The development and implementation of an expert system for the analysis of umbilical cord blood.

An assessment of neonatal outcome may be obtained from analysis of blood in the umbilical cord of the infant immediately after delivery. This can provide information on the health of the newborn infant, guide requirements for neonatal care, and is recommended practice of the Royal College of Obstetricians and Gynaecologists. However, there are problems with the technique. Samples frequently contain errors in one or more of the important parameters, preventing accurate interpretation and many clinical staff lack the expert knowledge required to interpret error-free results. In this paper the development and implementation of an expert system to overcome these difficulties is described. The expert system validates results, provides a textual interpretation and archives all results to database for audit, research and medico-legal purposes. The system has now been in routine clinical use for over 3 years in Plymouth, and has also been installed in several other hospitals in the UK. Results are presented in which the types and frequency of errors are established and the user acceptance of the system is determined.

Scalp blood gas analysis.

The use of fetal blood sampling has been advocated widely to improve the specificity of fetal heart rate monitoring, but it remains a clinically unpopular procedure. This article considers its physiologic rationale and evidence base. It includes descriptions of the technique with suggestions for improved clinical interpretation and discusses the efficacy of fetal blood sampling with some consideration of possible alternatives.

Fetal pulse oximetry--a preliminary report on sensor precision determined by dual sensor studies.

OBJECTIVE: The objective of the study was to test the clinical reproducibility of intrapartum fetal pulse oximetry. STUDY DESIGN: This observational study was performed on the labour ward and 27 women were recruited. After obtaining written consent two sensors were placed on the same fetus. RESULTS: More than 82 h of valid paired data was obtained and preliminary analysis is presented. The mean signed difference between dual sensors was -0.04%Sat (S.D. 8.12%Sat) The precision for a single sensor was +/-5.74%Sat. The most common absolute saturation difference was 1%Sat (median: 46%Sat, 5th and 95th centiles: 29 and 60%Sat, respectively). Occasions when the difference was outside 2 S.D. were of short duration. CONCLUSIONS: There is good clinical reproducibility with the latest sensor design. The frequency distribution of oxygen saturation values lends support to 30-60%Sat as the normal range in the human fetus.

Suitability of artificial neural networks for feature extraction from cardiotocogram during labour.

Fetal condition during labour is inferred from a continuous display of fetal heart rate and uterine contractions called the cardiotocogram (CTG). The CTG requires a considerable expertise for correct interpretation, which is not always available. We are developing an intelligent system to support clinical decision-making during labour. The system's performance depends on its ability to classify features from the CTG similarly to experts. Artificial neural networks (NNs) can be taught by experts for such tasks, and so may be particularly suitable. We found NNs suitable for feature extraction when the problem was reduced to small well defined tasks, and numerical algorithms were used to pre-process the raw data before application to the NNs. A NN with optimised dimensions was used in this way to classify the magnitude of decelerations, a feature clinicians find particularly difficult. The NN was compared with the algorithm used in a commercial antenatal monitor and six reviewers which included two CTG experts. The experts were consistent (89.7% and 97.0%) and agreed well with each other (81.0%), whereas the non-experts were less consistent and agreed less well. The NN agreed well with the experts (75.0% and 81.9%) but the algorithm agreed poorly (56.5% and 68.9%). It was found that the algorithm's performance could be improved (72.1% and 76.7%) when modified to use additional information. Our earlier attempts to fully classify the raw CTG using a single NN were unsuccessful because of the large number of data patterns. A simplified approach to classify the magnitude and timing of decelerations was also unsuitable when contraction data was of poor quality or absent.(ABSTRACT TRUNCATED AT 250 WORDS)

Umbilical cord blood gas analysis at the time of delivery.

AIMS: it is now recommended that cord blood acid-base measurement is performed routinely at time of delivery in the UK as a measure of fetal response to labour. However, there remains some uncertainty about the value of this procedure. In this paper our experience of cord blood analysis is described and the literature is reviewed to: (1) provide an overview of the physiological basis of cord blood acid-base assessment; (2) describe the appropriate methodology and identify issues which have contributed to confusion and undermined the value of cord blood sampling; and (3) address the practical issues of cord blood sampling. CONCLUSIONS: cord blood acid-base measurement has a sound physiological basis. It provides objective information which is a useful adjunct to subjective methods of newborn assessment, enables babies at risk of neonatal morbidity to be identified, can be helpful in litigation cases and is a prerequisite for clinical audit. However, to be of benefit the information must be correct and correctly interpreted.

