Role of artificial neural networks in prediction of survival of burn patients-a new approach.

A burn patient may require the most complicated treatment regimes encountered among trauma victims. Predicting the outcome of such treatment depends on several factors which have non-linear relationships. Traditional methods in prediction are "logistic regression" and "maximum likelihood". In this study, an artificial neural network (ANN) is used for computing survival among burn patients admitted to the "Motahary Burn Center", during a 1 year period (1996-1997). Fifteen different observations, such as total body surface area (TBSA), rescue time, admission period, surgery, inhalation injuries, etc. were obtained, retrospectively. A normal feed forward ANN was developed by Thinkspro software. It has 15 input-units, two hidden layers, and one output-unit. Survival was higher in males, those in whom early fluid resuscitation had been initiated and in patients in the middle of the age spectrum (P<0.0001). Strong correlations with these factors were noted. In the training phase, the ANNs accuracy reached 90%. In this study, the ANN has been applied for the first time to predict burn victim survival. This study can enable a different view point to help burn center physicians in the prediction of survival of their patients.

[1]  N. H. Mann,et al.  Artificial intelligence in the diagnosis of low back pain. , 1991, The Orthopedic clinics of North America.

[2]  J. K. Rose,et al.  Advances in the treatment of burn patients. , 1997, Burns : journal of the International Society for Burn Injuries.

[3]  E. Merwin,et al.  Alternative statistical methods to use with survival data. , 1996, Nursing research.

[4]  J. Doctor,et al.  The 1997 Clinical Research Award. Health outcome for burn survivors. , 1997, The Journal of burn care & rehabilitation.

[5]  C. Ryan,et al.  Objective estimates of the probability of death from burn injuries. , 1998, The New England journal of medicine.

[6]  D Faraggi,et al.  A neural network model for survival data. , 1995, Statistics in medicine.

[7]  W. Firth,et al.  Chaos--predicting the unpredictable. , 1991, BMJ.

[8]  A. Detsky,et al.  Neural networks: what are they? , 1991, Annals of internal medicine.

[9]  M. D. Williams,et al.  Prediction of trauma mortality using a neural network. , 1997, The American surgeon.

[10]  Bruce W. Colletti,et al.  Artificial intelligence versus logistic regression statistical modelling to predict cardiac complications after noncardiac surgery , 1994, Clinical Cardiology.

[11]  J. R. Saffle.  Predicting outcomes of burns. , 1998, The New England journal of medicine.

[12]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[13]  M A Musen,et al.  Hierarchical neural networks for survival analysis. , 1995, Medinfo. MEDINFO.

[14]  L Ohno-Machado,et al.  A comparison of Cox proportional hazards and artificial neural network models for medical prognosis , 1997, Comput. Biol. Medicine.

[15]  J. Constable.  The state of burn care: past, present and future. , 1994, Burns : journal of the International Society for Burn Injuries.

[16]  Z H Khan,et al.  Artificial neural network and medicine. , 1998, Indian journal of physiology and pharmacology.

[17]  B Cochand-Priollet,et al.  Potential of the back propagation neural network in the morphologic examination of thyroid lesions. , 1996, Analytical and quantitative cytology and histology.

[18]  G. Germann,et al.  Factors influencing the early prediction of outcome from burns. , 1996, Acta chirurgiae plasticae.

[19]  A. E. Danaf,et al.  Burn variables influencing survival: a study of 144 patients , 1995 .