A multilayer perceptron network for the diagnosis of low back pain

作者: Bounds , Lloyd , Mathew , Waddell

DOI: 10.1109/ICNN.1988.23963

关键词:

摘要: A description is given of the training a multilayer perceptron (MLP) network for diagnosis low back pain and sciatica. The performance system compared with that three groups doctors also another computer program based on fuzzy logic ideas. Although clinical data larger numbers patients would be necessary before this neural-network approach could fully validated, initial results are very promising. For diagnostic category which it most crucial to get right (because surgery may required urgently), MLP produces correct classification more often than any or system. mean accuracy over all possible diagnoses higher doctors, but slightly worse >

参考文章(2)
DAVID MORRIS PhD, DAVID HENDRY, GORDON WADDELL, BRUCE MATHEW MB, Artificial intelligence in the diagnosis of low-back pain and sciatica. Spine. ,vol. 13, pp. 168- 172 ,(1988) , 10.1097/00007632-198802000-00007
D. E. Rumelhart, G. E. Hinton, R. J. Williams, Learning internal representations by error propagation Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. ,vol. 1, pp. 318- 362 ,(1986)