Open Science to Foster Progress in Automatic ECG Analysis: Status and Future Directions

Recently, there has been a significant increase in the availability of publicly accessible ECG datasets.These datasets have been used in thousands of research works, showcasing their profound impact on the research landscape.However, despite their widespread use, many currently available public datasets lack certain crucial components.These include the absence of high-quality expert annotations based on standardized ontologies or mapping schemes to facilitate comparisons across datasets.Additionally, there is a need for enriched metadata, such as ECG features or automatic diagnostic statements, to improve their usability and interoperability.Nevertheless, the most glaring shortfall of current publicly available datasets is the absence of clinical ground truth.This deficiency prevents the broader research community from replicating and expanding upon literature works based on closed in-hospital datasets, which impedes scientific progress.In this paper, we trace the recent history on publicly available ECG datasets and discuss possible directions for the enrichment of existing datasets.We close with a possible path towards ECG datasets with clinical ground truth based on recent work in the context of the MIMIC-IV-ECG dataset.