Key result
Machine learning predicts short-term ventricular arrhythmias with ~21-fold higher diagnostic odds.
Why the study?
Increasing electrophysiological signal availability combined with machine learning holds potential for personalized arrhythmia predictions, but state-of-the-art model performance and potential bias required assessment.
Does machine learning of electrophysiological signals accurately predict malignant ventricular arrhythmias and sudden cardiac death?
Meta-Analysis
Does machine learning of electrophysiological signals accurately predict malignant ventricular arrhythmias and sudden cardiac death?
While machine learning models applied to electrophysiological signals demonstrate high theoretical accuracy for predicting malignant ventricular arrhythmias, clinical implementation is currently hindered by methodological flaws, reliance on non-representative datasets, and a lack of external validation.
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).
No takes yet. Share an insight, caveat, or question.
Kolk et al. (2023) conducted a meta-analysis in Malignant ventricular arrhythmias and sudden cardiac death. Machine learning and deep learning of electrophysiological signals was evaluated on Short-term prediction (time-to-event up to 72 hours) of malignant ventricular arrhythmia or sudden cardiac death (DOR 21.45, 95% CI 11.42-40.29). Machine learning and deep learning models accurately predicted short-term malignant ventricular arrhythmias and sudden cardiac death, demonstrating a pooled diagnostic odds ratio of 21.45 and a summary AUROC of 0.856.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: