Michal Jezewski

Computerized analysis of fetal heart rate signals as the predictor of neonatal acidemia

Cardiotocography is the primary method for biophysical assessment of fetal state, which is mainly based on the recording and analysis of fetal heart rate (FHR) signal. Computerized systems for fetal monitoring provide a quantitative analysis of FHR signals, however the effective methods of qualitative assessment that could support the process of medical diagnosis are still needed. The measurements of hydronium ions concentration (pH) in neonatal cord blood are an objective indicator of the fetal outcome. Improper pH level is a symptom of acidemia being the result of fetal hypoxia. The paper proposes a two-step analysis of fetal heart rate recordings that allows for effective prediction of the acidemia risk. The first step consists in fuzzy classification of FHR signals. Fuzzy inference corresponds to the clinical interpretation of signals based on the FIGO guidelines. The goal of inference is to eliminate recordings indicating the fetal wellbeing from the further classification process. In the second step, the remained recordings are nonlinearly classified using multilayer perceptron and Lagrangian Support Vector Machines (LSVM). The proposed procedures are evaluated using data collected with computerized fetal surveillance system. The assessment performance is evaluated with the number of correct classifications (CC) and quality index (QI) defined as the geometric mean of sensitivity and specificity. The highest CC=92.0% and QI=88.2% were achieved for the Weighted Fuzzy Scoring System combined with the LSVM algorithm. The obtained results confirm the efficacy of the proposed methods of computerized analysis of FHR signals in the evaluation of the risk of neonatal acidemia.

Predicting the Risk of Low-Fetal Birth Weight From Cardiotocographic Signals Using ANBLIR System With Deterministic Annealing and

Cardiotocography (CTG) is a biophysical method of fetal condition assessment based mainly on recording and automated analysis of fetal heart activity. The computerized fetal monitoring systems provide the quantitative description of the CTG signals, but the effective conclusion generation methods for decision process support are still needed. Assessment of the fetal state can be verified only after delivery using the fetal (newborn) outcome data. One of the most important features defining the abnormal fetal outcome is low birth weight. This paper describes an application of the artificial neural network based on logical interpretation of fuzzy if-then rules neurofuzzy system to evaluate the risk of low-fetal birth weight using the quantitative description of CTG signals. We applied different learning procedures integrating least squares method, deterministic annealing (DA) algorithm, and ε-insensitive learning, as well as various methods of input dataset modification. The performance was evaluated with the number of correctly classified cases (CC) expressed as the percentage of the testing set size, and with overall index (OI) being the function of predictive indexes. The best classification efficiency (CC = 97.5% and OI = 82.7%), was achieved for integrated DA with ε-insensitive learning and dataset comprising of the CTG traces recorded as earliest for a given patient. The obtained results confirm efficiency for supporting the fetal outcome prediction using the proposed methods.

{\bm \varepsilon}

Cardiotocographic monitoring is a primary biophysical method for assessment of a fetal state based on quantitative analysis of the biophysical signals. Although the computerized fetal monitoring systems have become a standard in clinical centres, the effective methods, which could enable conclusion generation, are still being searched. In the proposed work the attempts have been made to answer some important questions, which occurred during application of neural network for classification of the fetal state as being normal or abnormal. These questions are particularly important for medical applications and concern the influence of data set organization, inputs representation and the networks architecture. The networks of MLP and RBF types were developed and tested using 50 trials, with randomly mixed data contents in learning, validating and testing subsets. Additionally, the influence of numerical and categorical representation of the input quantitative parameters describing fetal cardiotocograms on the efficiency of the learning process was tested.

-Insensitive Learning

Cardiotocography (CTG) is a primary biophysical method of fetal monitoring. The assessment of the printed CTG traces is based on the visual analysis of patterns describing the variability of fetal heart rate signal. The correct interpretation of traces from a bedside monitor is rather difficult even for experienced clinicians, so computer-aided fetal monitoring systems have become very popular. At present effective techniques enabling automated conclusion generation based on cardiotocograms are still being searched. The presented work describes an application the Artificial Neural Network Based on Logical Interpretation of fuzzy if-then Rules (ANBLIR) to classification of the fetal state as being normal or abnormal. A set of quantitative parameters describing fetal cardiotocograms is the system input. To evaluate the quality of the classification we proposed the overall validity index as a function of various prognostic indices. The obtained results confirm the usability of the ANBLIR neuro-fuzzy system for records classification within computer-aided fetal surveillance systems.

Some Practical Remarks on Neural Networks Approach to Fetal Cardiotocograms Classification

Cardiotocography (CTG) as a simultaneous recording of fetal heart rate, uterine contractions and fetal movement activity is a primary method for the assessment of fetal condition. At present, computerized fetal monitoring systems for on-line automated signal analysis are widely used. But effective techniques enabling conclusion generation are still being searched, and neural networks (NN) seem to be particularly attractive. In the presented work a number of investigations were carried out concerning application of NN when quantitative parameters describing fetal CTG signal — input variables - were used for prediction of fetal outcome (normal or abnormal). We tested how the efficiency of NN classification could be influenced by different modification of inputs, by interpretation of fetal outcome definition (output) as well as by various modifications of learning data sets. The obtained results gave a good background for application of the proposed classification tool within computer-aided fetal surveillance systems.

