Types of intrapartum hypoxia on the cardiotocograph (CTG): do they have any relationship with the type of brain injury in the MRI scan in term babies?

Yatham, Swetha; Whelehan, Virginia; Archer, Abigail; Chandraharan, Edwin

doi:10.1080/01443615.2019.1652576

Cited by 21 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This will contribute to delineate better the fetal ability to respond and compensate to an hypoxic insult, which is the corner-stone of intrapartum-CTG. Similar findings were reported in a recent study 19 which analysed 52,187 births over an 11-years period, which reported 81% agreement between clinicians when 'types of hypoxia' were used to classify the CTG-Trace, instead of using guidelines based on 'pattern-recognition'.…”

Section: Importance Of Fetal-physiology Training and Multi-professional Approachsupporting

confidence: 86%

The impact that intense ‘fetal-physiology’ training has on inter-observer agreement in interpreting intrapartum cardiotocograph traces in comparison to the classical ‘pattern-recognition’ approach: a prospective observational study

Henares¹,

Gomez²,

Chandraharan³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: To explore the level of agreement as well as the contribution of human-factors on CTG interpretation in a hospital where a high intense, 'fetal physiology-based' training on CTG-interpretation was implemented by a dedicated CTG-Team. Design: Prospective observational study Setting: Tertiary Hospital, UK Population: A total of 25 midwives and 7 doctors ([?]10% of staff) Method: interpretation of 5 anonymised colour-printed copies of 5 different CTGs using a questionnaire (160 CTG interpretations) using local CTG-guidelines (pattern-recognition approach) and Types of hypoxia (fetal-physiology).Results: Interpretation of CTG by type of hypoxia compared against CTG-guidelines presented better Proportion of concordance (PC=76.1% vs 61.2%, P=0.006) and slightly better reliability (K= 0.37 (0.35-0.39) vs 0.33 (0.32-0.36)). Doctors rely most in fetal-physiology than midwives who rely most in guidelines. Overall, 68% of the staff felt confident or very confident in CTG interpretation. In general, Self-reported confidence on CTG interpretation and fetal-physiology knowledge increased with the level of seniority. Conclusions: 'Fetal-physiology-based' training increases level of self-reported confidence and level of fetal-physiology knowledge leading to better inter-observer agreement and reliability in CTG interpretation especially when considering type of hypoxia in CTG-classification. Funding: JG collected the data as part of a Self-funded university MSc program. A secondary analysis of the data was performed to elaborate this manuscript.

show abstract

Section: Importance Of Fetal-physiology Training and Multi-professional Approachsupporting

confidence: 86%

The impact that intense ‘fetal-physiology’ training has on inter-observer agreement in interpreting intrapartum cardiotocograph traces in comparison to the classical ‘pattern-recognition’ approach: a prospective observational study

Henares¹,

Gomez²,

Chandraharan³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…overlapping windows of 15-30 min segments), as there is a significant risk of introducing predominantly noisy labels, unless the fetal hypoxia is chronic and prevalent throughout the duration of the recording. Furthermore, studies have shown that not all infants diagnosed postnatally with HIE have evidence of intrapartum hypoxia in the CTG (using current human interpretation) (Yatham et al, 2020). Machine learning architectures that use hand-labelled CTG at an event/epoch level by an expert annotator would result in stronger labels and, in theory, achieve improved performance.…”

Section: Weak Labels Versus Expert Annotated Labelsmentioning

confidence: 99%

“…However, introducing human labels may result in similar clinical outcomes to those observed in the prior RCTs, whereby high algorithm-human agreement is achieved but it is akin to adding a second evaluator with similar instructions. Similarly, multiple studies have shown inter-observer agreement for human CTG interpretation in the range of 30-50% (Yatham et al, 2020) (Hruban et al, 2015) (Rhöse et al, 2014). Therefore, there is a risk that human annotations may introduce human bias into the classification, given that expert use of CTG in general is still widely debated (Garcia-Canadilla et al, 2020).…”

Section: Weak Labels Versus Expert Annotated Labelsmentioning

confidence: 99%

“…pH < 7.05), regardless of the duration of the CTG abnormality, or the type of hypoxia. Different types of fetal hypoxia (acute, subacute, evolving, chronic) generally manifest in different forms in the CTG, and are associated with widely differing clinical events ( Yatham et al, 2020 ). This introduces problems, as in an acute event (such as cord prolapse, uterine rupture, or acute cord compression) the CTG may only change during the event.…”

