Clustering gene expression data using Coxian phase-type survival

The paper is concerned with modeling gene expression data of Acute Myeloid Leukemia patients and their survival. Of particular interest is the development of a clustering approach that will identify clusters of patients that have similar gene expression characteristics. This paper considers one such approach based on the Coxian phase-type distribution which proved to be an adequate representation for the patient survival distribution. If such an approach were introduced it would facilitate better patient management and hence allow the most suitable care plan for the different clusters of patients. This will not only have financial benefit but will provide a better quality of service to the patient who will no longer have to undergo ineffective treatments that may have damaging side effects.

[1]  J. Licht,et al.  HOX deregulation in acute myeloid leukemia. , 2007, The Journal of clinical investigation.

[2]  M. Cronin,et al.  Gene expression and benefit of chemotherapy in women with node-negative, estrogen receptor-positive breast cancer. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[3]  Van,et al.  A gene-expression signature as a predictor of survival in breast cancer. , 2002, The New England journal of medicine.

[4]  Ash A. Alizadeh,et al.  Di erent types of di use large b-cell lymphoma identi ed by gene expression pro ling , 2000 .

[5]  D. Cox A use of complex probabilities in the theory of stochastic processes , 1955, Mathematical Proceedings of the Cambridge Philosophical Society.

[6]  G. Morgan,et al.  Karyotype and age in acute myeloid leukemia. Are they linked? , 2001, Cancer genetics and cytogenetics.

[7]  Li Mao,et al.  Prognostic factors in resected stage I non-small-cell lung cancer: a multivariate analysis of six molecular markers. , 2004, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[8]  Laurence Lodé,et al.  Prediction of survival in multiple myeloma based on gene expression profiles reveals cell cycle and chromosomal instability signatures in high-risk patients and hyperdiploid signatures in low-risk patients: a study of the Intergroupe Francophone du Myélome. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[9]  D. Kleinbaum,et al.  Survival Analysis: A Self-Learning Text. , 1996 .

[10]  Sally McClean,et al.  Conditional phase-type distributions for modelling patient length of stay in hospital , 2003 .

[11]  M. Faddy Examples of fitting structured phase–type distributions , 1994 .

[12]  Ash A. Alizadeh,et al.  Distinct types of diffuse large B-cell lymphoma identified by gene expression profiling , 2000, Nature.

[13]  Meland,et al.  THE USE OF MOLECULAR PROFILING TO PREDICT SURVIVAL AFTER CHEMOTHERAPY FOR DIFFUSE LARGE-B-CELL LYMPHOMA , 2002 .

[14]  Marcel F. Neuts,et al.  Matrix-geometric solutions in stochastic models - an algorithmic approach , 1982 .

[15]  Yudong D. He,et al.  Gene expression profiling predicts clinical outcome of breast cancer , 2002, Nature.

[16]  J. Griffiths The Theory of Stochastic Processes , 1967 .