Determination of window size for baseline estimation of fetal heart rate using CTG

One of the major features of fetal heart rate (FHR) is its baseline, the accurate classification of which is of utmost importance as all the other parameters of cardiotography (CTG) rely on it. Though guidelines for interpretation had been put forward by different organizations, they not only lack uniformity, but also are not definite, hence, difficult to implement in automated systems. We aim to propose a standardized baseline estimation algorithm addressing these issues. Baseline was calculated within continuous sliding window of duration 10 minutes and varying slide-lengths. The best slide-length is chosen and the corresponding baseline value is compared with the one obtained with discreet window as suggested by NICHD [1] and the estimate given by three experienced physicians. The results are analyzed using standard statistical methods such as confidence level, error margin, standard error etc. at a Confidence Level of 95%. The results of the algorithm and mathematical calculations incorporated in this work is found encouraging. Thus the proposed algorithm can not only be used to easily estimate the baseline using overlapping window but can also be adopted in an automated system for the interpretation of CTG.