Section: Challenges In Ai For Ctgmentioning

confidence: 99%

See 1 more Smart Citation

Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring

O'Sullivan

Considine

O'Riordan

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Background: CTG remains the only non-invasive tool available to the maternity team for continuous monitoring of fetal well-being during labour. Despite widespread use and investment in staff training, difficulty with CTG interpretation continues to be identified as a problem in cases of fetal hypoxia, which often results in permanent brain injury. Given the recent advances in AI, it is hoped that its application to CTG will offer a better, less subjective and more reliable method of CTG interpretation.Objectives: This mini-review examines the literature and discusses the impediments to the success of AI application to CTG thus far. Prior randomised control trials (RCTs) of CTG decision support systems are reviewed from technical and clinical perspectives. A selection of novel engineering approaches, not yet validated in RCTs, are also reviewed. The review presents the key challenges that need to be addressed in order to develop a robust AI tool to identify fetal distress in a timely manner so that appropriate intervention can be made.Results: The decision support systems used in three RCTs were reviewed, summarising the algorithms, the outcomes of the trials and the limitations. Preliminary work suggests that the inclusion of clinical data can improve the performance of AI-assisted CTG. Combined with newer approaches to the classification of traces, this offers promise for rewarding future development.

show abstract

“…Instead of using terminologies such as "suspicious CTGs" and "uncomplicated tachycardias", clinicians should scrutinise the CTG trace for abnormal features such as absence of fetal heart rate cycling to diagnose subclinical chorioamnionitis [14]. Similarly, developing a deeper understanding of fetal pathophysiology and classifying the CTG traces based on the 'Types of Intrapartum Hypoxia" [15] instead of randomly grouping features to classify CTG traces into "Normal", "Suspicious", "Pathological", will help obviate the need for maternal administration of water and oxygen to treat CTG abnormalities.…”

Section: Fig 1 Potential Detrimental Effects Of Maternal Fluid and Oxygen Therapy To Treat Fetal Heart Rate Abnormalities On The Ctg Tracmentioning

confidence: 99%

Maternal “Oxygen and Fluids Therapy” to Correct Abnormalities in the Cardiotocograph (CTG): Scientific Principles vs Historical (Mal) Practices

Chandraharan

2020

JAMMR

Self Cite

View full text Add to dashboard Cite

Some Guidelines on Cardiotocograph (CTG) trace continue to recommend the administration of oxygen and fluids to the mother to correct the abnormalities observed on the cardiotocograph. However, the fetus has a separate autonomic nervous system, blood volume, haemoglobin concentration, oxygen saturation and cardiovascular responses as compared to the mother. Therefore, administration of oxygen and fluids to the mother to correct observed “suspicious” CTG traces should be questioned in contemporary obstetric practice. This commentary examines the scientific principles and current scientific evidence on these historical practices, and all practising midwives and obstetricians should urgently review their individual clinical practice, based on the knowledge of anatomy, physiology and biochemistry as well as a critical review of current scientific evidence to prevent avoidable patient harm. Current evidence suggests that administration of oxygen to the mother, who has a normal oxygen saturation does not correct the observed abnormalities on the CTG trace, and it may in fact lead to harm. Similarly, administration of fluids (oral or intravenous) to a woman during labour who is not dehydrated or hypotensive may not only cause maternal dilutional hyponatremia and resultant complications, but also, it may cause neonatal convulsions. Women and babies expect every healthcare provider to practice evidence-based medicine during the intrapartum period, which is based on logic, common sense and robust scientific principles, irrespective of what is erroneously stated by some CTG guidelines.

show abstract

Types of intrapartum hypoxia on the cardiotocograph (CTG): do they have any relationship with the type of brain injury in the MRI scan in term babies?

Cited by 21 publications

References 12 publications

The impact that intense ‘fetal-physiology’ training has on inter-observer agreement in interpreting intrapartum cardiotocograph traces in comparison to the classical ‘pattern-recognition’ approach: a prospective observational study

The impact that intense ‘fetal-physiology’ training has on inter-observer agreement in interpreting intrapartum cardiotocograph traces in comparison to the classical ‘pattern-recognition’ approach: a prospective observational study

Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring

Maternal “Oxygen and Fluids Therapy” to Correct Abnormalities in the Cardiotocograph (CTG): Scientific Principles vs Historical (Mal) Practices

Contact Info

Product

Resources

About