Prediction of Shock-Refractory Ventricular Fibrillation During Resuscitation of Out-of-Hospital Cardiac Arrest

Abstract

BACKGROUND: Out-of-hospital cardiac arrest due to shock-refractory ventricular fibrillation (VF) is associated with relatively poor survival. The ability to predict refractory VF (requiring ≥3 shocks) in advance of repeated shock failure could enable preemptive targeted interventions aimed at improving outcome, such as earlier administration of antiarrhythmics, reconsideration of epinephrine use or dosage, changes in shock delivery strategy, or expedited invasive treatments. METHODS: We conducted a cohort study of VF out-of-hospital cardiac arrest to develop an ECG-based algorithm to predict patients with refractory VF. Patients with available defibrillator recordings were randomized 80%/20% into training/test groups. A random forest classifier applied to 3-s ECG segments immediately before and 1 minute after the initial shock during cardiopulmonary resuscitation was used to predict the need for ≥3 shocks based on singular value decompositions of ECG wavelet transforms. Performance was quantified by area under the receiver operating characteristic curve. RESULTS: Of 1376 patients with VF out-of-hospital cardiac arrest, 311 (23%) were female, 864 (63%) experienced refractory VF, and 591 (43%) achieved functional neurological survival. Total shock count was associated with decreasing likelihood of functional neurological survival, with a relative risk (95% CI) of 0.95 (95% CI, 0.93–0.97) for each successive shock ( P <0.001). In the 275 test patients, the area under the receiver operating characteristic curve (95% CI) for predicting refractory VF was 0.85 (95% CI, 0.79–0.89), with specificity of 91%, sensitivity of 63%, and a positive likelihood ratio of 6.7. CONCLUSIONS: A machine learning algorithm using ECGs surrounding the initial shock predicts patients likely to experience refractory VF, and could enable rescuers to preemptively target interventions to potentially improve resuscitation outcome.

Machine learning prediction of refractory ventricular fibrillation in out-of-hospital cardiac arrest using features available to EMS

“…One study developed an ECG-based algorithm to predict patients with refractory VF with significant predictive performance (AUC = 0.85 [95% CI, 0.79–0.89]). 10 Another study developed a clinical decision rule that included variables such as bystander AED application, EMS-witnessed arrest, gender, initial rhythm, and time to arrival at the scene. In both studies, arriving at the scene and contacting the patients were essential to predict refractory VF.…”

“…One such study developed a random forest algorithm using ECG data with considerable performance. 10 Another previous study using North American OHCA cohorts developed a clinical decision rule derived from decision tree analysis using data available to emergency medical services (EMS) after obtaining the patient’s initial ECG rhythm. 7 However, there is no such study done using Asian OHCA datasets, and no studies that attempt prediction using information available prior to EMS arrival at scene.…”

Wolf Creek XVII Part 6: Physiology-Guided CPR

“…Innovative techniques of real-time ECG processing may predict at the outset of resuscitation which patients are most likely to manifest refractory VF, providing an opportunity for earlier interventions that may improve the course of resuscitation. 45 …”

Decoding 2.3 million ECGs: interpretable deep learning for advancing cardiovascular diagnosis and mortality risk stratification

“…Artificial intelligence (AI) is rapidly emerging as a powerful tool in various healthcare applications. 3 , 5 , 6 Artificial intelligence ECGs have been used to predict patients with refractory ventricular fibrillation, 7 identify asymptomatic left ventricular dysfunction, 8 and diagnose abnormality. 9 While acknowledging the promise of AI-ECGs, previous studies indicated that explainability was a key limitation of many deep neural network (DNN) models.…”