Identifying Heart Failure in ECG Data With Artificial Intelligence-A Meta-Analysis

Abstract

Introduction: Electrocardiography (ECG) is a quick and easily accessible method for diagnosis and screening of cardiovascular diseases including heart failure (HF). Artificial intelligence (AI) can be used for semi-automated ECG analysis. The aim of this evaluation was to provide an overview of AI use in HF detection from ECG signals and to perform a meta-analysis of available studies. Methods and Results: An independent comprehensive search of the PubMed and Google Scholar database was conducted for articles dealing with the ability of AI to predict HF based on ECG signals. Only original articles published in peer-reviewed journals were considered. A total of five reports including 57,027 patients and 579,134 ECG datasets were identified including two sets of patient-level data and three with ECG-based datasets. The AI-processed ECG data yielded areas under the receiver operator characteristics curves between 0.92 and 0.99 to identify HF with higher values in ECG-based datasets. Applying a random-effects model, an sROC of 0.987 was calculated. Using the contingency tables led to diagnostic odds ratios ranging from 3.44 [95% confidence interval (CI) = 3.12-3.76] to 13.61 (95% CI = 13.14-14.08) also with lower values in patient-level datasets. The meta-analysis diagnostic odds ratio was 7.59 (95% CI = 5.85-9.34). Conclusions: The present meta-analysis confirms the ability of AI to predict HF from standard 12-lead ECG signals underlining the potential of such an approach. The observed overestimation of the diagnostic ability in artificial ECG databases compared to patient-level data stipulate the need for robust prospective studies.

Keywords: ECG; artificial intelligence; diagnosis; heart failure; meta-analysis.

Figure 1

Flowchart summarizing the literature screening and study selection process.

Figure 2

Forest plot of the selected studies showing the ability to identify heart failure using artificial intelligence–processed ECG data. Data presented as a univariate analysis using a random-effects model with diagnostic odds ratio after natural logarithmic transformation (lnDOR) with respective confidence interval (CI).

Figure 3

Cumulative summary receiver operating characteristic curve (sROC) of an artificial intelligence–processed ECG approach to detect heart failure. Individual studies are shown as gray circles. Summary point is shown as red triangle. The area of interest is magnified on the right side. lnDOR denotes diagnostic odds ratio after natural logarithmic transformation, sAUROC denotes area under the sROC curve; CI, confidence interval.