Intelligent fetal heart rate computer systems in intrapartum surveillance.

The intrapartum cardiotocogram has had a disappointing impact on clinical practice. Misinterpretation of the cardiotocogram not only causes an increase in unnecessary intervention but is also implicated in a large proportion of patients with birth asphyxia and avoidable perinatal morbidity. Over the past 10-20 years, groups have attempted to develop computer systems capable of analysing the cardiotocogram but with limited success. The likely explanation is that these conventional systems analyse the cardiotocogram in isolation from clinical factors. More recently, research has focused on the use of artificial intelligence techniques which can assess the whole clinical picture to support clinical decision making during labour. The current literature is reviewed and a system that has been validated by comparison of its performance with 17 experts is described.

The ECG waveform.

Different portions of the ECG waveform are influenced differently. The QRS waveform is influenced principally by ventricular muscle mass but may be influenced by differences in ventricular filling which occur with cardiac failure or transiently with cord compression. The PR interval normally has a positive correlation with the R-R interval but this correlation becomes negative, probably as a result of catecholamines, when the fetus is stressed. This difference between PR/RR correlation may help distinguish vagally mediated decelerations from those associated with hypoxia. The ST waveform becomes elevated when myocardial oxygen delivery is insufficient to maintain aerobic metabolism to meet the energy demands of the myocardium, and anaerobic metabolism occurs with the production of lactate; this is a dynamic situation and may occur at different levels of oxygenation in different fetuses, depending on their ability to compensate and the workload on the myocardium. It is very likely that changes in PR/RR relationships and the ST waveform will be useful in intrapartum monitoring in the future, and this contention is supported by recent analysis of PR/RR and ST segment shifts (Figure 16). It seems clear that the detailed study of the ECG waveform provides more, and perhaps clinically more useful, information from the same signal and electrode as heart rate, and it is no longer reasonable to ignore it. However, as clinicians we have an extraordinary ability to move with disenchantment from one method of fetal monitoring to another of no proven value, with a firm but unreasoned conviction that it is better. ECG analysis is by no means ready for clinical use if we are to avoid the same pitfalls as continuous FHR monitoring. Further clinical assessment will not be easy. In modern obstetric practice asphyxiated infants are fortunately not common, so there are practical difficulties in monitoring sufficient numbers of patients to evaluate new indices of asphyxia, as well as the difficulties of defining an objective endpoint. Thorough clinical (probably multicentre) studies are needed with well defined endpoints and this is beginning. Further fetal lamb studies are also needed, particularly to examine the interrelationships between changes in heart rate, PR interval and ST waveform; it is hoped that this chapter has emphasized the importance of such animal studies in understanding the physiological and therefore clinical background to any change.(ABSTRACT TRUNCATED AT 400 WORDS)

Development, evaluation and validation of an intelligent system for the management of labour.

Over the past 4 years our group has developed a prototype intelligent system which applies captured expert knowledge to support clinical decision-making during labour. This chapter presents a review of the system and the progress made to date. The system classifies the same features from the CTG as experienced clinicians using numerical algorithms and a small neural network. This hybrid approach has been shown to obtain a comparable performance with experts. The CTG information, together with the patient information and labour events, are collectively passed to an expert system for processing. The expert system interprets this combined data using a database of over 400 rules which are used to recommend action. Importantly, as the knowledge is rule-based, it allows the system to explain the reasoning which led it to recommend a certain action. In this way, the clinician is not expected to blindly follow the system's recommendations but can reach an informed judgement in the same way they might by discussing the case with an experienced informed colleague. After two internal evaluations had found the system obtained a performance comparable with local experts, an extensive external validation was undertaken. This study involved 17 experts from 16 leading centres within the UK. Each expert and the system reviewed 50 cases twice, at least one month apart which contained those CTGs considered most difficult to interpret selected from a database of 2400 high-risk labours. This study found that the majority of experts agreed well and were consistent in their management of the cases. The system obtained a performance that was indistinguishable from the experts, except it was more consistent, even when used by an engineer with little knowledge of labour management. This study demonstrates the potential for intelligent systems to transform the cardiotocograph from a difficult-to-use, ineffective recorder of fetal heart rate, to an interactive and effective decision support tool capable of raising the skills of staff.

