SECTION I: Testing
|1||Has the R & D result been tested?|
|Yes the R&D result has been tested.|
|1a||In what mode has the result been tested?
• Pilot Application
• Alpha/BETA testing
|The R&D result has been tested on real data sets. The R&D dealt with wheezes, pathological breath sounds whose presence is related to airways’ obstruction. In particular, it addressed two problems corresponding to wheezes: their detection and the analysis of their characteristics. Wheezes detection methods were tested on 370 wheezes from 9 patients (5 with COPD and asthma 4), while the analysis of wheezes characteristics was performed in 393 wheezes from 21 patients (10 with COPD and 11 with asthma). The wheezes recordings had been made by German Marburg University and were lent to the Aristotle University R&D developer for testing.|
|1b.||Please describe and discuss the testing results|
|For their detection of wheezes, two methods were proposed.
In the first method, which is based on Short-Time Fourier Transform, different detection criteria were set for different frequency bands, since the spectrum of breath sounds is not the same in their whole frequency range. Additionally, through the inverse transform the representation in time of the signal which had been processed in the time-frequency domain was introduced. The proposed method exhibited high detectability, sensitivity and specificity (TDR=90.2%, SE=92.1%, SP=89.8%). Despite the high percentages, the resolution in time and in frequency of the suggested method was limited by the selected window length.
The second method for wheeze detection was based on the combination of the ensemble Empirical Mode Decomposition and the Instantaneous Frequency. The kernel of this method was the observation that the instantaneous frequency of a signal remains constant when the signal is dominated by particular frequency components, such as wheezes. The proposed method exhibited high detectability, sensitivity and specificity (TDR=94.0%, SE=94.9%, SP=98.4%), which were improved comparing to the previous method.
For the analysis of wheeze characteristics, and in particular the detection of non-linear phenomena, third-order spectra, which preserve the phase information of the signal, were combined with the Wavelet Transform, which allowed capturing non-linearities across time. Through wavelet Bispectrum and Bicoherence and the corresponding instantaneous values a new analysis domain was introduced. For the investigation of statistically significant differences between wheezes from patients with asthma and COPD, a set of features was introduced based on these mathematical tools.
After statistical analysis of the results it was concluded that there were statistical significant differences between wheezes coming form patients with asthma and those that come form patients with COPD.
SECTION 2: Current Stage of Development
|2a||To what extent does the development team have technical resources for supporting the production of a new product? (Researchers, human resources, hardware, etc.)|
|The developer of the R&D result is available both for full time employment as well as for technical advising. Some technical resources are available by the Aristotle University’s Signal Processing and Biomedical Technology Unit, but some other need to be acquired.|
|2b||What are the technical issues that need to be tackled for full deployment, if needed?|
|There is a number of technical issues that need to be tackled for the full deployment of a new product. These are the following:
|2c||What additional technical resources are needed for the production of this new product?|
|The additional technical resources needed are the following:
-sound recordings devices (they can take the form of a laptop connected with microphones)
-sound recordings through collaboration with pulmonary clinics
-software licences for MATLAB, SPSS, LabView
|2d||Overall assessment of the current stage of technical development.|
|The R&D result needs to be developed and tested further. However it has strong potential for becoming a successful new product.|
SECTION 3: Deployment
|3a||Define the demands for large scale production in terms of|
|• Technologies, Tools, Machineries, Software
Sound recording devices and microphones
4 laptop computers
Software licenses for MATLAB, SPSS ans Labview
• Staff effort
4 electrical engineers for product and software development
1 pneumonologist for assistance with the recognition and filing of the sound characteristics of each disease and each age group
Collaboration with Signal Processing and Biomedical Technology Unit for the definition of the recording system
Collaboration with 3 pneumonologic clinics for the respiratory sound recordings
SECTION 4: Overall Assessment
|4||What is your overall assessment of the technical feasibility of the research result?|
|If the R&D result is developed further it can be transformed in a successful new product, both in the form of a new device as well as computer software.|