On an ensemble algorithm for clustering cancer patient data

Authors

Ran Qi, University of Maryland at Baltimore County
Dengyuan Wu, George Washington University
Li Sheng, Drexel University
Donald E. Henson, George Washington UniversityFollow
Arnold M. Schwartz, George Washington UniversityFollow
Eric Xu, University of Virginia
Kai Xing, University of Science and Technology of China
Dechang Chen, Uniformed Services University of the Health Sciences

Document Type

Journal Article

Publication Date

2013

Journal

BMC Systems Biology

Volume

Volume 7, Supplement 4

Inclusive Pages

Article number S9

Abstract

Background

The TNM staging system is based on three anatomic prognostic factors: Tumor, Lymph Node and Metastasis. However, cancer is no longer considered an anatomic disease. Therefore, the TNM should be expanded to accommodate new prognostic factors in order to increase the accuracy of estimating cancer patient outcome. The ensemble algorithm for clustering cancer data (EACCD) by Chen et al. reflects an effort to expand the TNM without changing its basic definitions. Though results on using EACCD have been reported, there has been no study on the analysis of the algorithm. In this report, we examine various aspects of EACCD using a large breast cancer patient dataset. We compared the output of EACCD with the corresponding survival curves, investigated the effect of different settings in EACCD, and compared EACCD with alternative clustering approaches.

Results

Using the basic T and N definitions, EACCD generated a dendrogram that shows a graphic relationship among the survival curves of the breast cancer patients. The dendrograms from EACCD are robust for large values of m (the number of runs in the learning step). When m is large, the dendrograms depend on the linkage functions.

The statistical tests, however, employed in the learning step have minimal effect on the dendrogram for large m. In addition, if omitting the step for learning dissimilarity in EACCD, the resulting approaches can have a degraded performance. Furthermore, clustering only based on prognostic factors could generate misleading dendrograms, and direct use of partitioning techniques could lead to misleading assignments to clusters.

Conclusions

When only the Partitioning Around Medoids (PAM) algorithm is involved in the step of learning dissimilarity, large values of m are required to obtain robust dendrograms, and for a large mEACCD can effectively cluster cancer patient data.

Comments

Reproduced with permission of BMC Systems Biology.

Creative Commons License

This work is licensed under a Creative Commons Attribution 3.0 License.

APA Citation

Qi, R., Wu, D., Sheng, L., Henson, D., Schwartz, A., Xu, E., Xing, K., Chen, D. (2013). On an ensemble algorithm for clustering cancer patient data. BMC Systems Biology, 7(suppl.4):S9.

Peer Reviewed

1

Open Access

1