Machine learning models to predict 30-day mortality for critical patients with myocardial infarction: a retrospective analysis from MIMIC-IV database
The ML-based predictive model demonstrated significant efficacy in forecasting 30-day mortality among MI patients admitted to the CCU. The prognostic factors identified were age, blood urea nitrogen, heart rate, pulse oximetry-derived oxygen saturation, bicarbonate, and metoprolol use. This model serves as a valuable decision-making tool for clinicians.
Authors
- Pei Yu
- Jiaming Xiu
- Haichuan Lu
- Xuping Lin (ORCID: https://orcid.org/0000-0003-4149-0125)
- Yukun Zhao (ORCID: https://orcid.org/0000-0003-1611-6588)
- Jin Lü (ORCID: https://orcid.org/0000-0002-1192-9021)
- Wencheng Yang (ORCID: https://orcid.org/0000-0003-2423-2853)
- Yanfang Yang (ORCID: https://orcid.org/0000-0001-7097-794X)
- Xiaomeng Wang
- Xi Pan
- Kaiwei Zou
- Yizhang Wang
Institutions
- Fujian Medical University (CN)
- Longyan University (CN)
- First Affiliated Hospital of Fujian Medical University (CN)
- Zhongshan Hospital of Xiamen University (CN)
- Second Affiliated Hospital of Zhejiang University (CN)
Publication Details
- Journal
- Frontiers in Cardiovascular Medicine
- Published
- 2024-09-20
- DOI
- https://doi.org/10.3389/fcvm.2024.1368022
- Citations
- 11
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.32