Abstract
Single clustering methods have often been used to elucidate clusters in high dimensional medical data, even though reliance on a single algorithm is known to be problematic. In this paper, we present a methodology to determine a set of 'core classes' by using a range of techniques to reach consensus across several different clustering algorithms, and to ascertain the key characteristics of these classes. We apply the methodology to immunohistochemical data from breast cancer patients. In doing so, we identify six core classes, of which several may be novel sub-groups not previously emphasised in literature.
| Original language | English |
|---|---|
| Pages (from-to) | 318-330 |
| Number of pages | 13 |
| Journal | Computers in Biology and Medicine |
| Volume | 40 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - Mar 2010 |
Fingerprint
Keywords
- Breast cancer
- Clustering methods
- Consensus clustering
- Molecular classification
- Validity indices
ASJC Scopus subject areas
- Computer Science Applications
- Health Informatics
Cite this
A methodology to identify consensus classes from clustering algorithms applied to immunohistochemical data from breast cancer patients. / Soria, Daniele; Garibaldi, Jonathan M.; Ambrogi, Federico; Green, Andrew R.; Powe, Des; Rakha, Emad; Douglas Macmillan, R.; Blamey, Roger W.; Ball, Graham; Lisboa, Paulo J G; Etchells, Terence A.; Boracchi, Patrizia; Biganzoli, Elia; Ellis, Ian O.
In: Computers in Biology and Medicine, Vol. 40, No. 3, 03.2010, p. 318-330.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A methodology to identify consensus classes from clustering algorithms applied to immunohistochemical data from breast cancer patients
AU - Soria, Daniele
AU - Garibaldi, Jonathan M.
AU - Ambrogi, Federico
AU - Green, Andrew R.
AU - Powe, Des
AU - Rakha, Emad
AU - Douglas Macmillan, R.
AU - Blamey, Roger W.
AU - Ball, Graham
AU - Lisboa, Paulo J G
AU - Etchells, Terence A.
AU - Boracchi, Patrizia
AU - Biganzoli, Elia
AU - Ellis, Ian O.
PY - 2010/3
Y1 - 2010/3
N2 - Single clustering methods have often been used to elucidate clusters in high dimensional medical data, even though reliance on a single algorithm is known to be problematic. In this paper, we present a methodology to determine a set of 'core classes' by using a range of techniques to reach consensus across several different clustering algorithms, and to ascertain the key characteristics of these classes. We apply the methodology to immunohistochemical data from breast cancer patients. In doing so, we identify six core classes, of which several may be novel sub-groups not previously emphasised in literature.
AB - Single clustering methods have often been used to elucidate clusters in high dimensional medical data, even though reliance on a single algorithm is known to be problematic. In this paper, we present a methodology to determine a set of 'core classes' by using a range of techniques to reach consensus across several different clustering algorithms, and to ascertain the key characteristics of these classes. We apply the methodology to immunohistochemical data from breast cancer patients. In doing so, we identify six core classes, of which several may be novel sub-groups not previously emphasised in literature.
KW - Breast cancer
KW - Clustering methods
KW - Consensus clustering
KW - Molecular classification
KW - Validity indices
UR - http://www.scopus.com/inward/record.url?scp=77549085806&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77549085806&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2010.01.003
DO - 10.1016/j.compbiomed.2010.01.003
M3 - Article
C2 - 20106472
AN - SCOPUS:77549085806
VL - 40
SP - 318
EP - 330
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
SN - 0010-4825
IS - 3
ER -