Prediction of cardiac arrest in critically ill patients presenting to the emergency department using a Machine Learning score incorporating Heart Rate Variability compared with the modified early warning score.

Crit Care. 2012 Jun 21;16(3):R108

Authors: Ong ME, Ng CH, Goh K, Liu N, Koh ZX, Shahidah N, Zhang TT, Fook-Chong S, Lin Z

Abstract

ABSTRACT: INTRODUCTION: A key aim of triage is to identify those with high risk of cardiac arrest, as they require intensive monitoring, resuscitation facilities, and early intervention. We aim to validate a novel Machine Learning (ML) score incorporating Heart Rate Variability (HRV) for triage of critically ill patients presenting to the emergency department by comparing the area under the curve, sensitivity and specificity with the modified early warning score (MEWS). METHODS: We conducted a prospective observational study of critically ill patients (Patient Acuity Category Scale 1 and 2) in an emergency department of a tertiary hospital. At presentation, HRV parameters generated from a 5-minute electrocardiogram recording are incorporated with age and vital signs to generate the ML score for each patient. The patients are then followed up for outcomes of cardiac arrest or death. RESULTS: From June 2006 to June 2008, we enrolled 925 patients. The area under the receiver operating characteristic (AUROC) curve for ML scores in predicting cardiac arrest within 72 hours is 0.781 as compared to 0.680 for MEWS (difference in AUROC (95% CI): 0.101 (0.006, 0.197)). As for in-hospital death, the area under the curve for ML score is 0.741 as compared to 0.693 for MEWS (difference in AUROC (95% CI): 0.048 (-0.023, 0.119). A cutoff ML score of [greater than or equal to] 60 predicted cardiac arrest with a sensitivity of 84.1%, specificity of 72.3% and NPV of 98.8%. A cutoff MEWS of [greater than or equal to] 3 predicted cardiac arrest with a sensitivity of 74.4%, specificity of 54.2% and NPV of 97.8%. CONCLUSIONS: We found ML scores to be more accurate than MEWS in predicting cardiac arrest within 72 hours. There is potential to develop bedside devices for risk stratification based on cardiac arrest prediction.

PMID: 22715923 [PubMed - as supplied by publisher]