Prediction of labor outcome pilot study: evaluation of primiparous women at term

Gabriel, Assoc. Prof. Habil. Dr. MD. Iliescu Dominic; Belciug, Smaranda; Ivanescu, Mr. Renato Constantin; Cristina, Dragusin Roxana; Laura, Cara Monica; Laurentiu, Dira

doi:10.1016/j.ajogmf.2022.100711

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They were also identified as significant predictors of post partum hemorrhage in a risk prediction modeling research [29]. Fetal gestational age as a predictor of delivery outcome is also shared in a related study for the prediction of labor outcome [30] which among other factors mentioned gestational weeks of 37 and 38 as significant correlated variables to delivery outcome. Gestational age as a significant factor is underscored in other related works such as by [31].…”

Section: Discussionmentioning

confidence: 99%

An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers

Owusu-Adjei,

Ben Hayfron-Acquah,

Gaddafi

et al. 2024

Preprint

View full text Add to dashboard Cite

The desire for safer delivery mode that preserves the lives of both mother and child with minimal or no complications before, during and after childbirth is the wish for every expectant mother and their families. However, the choice for any particular birth delivery mode is determined primarily by a number of factors that feed into the ultimate decision of choice. Some of these include maternal birth history, maternal and child health conditions prevailing before and during labor onset. Predictive modeling has been used extensively to determine important contributory factors influencing delivery choice. However, missing among a myriad of features used in various research studies for this determination is maternal history of spontaneous, threatened and inevitable abortion(s) and how its inclusion can impact delivery outcomes. This research work therefore takes measurable maternal features that include real time information on administered partographs to predict delivery type. This is achieved by adopting effective feature selection technique to estimate variable relationship with the target variable. Three supervised learning techniques are used and evaluated for performance. Prediction accuracy score of area under the curve obtained show Gradient Boosting classifier achieved 91% accuracy, Logistic Regression 93% and Random Forest 91%. Balanced accuracy score for the same learning techniques obtained were; Gradient Boosting 82.73%, Logistic Regression 84.62% and Random Forest 83.02%. Correlation statistic for variable independence among input variables showed that delivery type as an output is associated with gestational age and the progress of maternal cervix dilatation during labor onset.

show abstract

Section: Discussionmentioning

confidence: 99%

An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers

Owusu-Adjei,

Ben Hayfron-Acquah,

Gaddafi

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, these measurements apparently can be used to forecast the delivery mode when the pregnancy reaches term. 38 Shrivastava et al studied occipitospinal angle by abdominal USG in low-risk primigravid women in the first stage of labor. Patients with lower occipitospinal angle (average 125°) had taken a longer time to deliver the baby compared to those with higher occipitospinal angle >125 and women with <120° had cesarean sections.…”

Section: Predicting Vaginal Deliverymentioning

confidence: 99%

Utility of Ultrasonographic Parameters for Monitoring of Progress of Labor and Prediction of Successful Vaginal Delivery: Narrative Review

Dasari¹

2023

Annals of SBV

View full text Add to dashboard Cite

Traditionally, progress of labor and the prediction of vaginal delivery is done by clinical assessment. There is a lot of subjectivity in assessment and increased interobserver variability, especially with digital vaginal examination. For the past two decades, many ultrasonographic parameters were developed, and their utility was studied objectively. Of the ultrasound (USG) parameters, head position is the easiest to recognize. The descent and station of the head are determined indirectly by angle of progression (AOP) and head perineal distance (HPD). Cervical dilatation does not correlate well with digital vaginal examination, and it is difficult to visualize cervical rim beyond 8-cm dilatation. Midline angle and head-up position are other parameters in the second stage of labor that are determined to predict difficult vaginal delivery. Angle of progression of >110° and HPD <4 cm are good predictors of vaginal delivery. "Sonopartogram" may replace the traditional partogram as it is more objective, noninvasive, and women-friendly. Intrapartum apps are incorporating USG parameters with other patient characteristics to develop models for predicting vaginal delivery.

show abstract

Artificial Intelligence in Obstetrics

Belciug

Iliescu

2023

Intelligent Systems Reference Library

View full text Add to dashboard Cite

Prediction of labor outcome pilot study: evaluation of primiparous women at term

Cited by 4 publications

References 26 publications

An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers

An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers

Utility of Ultrasonographic Parameters for Monitoring of Progress of Labor and Prediction of Successful Vaginal Delivery: Narrative Review

Artificial Intelligence in Obstetrics

Contact Info

Product

Resources

About