Title :
An Investigation Into Feature Selection for Oncological Survival Prediction
Author :
Strunkin, Dmitry ; Namee, Brian Mac ; Kelleher, John D.
Author_Institution :
Appl. Math. & Inf. Dept., Kazan State Tech. Univ., Kazan, Russia
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 :
cancer; decision support systems; feature extraction; learning (artificial intelligence); medical expert systems; medical information systems; CDS systems; accurate models; clinical decision support system; domain experts; feature extraction; feature selection; feature sets; machine learning; oncological survival prediction application scenario; structured expert-designed features; train prediction models; unstructured data sources; Accuracy; Data models; Decision trees; Feature extraction; Machine learning; Medical diagnostic imaging; Predictive models; feature selection; machine learning; oncology;
Conference_Titel :
Information Technology: New Generations (ITNG), 2012 Ninth International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4673-0798-7
DOI :
10.1109/ITNG.2012.148