Frequency Analysis of Capnogram Signals to Differentiate Asthmatic and Non-asthmatic Conditions Using Radial Basis Function Neural Networks
In this paper, the method of differentiating asthmatic and non-asthmatic patients using the frequency analysis of capnogram signals is presented. Previously, manual study on capnogram signal has been conducted by several researchers. All past researches showed significant correlation between ca...
| Hauptverfasser: | , , |
|---|---|
| Format: | Artikel |
| Sprache: | English |
| Veröffentlicht: |
Tehran University of Medical Sciences
2013-09-01
|
| Schriftenreihe: | Iranian Journal of Allergy, Asthma and Immunology |
| Schlagworte: | |
| Online Zugang: | https://ijaai.tums.ac.ir/index.php/ijaai/article/view/507 |
| Zusammenfassung: | In this paper, the method of differentiating asthmatic and non-asthmatic patients using the frequency analysis of capnogram signals is presented. Previously, manual study on capnogram signal has been conducted by several researchers. All past researches showed significant correlation between capnogram signals and asthmatic patients. However all of them are just manual study conducted through the conventional time domain method. In this study, the power spectral density (PSD) of capnogram signals is estimated by using Fast Fourier Transform (FFT) and Autoregressive (AR) modelling.
The results show the non-asthmatic capnograms have one component in their PSD estimation, in contrast to asthmatic capnograms that have two components. Furthermore, there is a significant difference between the magnitude of the first component for both asthmatic and non-asthmatic capnograms.
The effectiveness and performance of manipulating the characteristics of the first frequency component, mainly its magnitude and bandwidth, to differentiate between asthmatic and non-asthmatic conditions by means of receiver operating characteristic (ROC) curve analysis and radial basis function (RBF) neural network were shown.
The output of this network is an integer prognostic index from 1 to 10 (depends on the severity of asthma) with an average good detection rate of 95.65% and an error rate of 4.34%. This developed algorithm is aspired to provide a fast and low-cost diagnostic system to help healthcare professional involved in respiratory care as it would be possible to monitor severity of asthma automatically and instantaneously. |
|---|---|
| ISSN: | 1735-1502 1735-5249 |