Skip to main content

Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis

Publication ,  Journal Article
Das, SK; Chen, S; Deasy, JO; Zhou, S; Yin, FF; Marks, LB
Published in: Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
December 1, 2008

Combining different machine learning models (decision fusion) has been shown to be an effective method for estimating the underlying physical mechanism by allowing the models to reinforce each other when consensus exists, or, conversely, negate each other when there is no consensus. To be effective, decision fusion requires that the different models provide some degree of complementary information. In this work, we fuse the results of four different machine learning models (Boosted Decision Trees, Neural Networks, Support Vector Machines, Self Organizing Maps) to predict the risk of lung pneumonitis in patients undergoing thoracic radiotherapy. Fusion was achieved by simple averaging of the 10-fold cross validated predictions for each patient from all four models. To reduce prediction dependence on the manner in which the data set was split, 10-fold cross-validation was repeated 100 times for random data splitting. The area under the receiver operating characteristics curve for the fused cross-validated results was 0.79, higher than the individual models and with (generally) lower variance. The fusion extracted three important features as the consensus among all four models in predicting radiation pneumonitis risk: chemotherapy prior to radiotherapy, equivalent Uniform Dose (EUD) for exponent a = 1.2 to 3, and female gender. The results show great promise for machine learning in radiotherapy outcomes modeling. © 2008 IEEE.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

DOI

Publication Date

December 1, 2008

Start / End Page

545 / 550
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Das, S. K., Chen, S., Deasy, J. O., Zhou, S., Yin, F. F., & Marks, L. B. (2008). Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis. Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008, 545–550. https://doi.org/10.1109/ICMLA.2008.122
Das, S. K., S. Chen, J. O. Deasy, S. Zhou, F. F. Yin, and L. B. Marks. “Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis.” Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008, December 1, 2008, 545–50. https://doi.org/10.1109/ICMLA.2008.122.
Das SK, Chen S, Deasy JO, Zhou S, Yin FF, Marks LB. Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis. Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008 Dec 1;545–50.
Das, S. K., et al. “Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis.” Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008, Dec. 2008, pp. 545–50. Scopus, doi:10.1109/ICMLA.2008.122.
Das SK, Chen S, Deasy JO, Zhou S, Yin FF, Marks LB. Decision fusion of machine learning models to predict radiotherapyinduced lung pneumonitis. Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008 Dec 1;545–550.

Published In

Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

DOI

Publication Date

December 1, 2008

Start / End Page

545 / 550