monitored in real time. 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, with significant morbidity and mortality, and often difficult to predict outcomes. Changes of HRV for brain injured patients have been reported in several studies. This study aimed to utilize the continuous HRV collection from admission across the first 24 h in the ICU in severe TBI patients to develop a patient outcome prediction system.

Results: A feature extraction strategy was applied to measure the HRV fluctuation during time. A prediction model was developed based on HRV measures with a genetic algorithm for feature selection. The result (AUC: 0.77) was compared with earlier reported scoring systems (highest AUC: 0.76), encouraging further development and practical application.

Conclusions: The prediction models built with different feature sets indicated that HRV based parameters may help predict brain injury patient outcome better than the previously adopted illness severity scores.

Keywords: ECG; Euclidean distance; Feature extraction; HRV; ICU; Patient outcome; Time series.

Fig. 1

Example of RR time series analysis in the Time and Frequency domains. The RR time series are derived into the time and frequency domains. Time domain calculates overall variability within the sample, and frequency domain calculates autonomic modulation. (Kubios software, version 2.2, Biosignal Medical Group, Kupio, Finland)

Fig. 2

A diagram of the proposed method. APACHE II, APACHE III and SAPS scores were calculated based on medical records. HRV parameters were calculated based on the patient ECG data, and these parameters and the distribution of each of the HRV parameters across each of 8 continuous time points were used as the input variables (features) to the classification model. The classification model used here is logistic regression. A genetic algorithm (GA) was used for feature selection to find variable combinations that build the most accurate prediction model.