Ensemble learning of colorectal cancer survival rates

In this paper, we describe a dataset relating to cellular and physical conditions of patients who are operated upon to remove colorectal tumours. This data provides a unique insight into immunological status at the point of tumour removal, tumour classification and post-operative survival. We build...

Full description

Bibliographic Details
Main Authors: Roadknight, Chris, Aickelin, Uwe, Scholefield, John, Durrant, Lindy
Format: Conference or Workshop Item
Published: 2013
Subjects:
Online Access:https://eprints.nottingham.ac.uk/3344/
_version_ 1848801177158811648
author Roadknight, Chris
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
author_facet Roadknight, Chris
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
author_sort Roadknight, Chris
building Nottingham Research Data Repository
collection Online Access
description In this paper, we describe a dataset relating to cellular and physical conditions of patients who are operated upon to remove colorectal tumours. This data provides a unique insight into immunological status at the point of tumour removal, tumour classification and post-operative survival. We build on existing research on clustering and machine learning facets of this data to demonstrate a role for an ensemble approach to highlighting patients with clearer prognosis parameters. Results for survival prediction using 3 different approaches are shown for a subset of the data which is most difficult to model. The performance of each model individually is compared with subsets of the data where some agreement is reached for multiple models. Significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved.
first_indexed 2025-11-14T18:21:38Z
format Conference or Workshop Item
id nottingham-3344
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T21:03:18Z
publishDate 2013
recordtype eprints
repository_type Digital Repository
spelling nottingham-33442025-09-09T14:57:22Z https://eprints.nottingham.ac.uk/3344/ Ensemble learning of colorectal cancer survival rates Roadknight, Chris Aickelin, Uwe Scholefield, John Durrant, Lindy In this paper, we describe a dataset relating to cellular and physical conditions of patients who are operated upon to remove colorectal tumours. This data provides a unique insight into immunological status at the point of tumour removal, tumour classification and post-operative survival. We build on existing research on clustering and machine learning facets of this data to demonstrate a role for an ensemble approach to highlighting patients with clearer prognosis parameters. Results for survival prediction using 3 different approaches are shown for a subset of the data which is most difficult to model. The performance of each model individually is compared with subsets of the data where some agreement is reached for multiple models. Significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved. 2013-09 Conference or Workshop Item PeerReviewed Roadknight, Chris, Aickelin, Uwe, Scholefield, John and Durrant, Lindy (2013) Ensemble learning of colorectal cancer survival rates. In: IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) 2013, 15-17 July 2013, Milan, Italy. Biomedical Informatics http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6617400
spellingShingle Biomedical
Informatics
Roadknight, Chris
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
Ensemble learning of colorectal cancer survival rates
title Ensemble learning of colorectal cancer survival rates
title_full Ensemble learning of colorectal cancer survival rates
title_fullStr Ensemble learning of colorectal cancer survival rates
title_full_unstemmed Ensemble learning of colorectal cancer survival rates
title_short Ensemble learning of colorectal cancer survival rates
title_sort ensemble learning of colorectal cancer survival rates
topic Biomedical
Informatics
url https://eprints.nottingham.ac.uk/3344/
https://eprints.nottingham.ac.uk/3344/