Abstract
Intensive care units are complex, data-rich healthcare environments which provide substantial opportunities for applications in machine learning. While certain solutions can be derived directly from data, complex problems require additional human input provided in the form of data annotations. Due to the large size and complexities associated with healthcare data, the existing software packages for time-series data annotation are infeasible for effective use in the clinical setting and frequently require significant time commitments and technical expertise.
Our software provides a comprehensive, end-to-end solution to the time-series data annotation and proposes a novel approach for a semi-automated annotation in the cloud. It allows for conducting large-scale, asynchronous data annotation activities across multiple, geographically distributed users. The adoption of our software could benefit the wider research community by enhancing existing datasets, creating novel avenues for research that uses them and allowing for meaningful data annotation within smaller and highly specialised populations.
Our software provides a comprehensive, end-to-end solution to the time-series data annotation and proposes a novel approach for a semi-automated annotation in the cloud. It allows for conducting large-scale, asynchronous data annotation activities across multiple, geographically distributed users. The adoption of our software could benefit the wider research community by enhancing existing datasets, creating novel avenues for research that uses them and allowing for meaningful data annotation within smaller and highly specialised populations.
| Original language | English |
|---|---|
| Article number | 101593 |
| Journal | SoftwareX |
| Volume | 24 |
| DOIs | |
| Publication status | Published - 27 Nov 2023 |
Bibliographical note
Funding Information:This work was partly supported by the Engineering and Physical Sciences Research Council Digital Health and Care Centre for Doctoral Training at the University of Bristol, United Kingdom (UKRI grant EP/S023704/1 to MW). RSR is supported by the UKRI Turing AI Fellowship EP/V024817/1 , United Kingdom. The project received an AWS Cloud Credit for Research grant.
Publisher Copyright:
© 2023 The Authors