Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context
Summary: Background: Ventricular arrhythmia (VA) precipitating sudden cardiac arrest (SCD) is among the most frequent causes of death and pose a high burden on public health systems worldwide. The increasing availability of electrophysiological signals collected through conventional methods (e.g. e...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-03-01
|
Series: | EBioMedicine |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396423000270 |
_version_ | 1811166394078724096 |
---|---|
author | Maarten Z.H. Kolk Brototo Deb Samuel Ruipérez-Campillo Neil K. Bhatia Paul Clopton Arthur A.M. Wilde Sanjiv M. Narayan Reinoud E. Knops Fleur V.Y. Tjong |
author_facet | Maarten Z.H. Kolk Brototo Deb Samuel Ruipérez-Campillo Neil K. Bhatia Paul Clopton Arthur A.M. Wilde Sanjiv M. Narayan Reinoud E. Knops Fleur V.Y. Tjong |
author_sort | Maarten Z.H. Kolk |
collection | DOAJ |
description | Summary: Background: Ventricular arrhythmia (VA) precipitating sudden cardiac arrest (SCD) is among the most frequent causes of death and pose a high burden on public health systems worldwide. The increasing availability of electrophysiological signals collected through conventional methods (e.g. electrocardiography (ECG)) and digital health technologies (e.g. wearable devices) in combination with novel predictive analytics using machine learning (ML) and deep learning (DL) hold potential for personalised predictions of arrhythmic events. Methods: This systematic review and exploratory meta-analysis assesses the state-of-the-art of ML/DL models of electrophysiological signals for personalised prediction of malignant VA or SCD, and studies potential causes of bias (PROSPERO, reference: CRD42021283464). Five electronic databases were searched to identify eligible studies. Pooled estimates of the diagnostic odds ratio (DOR) and summary area under the curve (AUROC) were calculated. Meta-analyses were performed separately for studies using publicly available, ad-hoc datasets, versus targeted clinical data acquisition. Studies were scored on risk of bias by the PROBAST tool. Findings: 2194 studies were identified of which 46 were included in the systematic review and 32 in the meta-analysis. Pooling of individual models demonstrated a summary AUROC of 0.856 (95% CI 0.755–0.909) for short-term (time-to-event up to 72 h) prediction and AUROC of 0.876 (95% CI 0.642–0.980) for long-term prediction (time-to-event up to years). While models developed on ad-hoc sets had higher pooled performance (AUROC 0.919, 95% CI 0.867–0.952), they had a high risk of bias related to the re-use and overlap of small ad-hoc datasets, choices of ML tool and a lack of external model validation. Interpretation: ML and DL models appear to accurately predict malignant VA and SCD. However, wide heterogeneity between studies, in part due to small ad-hoc datasets and choice of ML model, may reduce the ability to generalise and should be addressed in future studies. Funding: This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T). |
first_indexed | 2024-04-10T15:51:37Z |
format | Article |
id | doaj.art-5067b091085c4144a024e7a86cdce2c7 |
institution | Directory Open Access Journal |
issn | 2352-3964 |
language | English |
last_indexed | 2024-04-10T15:51:37Z |
publishDate | 2023-03-01 |
publisher | Elsevier |
record_format | Article |
series | EBioMedicine |
spelling | doaj.art-5067b091085c4144a024e7a86cdce2c72023-02-11T04:15:46ZengElsevierEBioMedicine2352-39642023-03-0189104462Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in contextMaarten Z.H. Kolk0Brototo Deb1Samuel Ruipérez-Campillo2Neil K. Bhatia3Paul Clopton4Arthur A.M. Wilde5Sanjiv M. Narayan6Reinoud E. Knops7Fleur V.Y. Tjong8Amsterdam UMC Location University of Amsterdam, Heart Center, Department of Clinical and Experimental Cardiology, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart failure & arrhythmias, Amsterdam, The NetherlandsDepartment of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USADepartment of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USADepartment of Cardiology, Emory University, Atlanta, GA, USADepartment of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USAAmsterdam UMC Location University of Amsterdam, Heart Center, Department of Clinical and Experimental Cardiology, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart failure & arrhythmias, Amsterdam, The NetherlandsDepartment of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USAAmsterdam UMC Location University of Amsterdam, Heart Center, Department of Clinical and Experimental