Long-term ST waveform changes in the ovine fetal electrocardiogram: the relationship to spontaneous labour and intrauterine death.

The experimental evaluation of the fetal ECG waveform as a method of fetal surveillance has been based largely on experimentally induced hypoxia. The present data, obtained from chronically instrumented fetal lambs, includes three fetuses monitored throughout spontaneous labour, six fetuses with spontaneously developed long-term ST waveform changes and another three fetuses which died in the post-operative period. Uterine contractions could by themselves cause an increase in T wave height (T/QRS ratio greater than 0.30). If the ST elevation was normalised between contractions the fetus seemed to compensate to a moderate degree of hypoxia. When oxygenation was further reduced the T wave remained elevated between contractions and a progressive increase occurred in the T/QRS ratio (greater than 0.60) during the final stages of labour, in parallel with increasing blood lactate levels. Long-term ST changes with T/QRS consistently exceeding 0.30 were found to be related to low haemoglobin levels and/or fetal hypotension. Subsequently, all these fetuses died during labour as compared with a survival rate of 40% in fetuses showing a normal ST waveform. In this group negative T waves are reported as a sign of failing myocardial response to hypoxia. Death in utero, whatever the cause (bleeding, infection or spontaneous hypoxia) was always preceded by marked ST waveform changes. It is concluded that ST elevation with high peaked T waves can appear on a long-term basis in fetuses with intrauterine complications.

Umbilical cord blood gas analysis at delivery: a time for quality data.

OBJECTIVES: To address the practical problems of routine umbilical cord blood sampling, to determine the ranges for pH, PCO2 and base deficit and to examine the relationships of these parameters between cord vessels. DESIGN: An observational study of umbilical cord artery and vein blood gas results. SETTING: A large district general hospital in the UK. SUBJECTS: One thousand nine hundred and forty-two cord results from 2013 consecutive pregnancies of 34 weeks or more gestation, monitored by fetal scalp electrode during labour. RESULTS: Only 1448 (74.6%) of the 1942 supposedly paired samples had validated pH and PCO2 data both from an artery and the vein; 54 (2.8%) had only one blood sample available, 90 (4.6%) had an error in the pH or PCO2 of one vessel and in 350 (18%) pairs the differences between vessels indicated that they were not sampled from artery and vein as intended. Only 60% of the cases with an arterial pH less than 7.05 had evidence of a metabolic acidosis (base deficit in the extracellular fluid 10 mmol/l or more). Of all the cases, 2.5% had a venous-arterial pH difference greater than 0.22 units. CONCLUSIONS: Both artery and vein cord samples must be taken and the results screened to ensure separate vessels have been sampled. Interpretation of the results requires the examination of PCO2 and base deficit of the extracellular fluid from each vessel as well as the pH. Confusion about the value of cord gas measurements may be due to the use of erroneous data and inadequate definitions of acidosis which do not differentiate between respiratory and metabolic components.

ST waveform changes of the fetal electrocardiogram during labour--a clinical study.

Waveform changes in the fetal electrocardiogram (ECG) are under reassessment as a means of fetal surveillance. The purpose of the study was to identify ST waveform changes from the fetal scalp lead during labour and to compare any change with conventional signs of fetal distress. Two scalp electrodes provided a sufficiently stable signal from which ST waveform changes could be identified and measured as the T/QRS ratio. No infant was clinically hypoxic. Only 26% of the 46 patients studied had a continuously normal CTG whereas 67% had no ST waveform abnormalities. A relation was found between the two variables as the mean T/QRS ratio increased from 0.20 (SD 0.11) during epochs of normal CTG to 0.27 (SD 0.17) with CTG changes. A linear correlation (r = 0.58, P less than 0.01) was found between the T/QRS ratio before birth and the cord plasma lactate values.

Randomised trial of cardiotocography alone or with ST waveform analysis for intrapartum monitoring.

