Five systems for computer analysis of foetal monitoring signals are currently available, incorporating the evaluation of cardiotocographic (CTG) or combined CTG with electrocardiographic ST data. All systems have been integrated with central monitoring stations, allowing the simultaneous monitoring of several tracings on the same computer screen in multiple hospital locations. Computer analysis elicits real-time visual and sound alerts for health care professionals when abnormal patterns are detected, with the aim of prompting a re-evaluation and subsequent clinical action, if considered necessary. Comparison between the CTG analyses provided by the computer and clinical experts has been carried out in all systems, and in three of them, the accuracy of computer alerts in predicting newborn outcomes was evaluated. Comparisons between these studies are hampered by the differences in selection criteria and outcomes. Two of these systems have just completed multicentre randomised clinical trials comparing them with conventional CTG monitoring, and their results are awaited shortly. For the time being, there is limited evidence regarding the impact of computer analysis of foetal monitoring signals on perinatal indicators and on health care professionals’ behaviour.
Highlights
- •
Computer analysis was developed to overcome the limitations of visual analysis.
- •
A small number of systems exist integrated with central monitoring stations.
- •
Satisfactory results have been reported, when comparing analysis with experts.
- •
A good prediction of newborn outcome has been reported in a small number of studies.
- •
Two systems have completed randomised trials, and their results are expected soon.
Introduction
The development of computer analysis of foetal heart rate (FHR) and uterine contraction signals began in the 1980s , in an attempt to overcome the well-demonstrated subjectivity of visual analysis . The first of these systems was only suitable for the analysis of antepartum cardiotocography (CTG) , where reduced baseline instability, limited signal loss and artefacts and smaller tracing length pose much lesser challenges for signal processing and algorithm development.
Over the last two decades, several systems have been developed for the analysis of intrapartum signals, and many of them have been commercialised, usually in association with foetal central monitoring stations . Continued improvements in computer memory and processing speed have allowed real-time display and analysis of several tracings on the same computer screen, usually for the whole labour ward. Systems have also incorporated real-time visual and sound alerts for the health care professionals, based on the results of computer analysis, in order to raise attention to specific findings, thus promoting tracing re-evaluation and subsequent intervention, if considered necessary.
In this article, we provide an overview of the existing systems for computer analysis of foetal monitoring signals, with particular emphasis on the published research conducted to evaluate them ( Table 1 ).
| System | Display of other Data | Real-time alerts | FHR guidelines | Refs. |
|---|---|---|---|---|
| IntelliSpace Perinatal ® (Philips Healthcare ® , Eindhoven, the Netherlands) | Maternal vital signs, electronic partogram, ST events | Fetal tachycardia, bradycardia, signal loss, abnormal variability, decelerations | NICHHD | |
| Omniview-SisPorto ® (Speculum ® , Lisbon, Portugal) | Maternal vital signs, electronic partogram, foetal oxymetry, ST events | Combined CTG + ST colour-coded alerts: blue, yellow, orange and red | FIGO and STAN | |
| PeriCALM ™ (LMS Medical systems, Montreal, Canada and PeriGen, Princeton, USA) | Maternal vital signs, electronic partogram | Colour-coded FHR alerts: blue, yellow, orange and red | NICHHD | |
| INFANT ® (K2 Medical Systems™, Plymouth, UK) | Maternal vital signs, electronic partogram, FBS | Colour-coded FHR alerts: blue, yellow and red | – | |
| Trium CTG Online ® (Trium Analysis Online GmbH, Munich, Germany) | Baseline changes, reduced variability, decelerations and signal loss | FIGO |
IntelliSpace Perinatal ® (Philips Healthcare ® , Eindhoven, the Netherlands)
Housing a central foetal monitoring station that was previously called OBTraceVue, this obstetric database system was developed by Philips Medical ® in collaboration with the Department of Obstetrics and the Laboratory of Computer Science of the Massachusetts General Hospital, MA, USA. In addition to the foetal monitoring software, there is an electronic patient database for all aspects of obstetric care.
