Routine Laboratory Tests Predict 72‐h Fatality in Patients With D‐Dimer Levels ≥ 2 μg/<scp>mL</scp>: A Retrospective Cohort Study Comparing Statistical and Machine Learning Models
ML models, particularly LightGBM, effectively identify high-risk patients using routine laboratory tests. The model enables timely decision-making and early risk stratification in patients with high D-dimer values, even when clinical information is limited.
Authors
- Hitoshi Sugawara (ORCID: https://orcid.org/0000-0002-5060-9020)
- Hidenori Sanayama (ORCID: https://orcid.org/0000-0002-8225-7365)
- Kiyoka Omoto (ORCID: https://orcid.org/0000-0002-6324-3726)
- Takahiko Fukuchi (ORCID: https://orcid.org/0000-0001-6192-1653)
- Shizuo HAYASHI
- Kai Saito (ORCID: https://orcid.org/0000-0002-4167-527X)
- Tamami Watanabe (ORCID: https://orcid.org/0000-0002-0649-8810)
- Kayoko Nakamura
- R. Hayashi
Institutions
- Jichi Medical University (JP)
- Jichi Medical University Saitama Medical Center (JP)
Publication Details
- Journal
- Journal of Clinical Laboratory Analysis
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1002/jcla.70091
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- CSL Behring
- Otsuka Pharmaceutical
- Japan Society for the Promotion of Science
- Daiichi Sankyo Company
- Daiichi Sankyo Europe