Computerised analysis of antepartum foetal heart parameters: New reference ranges

Giuliano, Natascia; Annunziata, Maria Laura; Esposito, Francesca; Tagliaferri, Salvatore; Lieto, Andrea Di; Magenes, Giovanni; Signorini, M.G.; Campanile, Marta; Arduini, Domenico

doi:10.1080/01443615.2016.1239069

Cited by 8 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This assumption stands considering both the whole cohort but even when limiting the analysis to the considered IUGR population as reported in Table 2 . The reason behind feature adjustment for GA_CTG relies on previous studies showing the evolution of linear and nonlinear indices throughout pregnancy [32,33] .…”

Section: Selection and Statistical Preprocessing Of Featuresmentioning

confidence: 99%

Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring

Signorini

Pini

Malovini

et al. 2020

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

Background and objectives: Intrauterine Growth Restriction (IUGR) is a fetal condition defined as the abnormal rate of fetal growth. The pathology is a documented cause of fetal and neonatal morbidity and mortality. In clinical practice, diagnosis is confirmed at birth and may only be suspected during pregnancy. Therefore, designing an accurate model for the early and prompt identification of pathology in the antepartum period is crucial in view of pregnancy management. Methods: We tested the performance of 15 machine learning techniques in discriminating healthy versus IUGR fetuses. The various models were trained with a set of 12 physiology based heart rate features extracted from a single antepartum CardioTocographic (CTG) recording. The reason for the utilization of time, frequency, and nonlinear indices is based on their standalone documented ability to describe several physiological and pathological fetal conditions. Results: We validated our approach on a database of 60 healthy and 60 IUGR fetuses. The machine learning methodology achieving the best performance was Random Forests. Specifically, we obtained a mean classification accuracy of 0.911 [0.860, 0.961 (0.95 confidence interval)] averaged over 10 test sets (10 Fold Cross Validation). Similar results were provided by Classification Trees, Logistic Regression, and Support Vector Machines. A features ranking procedure highlighted that nonlinear indices showed the highest capability to discriminate between the considered fetal conditions. Nevertheless, is the combination of features investigating CTG signal in different domains, that contributes to an increase in classification accuracy. Conclusions: We provided validation of an accurate artificially intelligence framework for the diagnosis of IUGR condition in the antepartum period. The employed physiology based heart rate features constitute an interpretable link between the machine learning results and the quantitative estimators of fetal wellbeing.

show abstract

Section: Selection and Statistical Preprocessing Of Featuresmentioning

confidence: 99%

Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring

Signorini

Pini

Malovini

et al. 2020

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are only a few papers, which analyse sensitivity, specificity, PPV and NPV of CTG parameters. Giuliano et al [12], analyses 9 parameters of CTG (including STV); in healthy pregnancies from 30 th to 42 nd gestational week, with specificity and NPV: 89%, 93.7% respectively. One might spot a problem concerning a group of preterm pregnanciessensitivity, specificity, positive predictive value and negative predictive value are similar.…”

Section: Discussionmentioning

confidence: 99%

The relevance of Short-Term Variation (STV) value measured within 1 hour before delivery in predicting adverse neonatal outcome

et al. 2021

View full text Add to dashboard Cite

Objectives: Computer CTG analysis (cCTG) included short-term variation (STV) is one of the methods of monitoring fetal condition during delivery. The aim of our study was to define appropriability of STV measured within 1 hour before delivery in prediction of neonatal outcomes. Material and methods:The retrospective study included 1014 pregnant women, who gave birth in the Department of Obstetrics and Perinatology. Participants were divided into two groups: group 1term pregnancies (37-41 weeks) and group 2preterm pregnancies (lower than 37 weeks). In each of them, two subgroups have been separated: control (STV ≥ 3 ms) and study group (STV < 3 ms).Results: In both groups 1 and 2, there were no statistically significant differences related to Apgar scores in 1 st , 3 rd and 5 th minute between group with STV < 3 ms and group with STV > 3 ms Moreover, for 37-41 weeks the sensitivity, specificity, positive predictive value and negative predictive value were: 22.7%, 83.9%, 3.3% and 97.8% and for lower than 37: 45.7%, 65.4%, 47.1%, 64.2% in 1 th minute after delivery. In group 1 the area under curve (AUC) measurements were 0.45 (95% CI: 0.32-0.58) for 1 st minute and 0.55 (95% CI: 0.35-0.74) for 5 th minute and in group 2: 0.58 (95% CI: 0.45-0.71) for 1th minute and 0.57 (95% CI: 0.42-0.72) for 5 th minute.Conclusions: High specificity and negative predictive value of STV indicates a good Apgar score of newborns in term pregnancies. Analysis of STV in preterm pregnancy is not clear.Fetal well-being in preterm pregnancy should include STV and other non-invasive and invasive tools.

show abstract

“…Normal FHR baseline is indicated as normal in the ranges of 110 to 160 beats per minute (bpm) (10). Computerized CTG is an automatic analysis tool that provides further diagnostic criteria and objective parameters: the baseline fetal heart rate (Basal FHR), the accelerations and decelerations, the long-term FHR variation (LTV), the short-term FHR variation (STV), the episodes of high/low FHR variation, and the number of fetal movements for an hour (FM) (11). We hypothesize the possible analytical correlation between the presence of the fetal hiccups and the maternal perception of the fetal movements can be identified and so applied for future fetal well-being monitoring.…”

Section: Introductionmentioning

confidence: 99%

Objective and quantitative evaluation of fetal hiccups by computerized cardiotocography: a prospective observational study

Riemma

2021

It Journ Gyn Obs

View full text Add to dashboard Cite

The physiological function of fetal hiccup and its correlation with fetal well-being is a debated topic. We conducted a prospective observational study in a Tertiary care University Hospital to correlate the fetal hiccups with the antepartum computerized cardiotocography parameters. Fifty-one nonlaboring women with a term pregnancy were enrolled. We collected data regarding maternal perception of fetal hiccups and the computerized cardiotocographic examination. The pregnant were divided into three groups depending on fetal hiccups perception. There was a statistical difference for the number of fetal movements in an hour between the group of daily perception and the group of no perception. Changes in fetal movements frequency are essential to recognize pregnancies at increased risk for adverse fetal outcomes. No one studies in the medical literature utilized the computerized cardiotocographic machine to explore fetal hiccups. Then our study showed that a mother with daily fetal hiccups could be considered a low risk considering the significant numbers of fetal movements revealed by computerized cardiotocography. Nevertheless, randomized controlled trials are required to evaluate the fetal hiccups evaluation and its influence on fetal outcomes.

show abstract

Computerised analysis of antepartum foetal heart parameters: New reference ranges

Cited by 8 publications

References 40 publications

Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring

Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring

The relevance of Short-Term Variation (STV) value measured within 1 hour before delivery in predicting adverse neonatal outcome

Objective and quantitative evaluation of fetal hiccups by computerized cardiotocography: a prospective observational study

Contact Info

Product

Resources

About