Biomedical Engineering Reference
In-Depth Information
CHAPTER 10
SURVIVAL MODEL AND ESTIMATION FOR LUNG
CANCER PATIENTS
Xingchen Yuan
a
,DonHong
b
, and Yu Shyr
c,d
a
Fermilab, Batavia, IL 60510, USA
b
Department of Mathematical Sciences, Middle Tennessee State University,
P.O. Box 34, Murfreesboro, Tennessee 37132, USA
E-mail: dhong@mtsu.edu
c
Department of Biostatistics, Vanderbilt University, Nashville, TN 37232, USA
d
Department of Statistics, National Cheng Kung University, Taiwan, ROC
Lung cancer is the most frequently occuring fatal cancer in the United
States. By assuming a form for the hazard function for a group of lung
cancer patients for survival study, the covariates in the hazard function
are estimated by the maximum likelihood estimation following the pro-
portional hazards regression analysis. Although the proportional hazards
model does not give an explicit baseline hazard function, the function can
be estimated by fitting the data with non-linear least square technique.
The survival model is then examined by a neural network simulation.
The neural network learns the survival pattern from available hospital
data and gives survival prediction for random covariate combinations.
The simulation results support the covariate estimation in the survival
model.
1. Introduction
Cancer develops when cells in a part of the body begin to grow out of
control. It is the second most significant reason for US mortality. In 2001,
cancer caused 553,768 deaths in the United States, accounting for 22.9% of
all deaths in that year [13]. In the past fifty years, efforts have been made
to reduce death rates for different diseases, but the death rate for cancer
remains almost unchanged ([14], [15]). Among the various types of cancers,
lung cancer is the most frequently occuring fatal cancer, for both men
and women, in the United States. Each year there are about 170, 000 new
cases of lung cancer in the U.S.A. and 150,000 deaths attributable to this
Search WWH ::
Custom Search