Title :
A preliminary study for investigating idiopatic normal pressure hydrocephalus by means of statistical parameters classification of intracranial pressure recordings
Author :
Calisto, A. ; Bramanti, A. ; Galeano, M. ; Angileri, F. ; Campobello, G. ; Serrano, S. ; Azzerboni, B.
Author_Institution :
Dept. of Matter Phys. & Electron. Eng., Univ. of Messina, Messina, Italy
Abstract :
The objective of this study is to investigate Id-iopatic Normal Pressure Hydrocephalus (INPH) through a multidimensional and multiparameter analysis of statistical data obtained from accurate analysis of Intracranial Pressure (ICP) recordings. Such a study could permit to detect new factors, correlated with therapeutic response, which are able to validate a predicting significance for infusion test. The algorithm developed by the authors computes 13 ICP parameter trends on each of the recording, afterward 9 statistical information from each trend is determined. All data are transferred to the data mining software WEKA. According to the exploited feature-selection techniques, the WEKA has revealed that the most significant statistical parameter is the maximum of single-wave-amplitude: setting a 27 mmHg threshold leads to over 90% of correct classification.
Keywords :
brain; data analysis; data mining; feature extraction; medical disorders; medical signal processing; neurophysiology; signal classification; statistical analysis; biomedical signal classification; data mining software WEKA; feature selection technique; idiopatic normal pressure hydrocephalus; infusion test; intracranial pressure recording; multidimensional analysis; multiparameter analysis; pattern recognition; pressure 27 mm Hg; statistical data analysis; statistical parameter classification; Biomedical signal classification; Pattern recognition methods for data mining; Signals and systems; Adult; Aged; Algorithms; Automatic Data Processing; Biomedical Engineering; Data Interpretation, Statistical; Equipment Design; Female; Humans; Hydrocephalus, Normal Pressure; Intracranial Pressure; Male; Middle Aged; Pattern Recognition, Automated; Signal Processing, Computer-Assisted; Software; Spinal Puncture; Transducers, Pressure;
Conference_Titel :
Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
Conference_Location :
Minneapolis, MN
Print_ISBN :
978-1-4244-3296-7
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2009.5335371
