Advanced

Finding Risk Groups by Optimizing Artificial Neural Networks on the Area under the Survival Curve Using Genetic Algorithms

Kalderstam, Jonas LU ; Edén, Patrik LU and Ohlsson, Mattias LU (2015) In PLoS ONE 10(9).
Abstract
We investigate a new method to place patients into risk groups in censored survival data. Properties such as median survival time, and end survival rate, are implicitly improved by optimizing the area under the survival curve. Artificial neural networks (ANN) are trained to either maximize or minimize this area using a genetic algorithm, and combined into an ensemble to predict one of low, intermediate, or high risk groups. Estimated patient risk can influence treatment choices, and is important for study stratification. A common approach is to sort the patients according to a prognostic index and then group them along the quartile limits. The Cox proportional hazards model (Cox) is one example of this approach. Another method of doing... (More)
We investigate a new method to place patients into risk groups in censored survival data. Properties such as median survival time, and end survival rate, are implicitly improved by optimizing the area under the survival curve. Artificial neural networks (ANN) are trained to either maximize or minimize this area using a genetic algorithm, and combined into an ensemble to predict one of low, intermediate, or high risk groups. Estimated patient risk can influence treatment choices, and is important for study stratification. A common approach is to sort the patients according to a prognostic index and then group them along the quartile limits. The Cox proportional hazards model (Cox) is one example of this approach. Another method of doing risk grouping is recursive partitioning (Rpart), which constructs a decision tree where each branch point maximizes the statistical separation between the groups. ANN, Cox, and Rpart are compared on five publicly available data sets with varying properties. Cross-validation, as well as separate test sets, are used to validate the models. Results on the test sets show comparable performance, except for the smallest data set where Rpart's predicted risk groups turn out to be inverted, an example of crossing survival curves. Cross-validation shows that all three models exhibit crossing of some survival curves on this small data set but that the ANN model manages the best separation of groups in terms of median survival time before such crossings. The conclusion is that optimizing the area under the survival curve is a viable approach to identify risk groups. Training ANNs to optimize this area combines two key strengths from both prognostic indices and Rpart. First, a desired minimum group size can be specified, as for a prognostic index. Second, the ability to utilize non-linear effects among the covariates, which Rpart is also able to do. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
PLoS ONE
volume
10
issue
9
publisher
Public Library of Science
external identifiers
  • pmid:26352405
  • wos:000360932800101
  • scopus:84944754758
ISSN
1932-6203
DOI
10.1371/journal.pone.0137597
language
English
LU publication?
yes
id
5a6c4585-fcc1-4877-80d2-706701e2c2d4 (old id 8077176)
date added to LUP
2015-10-21 11:22:11
date last changed
2017-01-01 06:29:22
@article{5a6c4585-fcc1-4877-80d2-706701e2c2d4,
  abstract     = {We investigate a new method to place patients into risk groups in censored survival data. Properties such as median survival time, and end survival rate, are implicitly improved by optimizing the area under the survival curve. Artificial neural networks (ANN) are trained to either maximize or minimize this area using a genetic algorithm, and combined into an ensemble to predict one of low, intermediate, or high risk groups. Estimated patient risk can influence treatment choices, and is important for study stratification. A common approach is to sort the patients according to a prognostic index and then group them along the quartile limits. The Cox proportional hazards model (Cox) is one example of this approach. Another method of doing risk grouping is recursive partitioning (Rpart), which constructs a decision tree where each branch point maximizes the statistical separation between the groups. ANN, Cox, and Rpart are compared on five publicly available data sets with varying properties. Cross-validation, as well as separate test sets, are used to validate the models. Results on the test sets show comparable performance, except for the smallest data set where Rpart's predicted risk groups turn out to be inverted, an example of crossing survival curves. Cross-validation shows that all three models exhibit crossing of some survival curves on this small data set but that the ANN model manages the best separation of groups in terms of median survival time before such crossings. The conclusion is that optimizing the area under the survival curve is a viable approach to identify risk groups. Training ANNs to optimize this area combines two key strengths from both prognostic indices and Rpart. First, a desired minimum group size can be specified, as for a prognostic index. Second, the ability to utilize non-linear effects among the covariates, which Rpart is also able to do.},
  articleno    = {e0137597},
  author       = {Kalderstam, Jonas and Edén, Patrik and Ohlsson, Mattias},
  issn         = {1932-6203},
  language     = {eng},
  number       = {9},
  publisher    = {Public Library of Science},
  series       = {PLoS ONE},
  title        = {Finding Risk Groups by Optimizing Artificial Neural Networks on the Area under the Survival Curve Using Genetic Algorithms},
  url          = {http://dx.doi.org/10.1371/journal.pone.0137597},
  volume       = {10},
  year         = {2015},
}