Models for handling uncertainty in fetal heart rate and ECG analysis

Abstract

Abstract-Methods for handling imprecision and uncertainty in computer-based analysis of fetal heart rate patterns and ECG wave shape during childbirth are presented. Computational intelligence models, based on fuzzy logic techniques, that explicitly handle the imprecision and uncertainty inherent in the data obtained during childbirth and methods of interpreting the data are proposed. The ability to handle imprecision and uncertainty in clinical data and method of interpretation is vital to remove a key obstacle in electronic fetal monitoring.Keywords -Electronic fetal monitoring, fetal heart rate, cardiotocogram, fetal ECG, fuzzy logic, computational intelligence models. I. INTRODUCTIONMethods for handling imprecision and uncertainty in computer-based analysis of fetal heart rate patterns and electrocardiogram (ECG) wave shape during labour are described. Childbirth is a critical period for the fetus and mother. The outcome of labour is normally good, but sometimes problems occur that may lead to injury (e.g. fetal brain damage) or even death [1,2].Electronic fetal monitoring, introduced in the late 1960's [3], was expected to improve patient care, but this has not yet happened. The most common monitoring method is based on a continuous trace of the fetal heart rate pattern and maternal contractions, known as the cardiotocogram (CTG). Difficulties in the interpretation of the CTG have led to unnecessary medical interventions (e.g. Caesarean sections and forcept deliveries)[2] and a failure to intervene when necessary [1] (which can lead to preventable injuries and deaths). These problems have led to the development of a number of computerized systems to assist with the analysis and interpretation of CTG [4][5][6][7][8][9][10]. However, despite over two decades of development no system is in widespread routine clinical practice.Progress in computerized CTG analysis has been impeded by several factors. First, there are significant, inherent problems of imprecision and uncertainty in the clinical data and the interpretation methods used [11]. These problems have yet to be addressed in computerized CTG systems. Secondly, the CTG does not contain sufficient information for accurate assessment of the fetal condition [12]. Additional information may be obtained by a proper analysis of changes in the fetal electrocardiogram (ECG), but the problems of uncertainty and imprecision also exist in fetal ECG analysis.We have proposed computational intelligence models, based on fuzzy logic techniques, to explicitly handle the imprecision and uncertainty in clinical knowledge and data.In this paper, we describe the models and their application to fetal heart rate and ECG analysis. In sections II and III, respectively, the development of the models for CTG and ECG analysis will be presented. In each case, we start with a highlight of the nature and sources of imprecision and uncertainty to provide the basis for designing the fuzzy models. II. MODELLING UNCERTAINTY AND IMPRECISION IN FETAL HEART RATE ANALYSIS A. Uncertainty and i...