Developing a Scalable Annotation Method for Large Datasets That Enhances Alarms With Actionability Data to Increase Informativeness: Mixed Methods Approach
Our annotation method will enable a large number of alarms to be labeled semiautomatically, retrospectively, and quickly, and will provide information on their actionability based on further patient data. This will make it possible to generate annotated datasets for ML models in alarm management and alarm fatigue research. We believe that our annotation method and the resources provided are universal enough and could be used by others to prepare data for future ML projects, even beyond the topic of alarms.
Authors
- Anne Rike Flint (ORCID: https://orcid.org/0000-0002-1414-5812)
- Amin Chaoui (ORCID: https://orcid.org/0000-0002-2527-4783)
- Patrick Heeren (ORCID: https://orcid.org/0000-0001-9356-2296)
- Jonas Chromik (ORCID: https://orcid.org/0000-0002-5709-4381)
- Akira-Sebastian Poncette (ORCID: https://orcid.org/0000-0003-4627-7016)
- Thomas Ocker
- Mona Prendke (ORCID: https://orcid.org/0000-0003-0602-9691)
- Bert Arnrich (ORCID: https://orcid.org/0000-0001-8380-7667)
- Felix Balzer (ORCID: https://orcid.org/0000-0003-1575-2056)
- Sophie Anne Inès Klopfenstein (ORCID: https://orcid.org/0000-0002-8470-2258)
Institutions
- Hasso Plattner Institute (DE)
- Humboldt-Universität zu Berlin (DE)
- Einstein Center Digital Future (DE)
- Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-02-05
- DOI
- https://doi.org/10.2196/65961
- Citations
- 3
- Primary Topic
- Healthcare Technology and Patient Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 6.02