Automated analysis of cardiotocographic signals.

Abstract

Cardiotocographic signals, used as a perinatal diagnostic tool, comprise fetal heart beat signals (FHR), uterine contractions (UC) and fetal movements (FM). Visual inspection of these three signals is limited, subjective, time consuming and with low reproducibility. The present paper illustrates an application of signal processing techniques to the automatic analysis of cardiotocographic signals, allowing to overcome visual inspection limitations. Porto system of cardiotocograms automatic analysis acquires the signals from a conventional cardiotocograph. The signals are stored and processed by a personal computer. System software allows the user to perform several operations such as signal acquisition, signal storage and retrieval from files, signal analysis and display. Signal analysis is preceded by various signal conditioning operations (filtering, spike removal, etc.) and consists in the estimation of several parameters with diagnostic value: FHR baseline; FHR accelerations and decelerations; uterine contractions; long and short term FHR variability. The system prototype is working on a routine basis at the Obstetrics Department of S. João Hospital (main Oporto Hospital) and is being evaluated using a large data set. A preliminary evaluation performed by 3 experts on a 50 cases set, yielded an agreement rate with computer measurements of 98% for the baseline, 72% to 82% for accelerations and decelerations and 76% for the uterine contractions.