Ghent University Academic Bibliography

Advanced

Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy

K Jayasurya, G Fung, S Yu, C Dehing-Oberije, D De Ruysscher, A Hope, Wilfried De Neve UGent, Y Lievens, P Lambin and ALAJ Dekker (2010) MEDICAL PHYSICS. 37(4). p.1401-1407
abstract
Purpose: Classic statistical and machine learning models such as support vector machines (SVMs) can be used to predict cancer outcome, but often only perform well if all the input variables are known, which is unlikely in the medical domain. Bayesian network (BN) models have a natural ability to reason under uncertainty and might handle missing data better. In this study, the authors hypothesize that a BN model can predict two-year survival in non-small cell lung cancer (NSCLC) patients as accurately as SVM, but will predict survival more accurately when data are missing. Methods: A BN and SVM model were trained on 322 inoperable NSCLC patients treated with radiotherapy from Maastricht and validated in three independent data sets of 35, 47, and 33 patients from Ghent, Leuven, and Toronto. Missing variables occurred in the data set with only 37, 28, and 24 patients having a complete data set. Results: The BN model structure and parameter learning identified gross tumor volume size, performance status, and number of positive lymph nodes on a PET as prognostic factors for two-year survival. When validated in the full validation set of Ghent, Leuven, and Toronto, the BN model had an AUC of 0.77, 0.72, and 0.70, respectively. A SVM model based on the same variables had an overall worse performance (AUC 0.71, 0.68, and 0.69) especially in the Ghent set, which had the highest percentage of missing the important GTV size data. When only patients with complete data sets were considered, the BN and SVM model performed more alike. Conclusions: Within the limitations of this study, the hypothesis is supported that BN models are better at handling missing data than SVM models and are therefore more suitable for the medical domain. Future works have to focus on improving the BN performance by including more patients, more variables, and more diversity.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
CLASSIFICATION, STAGE, MISSING VALUES, PROGNOSTIC-FACTORS, RADIATION-INDUCED PNEUMONITIS, tumours, support vector machines, radiation therapy, positron emission tomography, parameter estimation, lung, learning (artificial intelligence), cancer, belief networks
journal title
MEDICAL PHYSICS
Med. Phys.
volume
37
issue
4
pages
1401 - 1407
Web of Science type
Article
Web of Science id
000276211200004
JCR category
RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
JCR impact factor
3.07 (2010)
JCR rank
27/111 (2010)
JCR quartile
1 (2010)
ISSN
0094-2405
DOI
10.1118/1.3352709
language
English
UGent publication?
yes
classification
A1
copyright statement
I have transferred the copyright for this publication to the publisher
id
1850306
handle
http://hdl.handle.net/1854/LU-1850306
date created
2011-06-30 18:43:17
date last changed
2011-07-05 09:50:30
@article{1850306,
  abstract     = {Purpose: Classic statistical and machine learning models such as support vector machines (SVMs) can be used to predict cancer outcome, but often only perform well if all the input variables are known, which is unlikely in the medical domain. Bayesian network (BN) models have a natural ability to reason under uncertainty and might handle missing data better. In this study, the authors hypothesize that a BN model can predict two-year survival in non-small cell lung cancer (NSCLC) patients as accurately as SVM, but will predict survival more accurately when data are missing.
Methods: A BN and SVM model were trained on 322 inoperable NSCLC patients treated with radiotherapy from Maastricht and validated in three independent data sets of 35, 47, and 33 patients from Ghent, Leuven, and Toronto. Missing variables occurred in the data set with only 37, 28, and 24 patients having a complete data set.
Results: The BN model structure and parameter learning identified gross tumor volume size, performance status, and number of positive lymph nodes on a PET as prognostic factors for two-year survival. When validated in the full validation set of Ghent, Leuven, and Toronto, the BN model had an AUC of 0.77, 0.72, and 0.70, respectively. A SVM model based on the same variables had an overall worse performance (AUC 0.71, 0.68, and 0.69) especially in the Ghent set, which had the highest percentage of missing the important GTV size data. When only patients with complete data sets were considered, the BN and SVM model performed more alike.
Conclusions: Within the limitations of this study, the hypothesis is supported that BN models are better at handling missing data than SVM models and are therefore more suitable for the medical domain. Future works have to focus on improving the BN performance by including more patients, more variables, and more diversity.},
  author       = {Jayasurya, K and Fung , G  and Yu, S and Dehing-Oberije , C  and De Ruysscher, D and Hope, A and De Neve, Wilfried and Lievens, Y and Lambin , P and Dekker, ALAJ},
  issn         = {0094-2405},
  journal      = {MEDICAL PHYSICS},
  keyword      = {CLASSIFICATION,STAGE,MISSING VALUES,PROGNOSTIC-FACTORS,RADIATION-INDUCED PNEUMONITIS,tumours,support vector machines,radiation therapy,positron emission tomography,parameter estimation,lung,learning (artificial intelligence),cancer,belief networks},
  language     = {eng},
  number       = {4},
  pages        = {1401--1407},
  title        = {Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy},
  url          = {http://dx.doi.org/10.1118/1.3352709},
  volume       = {37},
  year         = {2010},
}

Chicago
Jayasurya, K, G Fung , S Yu, C Dehing-Oberije , D De Ruysscher, A Hope, Wilfried De Neve, Y Lievens, P Lambin , and ALAJ Dekker. 2010. “Comparison of Bayesian Network and Support Vector Machine Models for Two-year Survival Prediction in Lung Cancer Patients Treated with Radiotherapy.” Medical Physics 37 (4): 1401–1407.
APA
Jayasurya, K., Fung , G., Yu, S., Dehing-Oberije , C., De Ruysscher, D., Hope, A., De Neve, W., et al. (2010). Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. MEDICAL PHYSICS, 37(4), 1401–1407.
Vancouver
1.
Jayasurya K, Fung G, Yu S, Dehing-Oberije C, De Ruysscher D, Hope A, et al. Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. MEDICAL PHYSICS. 2010;37(4):1401–7.
MLA
Jayasurya, K, G Fung , S Yu, et al. “Comparison of Bayesian Network and Support Vector Machine Models for Two-year Survival Prediction in Lung Cancer Patients Treated with Radiotherapy.” MEDICAL PHYSICS 37.4 (2010): 1401–1407. Print.