Pakistan Journal of Biological Sciences1028-88801812-5735Asian Network for Scientific Information10.3923/pjbs.2008.1076.1084AmiriZohreh MohammadKazem MahmoudiMahmoud ZeraatiHojjat FotouhiAkbar 82008118This study is designed to assess the application of neural networks
in comparison to the Kaplan-Meier and Cox proportional hazards model in
the survival analysis. Three hundred thirty gastric cancer patients admitted
to and surgically treated were assessed and their post-surgical survival
was determined. The observed baseline survival was determined with the
three methods of Kaplan-Meier product limit estimator, Cox and the neural
network and results were compared. Then the binary independent variables
were entered into the model. Data were randomly divided into two groups
of 165 each to test the models and assess the reproducibility. The Chi-square
test and the multiple logistic model were used to ensure the groups were
similar and the data was divided randomly. To compare subgroups, we used
the log-rank test. In the next step, the probability of survival in different
periods was computed based on the training group data using the Cox proportional
hazards and a neural network and estimating Cox coefficient values and
neural network weights (with 3 nodes in hidden layer). Results were used
for predictions in the test group data and these predictions were compared
using the Kaplan-Meier product limit estimator as the gold standard. Friedman
and Kruskal-Wallis tests were used for comparisons as well. All statistical
analyses were performed using SPSS version 11.5, Matlab version 7.2, Statistica
version 6.0 and S_PLUS 2000. The significance level was considered 5%
(α = 0.05). The three methods used showed no significance difference
in base survival probabilities. Overall, there was no significant difference
among the survival probabilities or the trend of changes in survival probabilities
calculated with the three methods, but the 4 year (48th month) and 4.5
year (54th month) survival rates were significantly different with Cox
compared to standard and estimated probabilities in the neural network
(p<0.05). Kaplan-Meier and Cox showed almost similar results for the
baseline survival probabilities, but results with the neural network were
different: higher probabilities up to the 4th year, then comparable with
the other two methods. Estimates from Cox proportional hazards and the
neural network with three nodes in hidden layer were compared with the
estimate from the Kaplan-Meier estimator as the gold standard. Neither
comparison showed statistically significant differences. The standard
error ratio of the two estimate groups by Cox and the neural network to
Kaplan-Meier were no significant differences, it indicated that the neural
network was more accurate. Although we do not suggest neural network methods
to estimate the baseline survival probability, it seems these models is
more accurately estimated as compared with the Cox proportional hazards,
especially with today`s advanced computer sciences that allow complex
calculations. These methods are preferable because they lack the limitations
of conventional models and obviate the need for unnecessary assumptions
including those related to the proportionality of hazards and linearity.]]>Anagnostopoulos, I. and I. Maglogiannis,200644773784Ashutosh, K., H. Lee, C.K. Mohan, S. Ranka, K. Mehrotra and C. Alexander,19922012951301Bakker, B., T. Heskes, J. Neijt and B. Kappen,20042329893012Baxt, W.G.,1991115843848Baxt, W.G.,19922114391444Biganzoli, E., P. Boracch, D. Coradini, M. Grazia Daidone and E. Marubini,20031414841493Burke, H.B.,1994107379De Laurentiis, M. and P.M. Ravdin,199477127138Ding, Y.B., G.Y. Chen, J.G. Xia, H.Y. Yang, L. Yang and Y.X. Liu,200410182185Doyle, H.R., I. Dvorchik, S. Mitchell, I.R. Marino, F.H. Ebert, J. McMichael and J.J. Fung,1994219408415Ebell, M.H.,199336297303Fuxe, K., A. Dahlstrom, M. Hoistad, D. Marcellino and A. Jansson et al.,2007551754Hirsch, S., J. Shapiro, M. Turega, T.L. Frank, R. Niven and P.I. Frank,200111369376Jerez, J.M., L. Franco, E. Alba, A. Llombart-Cussac and A. Lluch et al.,200594265272Jones, A.S., A.G. Taktak, T.R. Helliwell, J.E. Fenton, M.A. Birchall, D.J. Husband and A.C. Fisher,2006263541547Kaplan, E.L. and P. Meier,195853457481Klien, J.P. and M.L. Moeschberger,19972nd Edn.,Marsland, S., J. Shapiro and U. Nehmzow,20021510411058Mohagheghi, M.A., A.M. Jarahi, S.S. Torbaghan and H. Zeraati,1998Mohagheghi, M.A., A.M. Jarahi, S.S. Torbaghan and H. Zeraati,1999Mohagheghi, M.A.,2004Ohno-Machado, L.,19963170174Papik, K., B. Molnar, R. Schaefer, Z. Dombovari, Z. Tulassay and J. Feher,19984538546Park, Y.S. and Y.J. Chung,2006222222233Ravdin, P.M., G.M. Clark, S.G. Hilsenbeck, M.A. Owens, P. Vendely, M.R. Pandian and W.L. McGuire,1992214753Ravdin, P.M. and G.M. Clark,199222285293Ripley, B.D. and R.M. Ripley,2001Ripley, R.M. and A.L. Harris,200423825842Sato, F., Y. Shimada, F.M. Selaru, D. Shibata and M. Maeda et al.,200510315961605Schwarz, R.E. and K. Zagala-Nevarez,20029394400Suka, M., S. Oeda, T. Ichimura, K. Yoshida and J. Takezawa,200411741745Thong-Ngam, D., P. Tangkijvanich, V. Mahachai and P. Kullavanijaya,200184475482Triboulet, J.P., S. Fabre, B. Castel and H. Toursel,200159097Zeraati, H., M. Mahmoudi, A. Kazemnejad and K. Mohammad,20052612031207