Early Prediction of Cardiac Arrest in the Intensive Care Unit Using Explainable Machine Learning: Retrospective Study
Our novel framework for learning unique features provides stable predictive power across different ICU environments. Most of the interpretable global information reveals statistical differences between CA and non-CA groups, demonstrating its utility as an indicator for clinical decisions. Consequently, the proposed CA prediction system is a clinically validated algorithm that enables clinicians to intervene early based on CA prediction information and can be applied to clinical trials in digital health.
Authors
- Ja Hyung Koo (ORCID: https://orcid.org/0000-0001-5904-3652)
- Yun Kwan Kim (ORCID: https://orcid.org/0000-0002-6397-4043)
- Sun Jung Lee (ORCID: https://orcid.org/0000-0002-1087-2051)
- Hee Seok Song (ORCID: https://orcid.org/0000-0003-3794-8033)
- Won-Doo Seo (ORCID: https://orcid.org/0000-0001-8944-4262)
- Minji Lee (ORCID: https://orcid.org/0000-0003-4261-875X)
- Gyung Chul Kim (ORCID: https://orcid.org/0009-0003-8384-040X)
Institutions
- Korea University (KR)
- Catholic University of Korea (KR)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-09-17
- DOI
- https://doi.org/10.2196/62890
- Citations
- 19
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 6.60