An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates

This paper primarily addresses a dataset relating to cellular, chemical and physical conditions of patients gathered at the time they are operated upon to remove colorectal tumours. This data provides a unique insight into the biochemical and immunological status of patients at the point of tumour r...

Full description

Bibliographic Details
Main Authors: Roadknight, Chris, Suryanarayanan, Durga, Aickelin, Uwe, Scholefield, John, Durrant, Lindy
Format: Conference or Workshop Item
Published: 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/34117/
_version_ 1848794778728136704
author Roadknight, Chris
Suryanarayanan, Durga
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
author_facet Roadknight, Chris
Suryanarayanan, Durga
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
author_sort Roadknight, Chris
building Nottingham Research Data Repository
collection Online Access
description This paper primarily addresses a dataset relating to cellular, chemical and physical conditions of patients gathered at the time they are operated upon to remove colorectal tumours. This data provides a unique insight into the biochemical and immunological status of patients at the point of tumour removal along with information about tumour classification and post-operative survival. The relationship between severity of tumour, based on TNM staging, and survival is still unclear for patients with TNM stage 2 and 3 tumours. We ask whether it is possible to predict survival rate more accurately using a selection of machine learning techniques applied to subsets of data to gain a deeper understanding of the relationships between a patient’s biochemical markers and survival. We use a range of feature selection and single classification techniques to predict the 5 year survival rate of TNM stage 2 and 3 patients which initially produces less than ideal results. The performance of each model individually is then compared with subsets of the data where agreement is reached for multiple models. This novel method of selective ensembling demonstrates that significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved. Finally we point at a possible method to identify whether a patients prognosis can be accurately predicted or not.
first_indexed 2025-11-14T19:21:36Z
format Conference or Workshop Item
id nottingham-34117
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:21:36Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling nottingham-341172020-05-04T17:12:30Z https://eprints.nottingham.ac.uk/34117/ An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates Roadknight, Chris Suryanarayanan, Durga Aickelin, Uwe Scholefield, John Durrant, Lindy This paper primarily addresses a dataset relating to cellular, chemical and physical conditions of patients gathered at the time they are operated upon to remove colorectal tumours. This data provides a unique insight into the biochemical and immunological status of patients at the point of tumour removal along with information about tumour classification and post-operative survival. The relationship between severity of tumour, based on TNM staging, and survival is still unclear for patients with TNM stage 2 and 3 tumours. We ask whether it is possible to predict survival rate more accurately using a selection of machine learning techniques applied to subsets of data to gain a deeper understanding of the relationships between a patient’s biochemical markers and survival. We use a range of feature selection and single classification techniques to predict the 5 year survival rate of TNM stage 2 and 3 patients which initially produces less than ideal results. The performance of each model individually is then compared with subsets of the data where agreement is reached for multiple models. This novel method of selective ensembling demonstrates that significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved. Finally we point at a possible method to identify whether a patients prognosis can be accurately predicted or not. 2015-07-22 Conference or Workshop Item PeerReviewed Roadknight, Chris, Suryanarayanan, Durga, Aickelin, Uwe, Scholefield, John and Durrant, Lindy (2015) An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates. In: 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA 2015), 19-21 Oct 2015, Paris, France. Ensemble Bioinformatics Machine Learning http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7344863
spellingShingle Ensemble
Bioinformatics
Machine Learning
Roadknight, Chris
Suryanarayanan, Durga
Aickelin, Uwe
Scholefield, John
Durrant, Lindy
An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title_full An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title_fullStr An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title_full_unstemmed An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title_short An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
title_sort ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
topic Ensemble
Bioinformatics
Machine Learning
url https://eprints.nottingham.ac.uk/34117/
https://eprints.nottingham.ac.uk/34117/