A support vector machine for predicting defibrillation outcomes from waveform metrics.

Andrew Howe, OJ Escalona, Rebecca Di Maio, Bertrand Massot, Nick A Cromie, Karen M Darragh, Jennifer Adgey, DJ McEneaney

Research output: Contribution to journalArticlepeer-review

23 Citations (Scopus)

Abstract

Background: Algorithms to predict shock success based on VF waveform metrics could significantly enhance resuscitation by optimising the timing of defibrillation. Objective: To investigate robust methods of predicting defibrillation success in VF cardiac arrest patients, by using a support vector machine (SVM) optimisation approach. Methods: Frequency-domain (AMSA, dominant frequency and median frequency) and time-domain (slope and RMS amplitude) VF waveform metrics were calculated in a 4.1s window prior to defibrillation. Conventional prediction test validity of each waveform parameter was conducted and used AUC > 0.6 as the criterion for inclusion as a corroborative attribute processed by the SVM classification model. The latter used a Gaussian radial-basis-function (RBF) kernel and the error penalty factor C was fixed to 1. A two-fold cross-validation resampling technique was employed. Results: A total of 41 patients had 115 defibrillation instances. AMSA, slope and RMS waveform metrics performed test validation with AUC > 0.6 for predicting termination of VF and return-to-organised rhythm. Predictive accuracy of the optimised SVM design for termination of VF was 81.9% (±1.24 SD); positive and negative predictivity were respectively 84.3% (±1.98 SD) and 77.4% (±1.24 SD); sensitivity and specificity were 87.6% (±2.69 SD) and 71.6% (±9.38 SD) respectively. Conclusions: AMSA, slope and RMS were the best VF waveform frequency–time parameters predictors of termination of VF according to test validity assessment. This a priori can be used for a simplified SVM optimised design that combines the predictive attributes of these VF waveform metrics for improved prediction accuracy and generalisation performance without requiring the definition of any threshold value on waveform metrics.
Original languageEnglish
Pages (from-to)343-349
JournalResuscitation
Volume85
Issue number3
DOIs
Publication statusPublished (in print/issue) - 28 Nov 2013

Keywords

  • Cardiac arrest
  • defibrillation
  • VF waveform metrics
  • group classification
  • resuscitation therapy
  • outcome prediction
  • support vector machine
  • SVM
  • supervised machine learning
  • CPR

Fingerprint

Dive into the research topics of 'A support vector machine for predicting defibrillation outcomes from waveform metrics.'. Together they form a unique fingerprint.

Cite this