Cardiology, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart failure & arrhythmias, Amsterdam, The NetherlandsAmsterdam UMC Location University of Amsterdam, Heart Center, Department of Clinical and Experimental Cardiology, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart failure & arrhythmias, Amsterdam, The Netherlands; Corresponding author. Heart Center, University of Amsterdam, Amsterdam, 1105 AZ, the Netherlands.Summary: Background: Ventricular arrhythmia (VA) precipitating sudden cardiac arrest (SCD) is among the most frequent causes of death and pose a high burden on public health systems worldwide. The increasing availability of electrophysiological signals collected through conventional methods (e.g. electrocardiography (ECG)) and digital health technologies (e.g. wearable devices) in combination with novel predictive analytics using machine learning (ML) and deep learning (DL) hold potential for personalised predictions of arrhythmic events. Methods: This systematic review and exploratory meta-analysis assesses the state-of-the-art of ML/DL models of electrophysiological signals for personalised prediction of malignant VA or SCD, and studies potential causes of bias (PROSPERO, reference: CRD42021283464). Five electronic databases were searched to identify eligible studies. Pooled estimates of the diagnostic odds ratio (DOR) and summary area under the curve (AUROC) were calculated. Meta-analyses were performed separately for studies using publicly available, ad-hoc datasets, versus targeted clinical data acquisition. Studies were scored on risk of bias by the PROBAST tool. Findings: 2194 studies were identified of which 46 were included in the systematic review and 32 in the meta-analysis. Pooling of individual models demonstrated a summary AUROC of 0.856 (95% CI 0.755–0.909) for short-term (time-to-event up to 72 h) prediction and AUROC of 0.876 (95% CI 0.642–0.980) for long-term prediction (time-to-event up to years). While models developed on ad-hoc sets had higher pooled performance (AUROC 0.919, 95% CI 0.867–0.952), they had a high risk of bias related to the re-use and overlap of small ad-hoc datasets, choices of ML tool and a lack of external model validation. Interpretation: ML and DL models appear to accurately predict malignant VA and SCD. However, wide heterogeneity between studies, in part due to small ad-hoc datasets and choice of ML model, may reduce the ability to generalise and should be addressed in future studies. Funding: This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).http://www.sciencedirect.com/science/article/pii/S2352396423000270CardiologyArtificial intelligenceElectrocardiographySystematic reviewMeta-analysisMachine Learning |
spellingShingle | Maarten Z.H. Kolk Brototo Deb Samuel Ruipérez-Campillo Neil K. Bhatia Paul Clopton Arthur A.M. Wilde Sanjiv M. Narayan Reinoud E. Knops Fleur V.Y. Tjong Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context EBioMedicine Cardiology Artificial intelligence Electrocardiography Systematic review Meta-analysis Machine Learning |
title | Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context |
title_full | Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context |
title_fullStr | Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context |
title_full_unstemmed | Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context |
title_short | Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studiesResearch in context |
title_sort | machine learning of electrophysiological signals for the prediction of ventricular arrhythmias systematic review and examination of heterogeneity between studiesresearch in context |
topic | Cardiology Artificial intelligence Electrocardiography Systematic review Meta-analysis Machine Learning |
url | http://www.sciencedirect.com/science/article/pii/S2352396423000270 |
work_keys_str_mv | AT maartenzhkolk machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT brototodeb machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT samuelruiperezcampillo machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT neilkbhatia machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT paulclopton machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT arthuramwilde machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT sanjivmnarayan machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT reinoudeknops machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext AT fleurvytjong machinelearningofelectrophysiologicalsignalsforthepredictionofventriculararrhythmiassystematicreviewandexaminationofheterogeneitybetweenstudiesresearchincontext |