Improved stacking ensemble learning based on feature selection to accurately predict warfarin dose
Mingyuan Wang, Yiyi Qian, Yaodong Yang, Haobin Chen, Wei-Feng Rao · 2024
Read Improved stacking ensemble learning based on feature selection to accurately predict warfarin dose by Mingyuan Wang, Yiyi Qian, Yaodong Yang, Haobin Chen, Wei-Feng Rao (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10834785.txt.
Description
Mingyuan Wang and co-authors built a machine learning method to predict the right dose of warfarin, a blood thinner whose correct amount varies a lot between patients. Dose links to patient traits in both straight-line and curved ways, so single standard methods struggle. The team gathered records for six hundred forty-one patients in southern China who had settled on a steady dose, with details on age, history, genes, and other drugs.
Their improved stacking method, which layers several models and first picks the most useful features, beat the standard stacking version. It placed more patients at their ideal dose and cut average errors. The feature search also flagged high blood pressure and a past severe blockage event before surgery as traits linked to dose.
Catalog record
| CREATOR | Mingyuan Wang, Yiyi Qian, Yaodong Yang, Haobin Chen, Wei-Feng Rao |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |