PRELIMINARY-REPORT OF DETECTING MICROEMBOLIC SIGNALS IN TRANSCRANIAL DOPPLER TIME-SERIES WITH NONLINEAR FORECASTING

Background and Purpose-Most algorithms used for automatic detection of microembolic signals (MES) are based on power spectral analysis of th e Doppler shift. However, controversies exist as to whether these algo rithms can replace the human expert. Therefore, a different algorithm was applied that takes advantage of the periodicity of the MES. This s o-called nonlinear forecasting (NLF) is able to detect periodicity in a time series, and it is hypothesized that this technique has the pote ntial to detect MES. Moreover, because of the lack of prominent period icity in both the normal Doppler signals (DS) and movement artifacts ( MA), the NLF has a potential to differentiate MES from normal blood fl ow variations and MA. Methods-Twenty single MES and 100 MA were select ed by 2 human experts. NLF was applied to MES and MA and compared with 200 randomly chosen DS. NLF resulted in a so-called prediction value that ranges from +1 in signals with prominent periodicity to 0 in sign als that lack periodicity. Results-NLF revealed that MES are more pred ictable than the normal Doppler signals (prediction [MES]=0.829+/-0.08 4 versus prediction [DS]=-0.060+/-0.228; P<0.0001). Moreover, MES are more predictable than the MA (prediction [MA] = -0.034+/-0.223; P<0.00 01). No difference in prediction could be found between DS and MA. Con clusions-This preliminary report shows that MES can be separated from DS and MA by NLF. Research is needed as to whether this technology can be further developed fdr automatic detection of MES.