It is possible to record the fetal electrocardiographic waveform (ECG) from the scalp electrode used in labour for detection of fetal heart rate. Animal and observational studies of changes in the ST waveform of the ECG during hypoxia suggest that a combination of heart rate and ST waveform analysis might improve the predictive value of intrapartum monitoring. In a randomised trial, we have studied intervention rates and neonatal outcome for high-risk labours monitored either by conventional cardiotocography (CTG) or by ST waveform analysis plus CTG. 1200 women with pregnancy of at least 34 weeks' gestation were assigned to the groups when the decision to apply a fetal scalp electrode was made. Neonatal outcome was assessed by umbilical-cord blood gas analysis, Apgar scores, resuscitation needed, and postnatal course. All recordings were retrospectively viewed by an observer unaware of clinical details to check adherence to the trial protocol. The addition of ST waveform monitoring to CTG substantially reduced the proportion of deliveries for fetal distress (ST + CTG 27/615 vs CTG 58/606; p less than 0.001). The groups did not differ in rate of operative delivery for other reasons, incidence of asphyxia at birth, or neonatal outcome. Metabolic acidosis and low 5 min Apgar scores were less common in the ST + CTG than the CTG group, but not significantly so. The only case of birth asphyxia in the ST + CTG group was identified by both heart rate and ST changes. The review of recordings showed that the reduction in intervention rate was among cases with CTG patterns classified as normal or intermediate, whereas there was no difference in intervention rates among cases with abnormal recordings. Our findings confirm that ST waveform analysis discriminates CTG changes in labour and that our protocol for interpretation is safe. Further randomised studies are warranted.

Preliminary evaluation of an intelligent system for the management of labour.

Over the past 10-15 years, workers using conventional computing approaches have attempted to provide an accurate assessment of fetal condition during labour based on the cardiotocogram (CTG) alone. These have not proved successful perhaps because the correct interpretation of fetal condition also requires physiological knowledge, specific patient information, knowledge of events during labour and considerable practical experience. An intelligent system which considers all the relevant information and embodies expertise may better diagnose fetal condition and support decision making. This study reports the preliminary evaluation of such a system and investigates whether this approach can attain a performance comparable with experienced local clinicians. From a database of 200 high risk labour records, 30 cases were selected; the 9 cases which received clinical intervention for 'fetal-distress' and a further 21 cases selected randomly. The management specified by the system, 3 experienced clinicians (A, B and C) and the actual clinical management were compared in a retrospective blinded review. The experts were found to agree well with each other. Expert A reviewed the cases five months later and was found to be entirely consistent in the management of 28 of the 30 cases. The system's actions were indistinguishable from the experts' and in no case did the system recommend an action not also recommended by at least one experienced reviewer. This study demonstrates the potential of an intelligent system to assist in the management of labour.

Suitability of fetal scalp electrodes for monitoring the fetal electrocardiogram during labour.

As the limitations of heart-rate based intrapartum monitoring have become apparent, there is renewed interest in analysis of the fetal electrocardiographic waveform as obtained from a fetal scalp electrode. A high quality ECG signal is necessary for waveform analysis. This study examined the suitability of five commonly available scalp electrodes for collecting this signal by examining their physical and electrical characteristics, together with a randomised clinical trial in which the ECG trace quality was assessed in 50 patients. The frequency response of Copeland electrodes was such that they attenuate the ECG signal more than the baseline noise. Difficulties were experienced in obtaining optimum attachment and the long, semi-rigid design increased movement artefact resulting in significantly poorer quality ECG signals. Whilst the Hewlett-Packard double spiral electrode had a near ideal frequency response, certain design features made it difficult to apply and remain secure so the clinical signals were of intermediate quality. The Corometrics and Cetro single spirals had the most stable attachment to the scalp and a near ideal frequency response, so produced significantly better signal quality in the clinical trial. Currently, single spiral electrodes are the most suitable for electrocardiographic data collection.

Changes in the ST waveform of the fetal lamb electrocardiogram with hypoxemia.

The ST waveform of the fetal electrocardiogram (ECG) was examined in 10 chronically instrumented fetal lambs from 115 days to term. Averaged ST waveforms were plotted at 5-minute intervals in six fetuses for 2 to 22 days. No diurnal or other rhythms were seen. To correct for changes in signal gain the amplitude of the T wave was measured relative to the amplitude of the QRS complex. The T/QRS ratio was normally less than 0.30. Persistently elevated ST waveforms with a T/QRS range 0.32 to 0.65 preceded fetal death by some days in three fetuses and were associated with anemia and/or hypotension in a further three. In these animals hypoxia produced a further rise in the ST waveform (mean T/QRS, from 0.48 to 0.81) and all died during labor. In lambs with a normal ST waveform there were differences in the response to hypoxia over 1 hour for a similar fall in PO2. In eight experiments the ST segment and T wave increased (mean T/QRS, from 0.17 to 0.59) and promptly reverted to normal with normoxia. There was a significant rise in mean arterial blood pressure, plasma lactate, and glucose and a fall in pH. In four experiments there was little change (mean T/QRS, from 0.19 to 0.25), with a small rise in plasma lactate suggesting that these lambs were able to maintain aerobic myocardial metabolism. Overall there was a strong correlation of the T/QRS ratio to the rate of rise of lactate. These findings complement previous results in the acute fetal lamb preparation and suggest that ST waveform elevation expressed as the T/QRS ratio identifies a change to anerobic myocardial metabolism.

