@inproceedings{c90d4afb402d4e228ec9a437eb1c66ec,
title = "An investigation into feature selection for oncological survival prediction",
abstract = "In machine learning based clinical decision support (CDS) systems the features used to train prediction models are of paramount importance. Strong features will lead to accurate models, whereas as weak features will have the opposite effect. Feature sets can either be designed by domain experts, or automatically extracted for unstructured data that happens to be available from some process other than a CDS system. This paper compares the usefulness of structured expert-designed features to features extracted from unstructured data sources in an oncological survival prediction application scenario.",
keywords = "feature selection, machine learning, oncology",
author = "Dmitry Strunkin and Namee, {Brian Mac} and Kelleher, {John D.}",
year = "2012",
doi = "10.1109/ITNG.2012.148",
language = "English",
isbn = "9780769546544",
series = "Proceedings of the 9th International Conference on Information Technology, ITNG 2012",
pages = "764--768",
booktitle = "Proceedings of the 9th International Conference on Information Technology, ITNG 2012",
note = "9th International Conference on Information Technology, ITNG 2012 ; Conference date: 16-04-2012 Through 18-04-2012",
}