For foetal monitoring, computer algorithms detect changes in baseline, variability, accelerations and number and type of decelerations and contractions, using criteria based on the National Institute of Child Health and Human Development (NICHHD) guidelines . Alarms are elicited for foetal tachycardia, bradycardia, signal loss, abnormal variability, decelerations and detection of coincidences between foetal and maternal heart rates ( Fig. 1 ). ( http://www.healthcare.philips.com/main/products/patient_monitoring/products/intellispace_cca/obstetrics/ . Accessed 3 December 2014.)
Devoe et al. compared the visual analyses of 50 1-h intrapartum tracings by four observers, among each other, and with the system. Overall levels of inter-observer agreement for baseline heart rate were between 97.3% and 99%, while agreement between individual observers and the computer ranged between 83.5% and 88.1%. For accelerations, inter-observer agreement ranged from 47.2% to 61.8%, while agreement between observers and the computer ranged from 49.5% to 62.3%. For decelerations, inter-observer agreement varied between 43.1% and 66.5%, while agreement between observers and the computer ranged between 35.8% and 51.1%. Regarding the occurrence of alerts within a 20-min window, inter-observer agreement varied between 71.7% and 83.8%, while agreement between observers and the computer ranged from 76.9% to 79.2%, the latter with a kappa statistic of 0.25 (95% confidence intervals (CI) 0.19–0.30).
IntelliSpace Perinatal ® (Philips Healthcare ® , Eindhoven, the Netherlands)
Housing a central foetal monitoring station that was previously called OBTraceVue, this obstetric database system was developed by Philips Medical ® in collaboration with the Department of Obstetrics and the Laboratory of Computer Science of the Massachusetts General Hospital, MA, USA. In addition to the foetal monitoring software, there is an electronic patient database for all aspects of obstetric care.
For foetal monitoring, computer algorithms detect changes in baseline, variability, accelerations and number and type of decelerations and contractions, using criteria based on the National Institute of Child Health and Human Development (NICHHD) guidelines . Alarms are elicited for foetal tachycardia, bradycardia, signal loss, abnormal variability, decelerations and detection of coincidences between foetal and maternal heart rates ( Fig. 1 ). ( http://www.healthcare.philips.com/main/products/patient_monitoring/products/intellispace_cca/obstetrics/ . Accessed 3 December 2014.)
Devoe et al. compared the visual analyses of 50 1-h intrapartum tracings by four observers, among each other, and with the system. Overall levels of inter-observer agreement for baseline heart rate were between 97.3% and 99%, while agreement between individual observers and the computer ranged between 83.5% and 88.1%. For accelerations, inter-observer agreement ranged from 47.2% to 61.8%, while agreement between observers and the computer ranged from 49.5% to 62.3%. For decelerations, inter-observer agreement varied between 43.1% and 66.5%, while agreement between observers and the computer ranged between 35.8% and 51.1%. Regarding the occurrence of alerts within a 20-min window, inter-observer agreement varied between 71.7% and 83.8%, while agreement between observers and the computer ranged from 76.9% to 79.2%, the latter with a kappa statistic of 0.25 (95% confidence intervals (CI) 0.19–0.30).
Omniview-SisPorto ® (Speculum ® , Lisbon, Portugal)
This system was developed at the Institute of Biomedical Engineering of the University of Porto, in Portugal . CTG analysis is inspired on the International Federation of Obstetrics and Gynecology (FIGO) guidelines for foetal monitoring , incorporating baseline estimation, identification of accelerations and decelerations, evaluation of long- and short-term variability and detection of contractions ( Fig. 2 ). The system provides real-time visual and sound alerts of different colour codes . Combined alerts, integrating CTG and foetal electrocardiography-derived ST events (STAN, Neoventa ® , Gothenburg, Sweden), have also been incorporated, based on the revised STAN guidelines . ( http://www.speculum.pt/omniview . Accessed 3 December 2014.)
