Software for computerised analysis of cardiotocographic traces

Romano, Maria; Bifulco, Paolo; Ruffo, M.; Improta, Giovanni; Clemente, Fabrizio; Cesarelli, Mario

doi:10.1016/j.cmpb.2015.10.008

Cited by 44 publications

(27 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CTG signals were processed by software previously developed by the authors [ 7 , 84 ]. Firstly, they were preprocessed by means of a software [ 10 , 84 ] which processes signals in output from the cardiotocographs in order to recognize signal tracts having good and bad quality (these last including tracts of signal loss); for each segment of good quality, recover the real uneven FHR series when CTG output is evenly spaced (case of HP/Philips cardiotocographs) [ 87 ] and detect and process outliers [ 88 ]; interpolate signal tracts of poor quality (according to an index provided by the equipment) or signal loss which last maximum 3 s, in order to avoid an excessive fragmentation of the signal.…”

Section: Methodsmentioning

confidence: 99%

“…In recent years, hence, interest has grown in how to recognize changes in FHR that might predict more accurately foetal distress. For example, in order to overcome the subjective nature of FHR interpretation, several attempts have been made to automate the diagnosis of the foetal status and many computerised algorithms have been developed to assess FHR parameters [ 1 , 6 – 10 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Frequency and Time Domain Analysis of Foetal Heart Rate Variability with Traditional Indexes: A Critical Survey

Romano

Iuppariello

Ponsiglione

et al. 2016

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Monitoring of foetal heart rate and its variability (FHRV) covers an important role in assessing health of foetus. Many analysis methods have been used to get quantitative measures of FHRV. FHRV has been studied in time and in frequency domain and interesting clinical results have been obtained. Nevertheless, a standardized definition of FHRV and a precise methodology to be used for its evaluation are lacking. We carried out a literature overview about both frequency domain analysis (FDA) and time domain analysis (TDA). Then, by using simulated FHR signals, we defined the methodology for FDA. Further, employing more than 400 real FHR signals, we analysed some of the most common indexes, Short Term Variability for TDA and power content of the spectrum bands and sympathovagal balance for FDA, and evaluated their ranges of values, which in many cases are a novelty. Finally, we verified the relationship between these indexes and two important parameters: week of gestation, indicator of foetal growth, and foetal state, classified as active or at rest. Our results indicate that, according to literature, it is necessary to standardize the procedure for FHRV evaluation and to consider week of gestation and foetal state before FHR analysis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Frequency and Time Domain Analysis of Foetal Heart Rate Variability with Traditional Indexes: A Critical Survey

Romano

Iuppariello

Ponsiglione

et al. 2016

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Since at the time of fetal monitoring, there is no other diagnostic method which could be able to confirm a correctness of the signal classification, the FHR signals, being acquired during pregnancy, are retrospectively assigned to true fetal outcome (newborn state) (Chudacek et al, 2014; Romano et al, 2016a). It is justified, as in obstetrics it is assumed that the normal fetal outcome has to be result of proper fetal development during the pregnancy period.…”

Section: Methodsmentioning

confidence: 99%

“…More important was to ensure the trace continuity which allowed clinicians to observe a general tendency of the fetal heart rate changes, and to recognize the features representing longitudinal FHR patterns relating to the fetal state, like acceleration or deceleration. It was found that the evaluation of fetal state, when based on visual interpretation, has been mainly affected by low inter- and intra-observer agreement (Jezewski et al, 2002; Romano et al, 2016a). That was a result of both complexity of the FHR signal and the fact that important part of information relating to instantaneous changes of FHR values has been hidden from a naked eye.…”

Section: Introductionmentioning

confidence: 99%

Is Abdominal Fetal Electrocardiography an Alternative to Doppler Ultrasound for FHR Variability Evaluation?

et al. 2017

View full text Add to dashboard Cite

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.

show abstract

“…Computerised CTG has played a significant role in developing objective measures as a function of CTG signals [14], particularly within the machine learning community [15]- [18], [7], [12], [19]- [23]. According to a Cochrane report in 2015, computerised interpretation of CTG traces significantly reduced perinatal mortality [24].…”

Section: Introductionmentioning

confidence: 99%

Machine learning ensemble modelling to classify caesarean section and vaginal delivery types using Cardiotocography traces

Fergus

Selvaraj

Chalmers

2018

Computers in Biology and Medicine

View full text Add to dashboard Cite

Human visual inspection of Cardiotocography traces is used to monitor the foetus during labour and avoid neonatal mortality and morbidity. The problem, however, is that visual interpretation of Cardiotocography traces is subject to high inter and intra observer variability. Incorrect decisions, caused by miss-interpretation, can lead to adverse perinatal outcomes and in severe cases death. This study presents a review of human Cardiotocography trace interpretation and argues that machine learning, used as a decision support system by obstetricians and midwives, may provide an objective measure alongside normal practices. This will help to increase predictive capacity and reduce negative outcomes. A robust methodology is presented for feature set engineering using an open database comprising 552 intrapartum recordings. State-of-the-art in signal processing techniques is applied to raw Cardiotocography foetal heart rate traces to extract 13 features. Those with low discriminative capacity are removed using Recursive Feature Elimination. The dataset is imbalanced with significant differences between the prior probabilities of both normal deliveries and those delivered by caesarean section. This issue is addressed by oversampling the training instances using a synthetic minority oversampling technique to provide a balanced class distribution. Several simple, yet powerful, machine-learning algorithms are trained, using the feature set, and their performance is evaluated with real test data. The results are encouraging using an ensemble classifier comprising Fishers Linear Discriminant Analysis, Random Forest and Support Vector Machine classifiers, with 87% (95% Confidence Interval: 86%, 88%) for Sensitivity, 90% (95% CI: 89%, 91%) for Specificity, and 96% (95% CI: 96%, 97%) for the Area Under the Curve, with a 9% (95% CI: 9%, 10%) Mean Square Error.

show abstract

Software for computerised analysis of cardiotocographic traces

Cited by 44 publications

References 44 publications

Frequency and Time Domain Analysis of Foetal Heart Rate Variability with Traditional Indexes: A Critical Survey

Frequency and Time Domain Analysis of Foetal Heart Rate Variability with Traditional Indexes: A Critical Survey

Is Abdominal Fetal Electrocardiography an Alternative to Doppler Ultrasound for FHR Variability Evaluation?

Machine learning ensemble modelling to classify caesarean section and vaginal delivery types using Cardiotocography traces

Contact Info

Product

Resources

About