Key result
The radial basis function network achieved an overall prediction rate of 98.5% for one-year survival in myocardial infarction patients, outperforming the backpropagation neural network (96.9%).
Why the study?
Does a radial basis function network improve the prediction of one-year survival in patients with myocardial infarction compared to a backpropagation neural network?
Does a radial basis function network improve the prediction of one-year survival in patients with myocardial infarction compared to a backpropagation neural network?
Absolute Event Rate: 98.5% vs 96.9%
A radial basis function neural network can accurately predict one-year survival in patients following a myocardial infarction, outperforming a standard backpropagation network.
RBFN may enhance MI survival prediction accuracy; hypothesis-generating and requires prospective validation before clinical adoption.
Myocardial infarction is still one of the leading causes of death and morbidity. The early prediction of such disease can prevent or reduce the development of it. Machine learning can be an efficient tool for predicting such diseases. Many people have suffered myocardial infarction in the past. Some of those have survived and others were dead after a period of time. A machine learning system can learn from the past data of those patients to be capable of predicting the one-year survival or death of patients with myocardial infarction. The survival at one year, death at one year, survival period, in addition to some clinical data of patients who have suffered myocardial infarction can be used to train an intelligent system to predict the one-year survival or death of current myocardial infarction patients. This paper introduces the use of two neural networks: Feedforward neural network that uses backpropagation learning algorithm (BPNN) and radial basis function networks (RBFN) that were trained on past data of patients who suffered myocardial infarction to be capable of generalizing the one-year survival or death of new patients. Experimentally, both networks were tested on 64 instances and showed a good generalization capability in predicting the correct diagnosis of the patients. However, the radial basis function network outperformed the backpropagation network in performing this prediction task.
No takes yet. Share an insight, caveat, or question.
Helwan et al. (2017) studied Myocardial infarction (n=131). Radial Basis Function Network (RBFN) vs. Backpropagation Neural Network (BPNN) was evaluated on Overall prediction rate of one-year survival or death. The radial basis function network achieved an overall prediction rate of 98.5% for one-year survival in myocardial infarction patients, outperforming the backpropagation neural network (96.9%).