Combining Statistical Learning with a Knowledge-Based Approach - A Case Study in Intensive Care Monitoring
Abstract
The paper describes a case study in combining different methods for acquiring medical knowledge. Given a huge amount of noisy, high dimensional numerical time series data describing patients in intensive care, the support vector machine is used to learn when and how to change the dose of which drug. Given medical knowledge about and expertise in clinical decision making, a first-order logic knowledge base about effects of therapeutical interventions has been built. As a preprocessing mechanism it uses another statistical method. The integration of numerical and knowledge-based procedures eases the task of validation in two ways. On one hand, the knowledge base is validated with respect to past patients' records. On the other hand, medical interventions that are recommended by learning results are justified by the knowledge base.
Cite
Text
Morik et al. "Combining Statistical Learning with a Knowledge-Based Approach - A Case Study in Intensive Care Monitoring." International Conference on Machine Learning, 1999. doi:10.17877/DE290R-3088Markdown
[Morik et al. "Combining Statistical Learning with a Knowledge-Based Approach - A Case Study in Intensive Care Monitoring." International Conference on Machine Learning, 1999.](https://mlanthology.org/icml/1999/morik1999icml-combining/) doi:10.17877/DE290R-3088BibTeX
@inproceedings{morik1999icml-combining,
title = {{Combining Statistical Learning with a Knowledge-Based Approach - A Case Study in Intensive Care Monitoring}},
author = {Morik, Katharina and Brockhausen, Peter and Joachims, Thorsten},
booktitle = {International Conference on Machine Learning},
year = {1999},
pages = {268-277},
doi = {10.17877/DE290R-3088},
url = {https://mlanthology.org/icml/1999/morik1999icml-combining/}
}