期刊
JOURNAL OF COMPUTATIONAL SCIENCE
卷 59, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.jocs.2022.101562
关键词
Clinical pathway; Evolutionary algorithms; Knowledge discovery; Multi-objective optimization; Parameter tuning; Predictive modeling; Surrogate modeling
资金
- Russian Science Foun-dation [19-11-00326]
- Russian Science Foundation [19-11-00326] Funding Source: Russian Science Foundation
This paper proposes and investigates an approach for surrogate-assisted performance prediction of data-driven knowledge discovery algorithms. The approach is applied to the discovery of clinical pathways and uses surrogate models to predict the quality and performance of the target algorithm. An analytical software prototype is developed to provide a more interpretable prediction of the algorithm's performance and quality.
The paper proposes and investigates an approach for surrogate-assisted performance prediction of data-driven knowledge discovery algorithms. The approach is based on the identification of surrogate models for predic-tion of the target algorithm's quality and performance. The proposed approach was implemented and investi-gated as applied to an evolutionary algorithm for discovering clusters of interpretable clinical pathways in electronic health records of patients with acute coronary syndrome. Several clustering metrics and execution time were used as the target quality and performance metrics respectively. An analytical software prototype based on the proposed approach for the prediction of algorithm characteristics and feature analysis was devel-oped to provide a more interpretable prediction of the target algorithm's performance and quality that can be further used for parameter tuning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据