Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning
<p>Abstract</p> <p>Background</p> <p>Ventricular Fibrillation (VF) is a common presenting dysrhythmia in the setting of cardiac arrest whose main treatment is defibrillation through direct current countershock to achieve return of spontaneous circulation. However, often...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2012-10-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | http://www.biomedcentral.com/1472-6947/12/116 |
| _version_ | 1818806146209677312 |
|---|---|
| author | Shandilya Sharad Ward Kevin Kurz Michael Najarian Kayvan |
| author_facet | Shandilya Sharad Ward Kevin Kurz Michael Najarian Kayvan |
| author_sort | Shandilya Sharad |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>Ventricular Fibrillation (VF) is a common presenting dysrhythmia in the setting of cardiac arrest whose main treatment is defibrillation through direct current countershock to achieve return of spontaneous circulation. However, often defibrillation is unsuccessful and may even lead to the transition of VF to more nefarious rhythms such as asystole or pulseless electrical activity. Multiple methods have been proposed for predicting defibrillation success based on examination of the VF waveform. To date, however, no analytical technique has been widely accepted. We developed a unique approach of computational VF waveform analysis, with and without addition of the signal of end-tidal carbon dioxide (PetCO2), using advanced machine learning algorithms. We compare these results with those obtained using the Amplitude Spectral Area (AMSA) technique.</p> <p>Methods</p> <p>A total of 90 pre-countershock ECG signals were analyzed form an accessible preshosptial cardiac arrest database. A unified predictive model, based on signal processing and machine learning, was developed with time-series and dual-tree complex wavelet transform features. Upon selection of correlated variables, a parametrically optimized support vector machine (SVM) model was trained for predicting outcomes on the test sets. Training and testing was performed with nested 10-fold cross validation and 6–10 features for each test fold.</p> <p>Results</p> <p>The integrative model performs real-time, short-term (7.8 second) analysis of the Electrocardiogram (ECG). For a total of 90 signals, 34 successful and 56 unsuccessful defibrillations were classified with an average Accuracy and Receiver Operator Characteristic (ROC) Area Under the Curve (AUC) of 82.2% and 85%, respectively. Incorporation of the end-tidal carbon dioxide signal boosted Accuracy and ROC AUC to 83.3% and 93.8%, respectively, for a smaller dataset containing 48 signals. VF analysis using AMSA resulted in accuracy and ROC AUC of 64.6% and 60.9%, respectively.</p> <p>Conclusion</p> <p>We report the development and first-use of a nontraditional non-linear method of analyzing the VF ECG signal, yielding high predictive accuracies of defibrillation success. Furthermore, incorporation of features from the PetCO2 signal noticeably increased model robustness. These predictive capabilities should further improve with the availability of a larger database.</p> |
| first_indexed | 2024-12-18T19:05:08Z |
| format | Article |
| id | doaj.art-89fb1ace8c1e48889c5704af8df1ba42 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-18T19:05:08Z |
| publishDate | 2012-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-89fb1ace8c1e48889c5704af8df1ba422022-12-21T20:56:27ZengBMCBMC Medical Informatics and Decision Making1472-69472012-10-0112111610.1186/1472-6947-12-116Non-linear dynamical signal characterization for prediction of defibrillation success through machine learningShandilya SharadWard KevinKurz MichaelNajarian Kayvan<p>Abstract</p> <p>Background</p> <p>Ventricular Fibrillation (VF) is a common presenting dysrhythmia in the setting of cardiac arrest whose main treatment is defibrillation through direct current countershock to achieve return of spontaneous circulation. However, often defibrillation is unsuccessful and may even lead to the transition of VF to more nefarious rhythms such as asystole or pulseless electrical activity. Multiple methods have been proposed for predicting defibrillation success based on examination of the VF waveform. To date, however, no analytical technique has been widely accepted. We developed a unique approach of computational VF waveform analysis, with and without addition of the signal of end-tidal carbon dioxide (PetCO2), using advanced machine learning algorithms. We compare these results with those obtained using the Amplitude Spectral Area (AMSA) technique.</p> <p>Methods</p> <p>A total of 90 pre-countershock ECG signals were analyzed form an accessible preshosptial cardiac arrest database. A unified predictive model, based on signal processing and machine learning, was developed with time-series and dual-tree complex wavelet transform features. Upon selection of correlated variables, a parametrically optimized support vector machine (SVM) model was trained for predicting outcomes on the test sets. Training and testing was performed with nested 10-fold cross validation and 6–10 features for each test fold.</p> <p>Results</p> <p>The integrative model performs real-time, short-term (7.8 second) analysis of the Electrocardiogram (ECG). For a total of 90 signals, 34 successful and 56 unsuccessful defibrillations were classified with an average Accuracy and Receiver Operator Characteristic (ROC) Area Under the Curve (AUC) of 82.2% and 85%, respectively. Incorporation of the end-tidal carbon dioxide signal boosted Accuracy and ROC AUC to 83.3% and 93.8%, respectively, for a smaller dataset containing 48 signals. VF analysis using AMSA resulted in accuracy and ROC AUC of 64.6% and 60.9%, respectively.</p> <p>Conclusion</p> <p>We report the development and first-use of a nontraditional non-linear method of analyzing the VF ECG signal, yielding high predictive accuracies of defibrillation success. Furthermore, incorporation of features from the PetCO2 signal noticeably increased model robustness. These predictive capabilities should further improve with the availability of a larger database.</p>http://www.biomedcentral.com/1472-6947/12/116Cardiac arrestResuscitationVentricular fibrillationCPRDefibrillation successShock outcomeComplex wavelet transformNon-linear analysisTime-series analysisSignal decompositionFeature selection |
| spellingShingle | Shandilya Sharad Ward Kevin Kurz Michael Najarian Kayvan Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning BMC Medical Informatics and Decision Making Cardiac arrest Resuscitation Ventricular fibrillation CPR Defibrillation success Shock outcome Complex wavelet transform Non-linear analysis Time-series analysis Signal decomposition Feature selection |
| title | Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| title_full | Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| title_fullStr | Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| title_full_unstemmed | Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| title_short | Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| title_sort | non linear dynamical signal characterization for prediction of defibrillation success through machine learning |
| topic | Cardiac arrest Resuscitation Ventricular fibrillation CPR Defibrillation success Shock outcome Complex wavelet transform Non-linear analysis Time-series analysis Signal decomposition Feature selection |
| url | http://www.biomedcentral.com/1472-6947/12/116 |
| work_keys_str_mv | AT shandilyasharad nonlineardynamicalsignalcharacterizationforpredictionofdefibrillationsuccessthroughmachinelearning AT wardkevin nonlineardynamicalsignalcharacterizationforpredictionofdefibrillationsuccessthroughmachinelearning AT kurzmichael nonlineardynamicalsignalcharacterizationforpredictionofdefibrillationsuccessthroughmachinelearning AT najariankayvan nonlineardynamicalsignalcharacterizationforpredictionofdefibrillationsuccessthroughmachinelearning |