A Neuro-Fuzzy Approach to the Classification of Fetal Cardiotocograms

Computer-aided fetal monitoring is based on automated analysis of the fetal heart rate (FHR) variability. The first and the main step in the automated signal interpretation is the estimation of the so called FHR baseline. There are various algorithms for baseline estimation, of different efficiency. For its evaluation, the method of modeling of FHR signal based on the preset baseline component has been developed. The best algorithm is expected to provide the same baseline as the component baseline used to model the FHR signal. Generated signals were used to compare the baselines that have been estimated by two algorithms: the first one relying on artificial neural networks and the classical one using nonlinear filtering of FHR signal

The Prediction of Fetal Outcome by Applying Neural Network for Evaluation of CTG Records

Great expectations are connected with application of indirect fetal electrocardiography (FECG), especially for home telemonitoring of pregnancy. Evaluation of fetal heart rate (FHR) variability, when determined from FECG, uses the same criteria as for FHR signal acquired classically—through ultrasound Doppler method (US). Therefore, the equivalence of those two methods has to be confirmed, both in terms of recognizing classical FHR patterns: baseline, accelerations/decelerations (A/D), long-term variability (LTV), as well as evaluating the FHR variability with beat-to-beat accuracy—short-term variability (STV). The research material consisted of recordings collected from 60 patients in physiological and complicated pregnancy. The FHR signals of at least 30 min duration were acquired dually, using two systems for fetal and maternal monitoring, based on US and FECG methods. Recordings were retrospectively divided into normal (41) and abnormal (19) fetal outcome. The complex process of data synchronization and validation was performed. Obtained low level of the signal loss (4.5% for US and 1.8% for FECG method) enabled to perform both direct comparison of FHR signals, as well as indirect one—by using clinically relevant parameters. Direct comparison showed that there is no measurement bias between the acquisition methods, whereas the mean absolute difference, important for both visual and computer-aided signal analysis, was equal to 1.2 bpm. Such low differences do not affect the visual assessment of the FHR signal. However, in the indirect comparison the inconsistencies of several percent were noted. This mainly affects the acceleration (7.8%) and particularly deceleration (54%) patterns. In the signals acquired using the electrocardiography the obtained STV and LTV indices have shown significant overestimation by 10 and 50% respectively. It also turned out, that ability of clinical parameters to distinguish between normal and abnormal groups do not depend on the acquisition method. The obtained results prove that the abdominal FECG, considered as an alternative to the ultrasound approach, does not change the interpretation of the FHR signal, which was confirmed during both visual assessment and automated analysis.

Evaluation of Fetal Heart Rate Baseline Estimation Method Using Testing Signals Based on a Statistical Model

The telemonitoring problem of high-risk pregnancies at home is introduced, and some design issues of the monitoring system are identified. A Medical Cyber-Physical System (MCPS) approach has been taken. Various MCPS design issues and requirements, like: interaction of caregivers and a patient with the MCPS system, Plug-and-Play architecture, maintenance support for caregivers, interoperability of medical devices, medical workflows automation, dependability of the system, smart alerting, and intelligent acquisition of biosignals, have been addressed. The telecare system consists of the Body Area Network (BAN) of advanced sensors that are interconnected on a body of a pregnant woman, the Personal Area Network (PAN) that is responsible for embedded processing of physical signals, smart alerting, an intelligent human-machine-interface, and a reliable transmission channel to the Surveillance Centre located in a hospital or a local medical centre. The system integrates the new strategy for abdominal signal acquisition and analysis based on the smart selection of algorithms realized in the mobile instrumentation of PAN. Dependable telemedical systems, when broadly deployed, will provide a high societal value to high-risk pregnant women, especially those in dispersed rural areas.

Is abdominal fetal electrocardiography an alternative to doppler ultrasound for FHR variability evaluation

Fuzzy clustering is often applied to determine the rules of the fuzzy rule-based classifiers (usually the antecedents only). In this work a new fuzzy clustering approach is proposed for such a purpose. The idea consists in alternating clustering of the objects from two classes with the prototypes obtained after the previous clustering not allowed to move during the current clustering. As a result each clustering provides new location of a single prototype. The classification quality obtained by the fuzzy rule-based classifier using the proposed clustering was compared with the Lagrangian SVM method on several benchmark databases.

Selected design issues of the medical cyber-physical system for telemonitoring pregnancy at home

ABSTRACT Cardiotocographic (CTG) monitoring, consisting in analysis of the fetal heart rate, uterine contractions, and fetal movements is the primary noninvasive method for the fetal state assessment. The visual interpretation of the CTG signals is characterized by the large inter- and intraobserver disagreement. Hence, the automated methods supporting the diagnosis process are the topic of researches. In the presented study, the evaluation of the CTG signals, based on fuzzy clustering with pairs of prototypes, is described. The efficiency of the proposed method is verified using two benchmark datasets of the CTG signals (CTU-UHB and SisPorto), and the problems of the two- and three-class classification are considered. The obtained results show the improved quality of the automated fetal state assessment in accordance with the applied reference procedures: the fuzzy (c+p)-means clustering and the Lagrangian Support Vector Machines.