An artificial neural network improves prediction of observed survival in patients with laryngeal squamous carcinoma

The accepted method of modelling and predicting failure/survival, Cox’s proportional hazards model, is theoretically inferior to neural network derived models for analysing highly complex systems with large datasets. A blinded comparison of the neural network versus the Cox’s model in predicting survival utilising data from 873 treated patients with laryngeal cancer. These were divided randomly and equally into a training set and a study set and Cox’s and neural network models applied in turn. Data were then divided into seven sets of binary covariates and the analysis repeated. Overall survival was not significantly different on Kaplan–Meier plot, or with either test model. Although the network produced qualitatively similar results to Cox’s model it was significantly more sensitive to differences in survival curves for age and N stage. We propose that neural networks are capable of prediction in systems involving complex interactions between variables and non-linearity.

[1]  E Biganzoli,et al.  Flexible Modelling in Survival Analysis. Structuring Biological Complexity from the Information Provided by Tumor Markers , 1998, The International journal of biological markers.

[2]  Mark A. Stephenson,et al.  Artificial neural networks and logistic regression as tools for prediction of survival in patients with Stages I and II non-small cell lung cancer. , 1998, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[3]  Max H. Myers,et al.  Manual for Staging of Cancer , 1992 .

[4]  Ronald Kates,et al.  Advanced statistical methods for the definition of new staging models. , 2003, Recent results in cancer research. Fortschritte der Krebsforschung. Progres dans les recherches sur le cancer.

[5]  Xianggui Qu,et al.  Multivariate Data Analysis , 2007, Technometrics.

[6]  Paulo J. G. Lisboa,et al.  A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer , 2003, Artif. Intell. Medicine.

[7]  L. Sobin,et al.  TNM Classification of Malignant Tumours , 1987, UICC International Union Against Cancer.

[8]  Donald E. Henson,et al.  Manual for Staging of Cancer, 3rd edition , 1988 .

[9]  H. Joensuu,et al.  Artificial Neural Networks Applied to Survival Prediction in Breast Cancer , 1999, Oncology.

[10]  D.,et al.  Regression Models and Life-Tables , 2022 .

[11]  Douglas G. Altman,et al.  Practical statistics for medical research , 1990 .

[12]  José Antonio Gómez-Ruiz,et al.  A combined neural network and decision trees model for prognosis of breast cancer relapse , 2003, Artif. Intell. Medicine.

[13]  J. Hair.  Multivariate data analysis , 1972 .

[14]  D M Rodvold,et al.  Neural network and regression predictions of 5‐year survival after colon carcinoma treatment , 2001, Cancer.

[15]  K. Liestøl,et al.  Survival analysis and neural nets. , 1994, Statistics in medicine.

[16]  C E Floyd,et al.  Artificial neural network model of survival in patients treated with irradiation with and without concurrent chemotherapy for advanced carcinoma of the head and neck. , 1998, International journal of radiation oncology, biology, physics.

[17]  P. Armitage,et al.  Statistical methods in medical research. , 1972 .

[18]  David Kerr,et al.  Neural networks in the prediction of survival in patients with colorectal cancer. , 2003, Clinical colorectal cancer.

[19]  F. Harrell,et al.  Artificial neural networks improve the accuracy of cancer survival prediction , 1997, Cancer.

[20]  E Biganzoli,et al.  Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. , 1998, Statistics in medicine.

[21]  L. Bottaci,et al.  Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions , 1997, The Lancet.

[22]  K. Murase,et al.  Survival prediction using artificial neural networks in patients with uterine cervical cancer treated by radiation therapy alone , 2002, International Journal of Clinical Oncology.

[23]  Guido Schwarzer,et al.  Artificial neural networks for diagnosis and prognosis in prostate cancer. , 2002, Seminars in urologic oncology.

[24]  W. Vach,et al.  On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology. , 2000, Statistics in medicine.

[25]  Michele De Laurentiis,et al.  Survival analysis of censored data: Neural network analysis detection of complex interactions between variables , 2004, Breast Cancer Research and Treatment.

[26]  P M Ravdin,et al.  A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients. , 1999, Clinical cancer research : an official journal of the American Association for Cancer Research.

[27]  John G. Hughes,et al.  An evaluation of intelligent prognostic systems for colorectal cancer , 1999, Artif. Intell. Medicine.

[28]  Diego Liberati,et al.  Forecasting the performance status of head and neck cancer patient treatment by an interval arithmetic pruned perceptron , 2002, IEEE Transactions on Biomedical Engineering.

[29]  Y Reisman,et al.  Computer-based clinical decision aids. A review of methods and assessment of systems. , 1996, Medical informatics = Medecine et informatique.