Multi-layer neural network analysis of cerebrospinal fluid pressure patterns in idiopathic normal-pressure hydrocephalus

Abstract

The cerebrospinal fluid (CSF) pressure patterns have been reported as one of the most relevant indexes for the diagnosis and treatment of idiopathic normal-pressure hydrocephalus (INPH). Forty consecutive patients coming from our observations with the classic Hakim’s triad underwent continuous CSF pressure monitoring via lumbar puncture for at least 12 hours. Twenty-eight patients were diagnosed as having INPH and underwent CSF shunt. A multi-layer neural network (perceptron) was employed to study the pressure patterns in order to try an alternative classification to the “expert” neurosurgeon one. Differences between expert and neural network classifications were indeed observed. Such differences may depend on the small group studied or on the inadequacy of CFS pressure patterns in correctly individuating those INPH patients who benefit from shunt surgery. The authors think that neural network processing of INPH could add relevant information to select the “responder” patients to surgery: in fact neural networks represent a powerful methodology for aiding the expert to select the proper choice on the basis of “what learnt” by the networks themselves.