TITLE:
Parametric and Non-Parametric Analysis of the Survival Times of Patients with Multiple Myeloma Cancer
AUTHORS:
Lohuwa Mamudu, Chris P. Tsokos
KEYWORDS:
Multiple Myeloma Cancer, Three-Parameter Lognormal, Kaplan-Meier, Maximum Likelihood Estimation, Health Science
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.10 No.4,
April
14,
2020
ABSTRACT: Multiple myeloma (MM) is a type of cancer that remains incurable. In the
last decade, most research into MM has focused on investigating the improvement
in the therapeutic strategy. Our study assesses the survival probability of 48
patients diagnosed with MM based on parametric and non-parametric techniques.
We performed parametric survival analysis and found a well-def- ined probability distribution
of the survival time to follow three-parameter lognormal. We then estimated the
survival probability and compared it with the commonly used non-parametric
Kaplan-Meier survival analysis of the survival times. The comparison of the
survival probability estimates of the two methods revealed a better survival
probability estimate by the parametric method than the Kaplan-Meier. The
parametric survival analysis is more robust
and efficient because it is based on a well-defined parametric probabilistic distribution, hence preferred over the non-parametric
Kaplan-Meier. This study offers therapeutic significance for further enhancement in the treatment strategy of multiple
myeloma cancer.