Fetal heart rate baseline estimation with analysis of fetal movement signal.

In order to assign appropriate baseline estimation algorithms to different fetal heart rate tracing, a method to evaluate the fetal heart rate (FHR) baseline combining with the fetal movement information was proposed. Fetal actography and tocography were used to extract the fetal movement information. The results showed that the combined method, where the fetal movement detection result was the union of results of actography and tocography, achieved a better performance with the highest sensitivity and an acceptable positive predictive value (PPV). Furthermore, the mean absolute errors (MAEs) of basal FHR values between the two algorithms and the expert were calculated with respect to the duration coefficient of fetal movement. The results showed that the algorithm using empirical mode decomposition (EMD) and Kohonen neural network (KNN) had lower MAEs than a traditional linear baseline estimation algorithm as the duration coefficient increased. However, if the duration coefficient is below 0.2, the errors may be tolerant for the FHR baseline estimation by a linear baseline estimation algorithm, which indicates that different algorithms may be selected for FHR baseline estimation based on different duration coefficients of fetal movement.