Plymouth randomized trial of cardiotocogram only versus ST waveform plus cardiotocogram for intrapartum monitoring in 2400 cases.

OBJECTIVE: The physiology of changes in the ST waveform of the fetal electrocardiogram has been elucidated in extensive animal and human observational studies. A combination of heart rate and ST waveform analysis might improve the predictive value of intrapartum monitoring. Our purpose was to compare operative intervention and neonatal outcome in labors monitored by the conventional cardiotocogram with those monitored by ST waveform plus the cardiotocogram. STUDY DESIGN: A prospective, randomized clinical trial was performed on 2434 high-risk labors in a district general hospital in Plymouth, England. Statistical analysis was performed by Student t test and chi 2 analysis. RESULTS: There was a 46% reduction (p < 0.001, odds ratio 1.85 [1.35-2.66]) in operative deliveries for "fetal distress" and a trend to less metabolic acidosis (p = 0.09, odds ratio 0.38 [0.13-1.07]) and fewer low 5-minute Apgar scores (p = 0.12, odds ratio 0.62 [0.35-1.08]) in the ST waveform plus cardiotocogram arm. CONCLUSIONS: ST waveform analysis discriminates cardiotocogram changes in labor, and the protocol for interpretation is safe. Further randomized studies are warranted.

A multicentre comparative study of 17 experts and an intelligent computer system for managing labour using the cardiotocogram.

OBJECTIVES: To investigate 1. whether an intelligent computer system could obtain a performance in labour management comparable with experts when using cardiotocograms (CTGs), patient information, and fetal blood sampling and 2. whether experts could be consistent and agree in their management of labour. SUBJECTS: An intelligent computer system and 17 clinicians experienced in fetal monitoring from 16 centres in the UK. DESIGN: Fifty cases with complete intrapartum CTGs and clinical data were reviewed by each expert and the system independently on two occasions, at least one month apart. Each CTG was scored in 15 min segments according to a protocol and estimates of the cervical dilatation and fetal scalp blood pH were given when requested. MAIN OUTCOME MEASURES: Consistency and agreement in the recorded scores, agreement and timing of cases recommended for caesarean sections, fetal blood sampling rates, intervention in cases with poor outcome and intervention in cases with good clinical outcome. RESULTS: The system: 1. Agreed with experts well and significantly better than chance (67.33%, kappa = 0.31, P << 0.001). 2. Was highly consistent (99.16%, kappa = 0.98, P << 0.001) when used by two operators independently. 3. Recommended no unnecessary intervention in cases with normal delivery and good condition (cord artery pH > 7.15, vein pH > 7.20, 5 min Apgar > or = 9 and no resuscitation). This was better than all but two of the experts. 4. Recommended delivery by caesarean section in 11 cases; at least 15 of the 17 experts in each review also recommended caesarean section delivery in these cases. The majority did so within 15 min of the system and two-thirds did so within 30 min. 5. Identified as many of the birth asphyxiated cases (cord arterial pH < 7.05 and BDecf > or = 12, and Apgar score at 5 min < or = 7 with neonatal morbidity) as the majority of experts and one more than was acted upon clinically. The experts were found to be consistent and to agree. There was good agreement in the cases and the timing of caesarean section recommendations. The majority of experts did not recommend operative intervention in cases which had a normal delivery and good outcome, but did recommend operative interventions in 10 of 12 cases delivered with cord arterial pH < 7.05. However, in one of the cases delivered with birth asphyxia, 14 of the 17 experts and the system failed to recommend intervention. CONCLUSIONS: The system's performance was found to be indistinguishable from the experts' in the 50 cases examined, but it was more consistent. This demonstrates the potential for an intelligent computer system to improve the interpretation of the CTG and decrease intervention. Furthermore, the good performance of most experts in this study demonstrates the potential effectiveness of the CTG and raises important questions regarding why the CTG has fallen short of expectations in current practice.