A novel oppositional binary crow search algorithm with optimal machine learning based postpartum hemorrhage prediction model

Krishnamoorthy, Sujatha; Liu, Yihang; Liu, Kun

doi:10.1186/s12884-022-04775-z

Cited by 7 publications

(5 citation statements)

References 24 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evidence-based inpatient care supports continuity of care, a reduction in episiotomy rates, and active management of the third stage with 10 IU syntocinone. Experts recommend that all women should benefit from active management of the third stage of labor, the only intervention known to prevent postpartum hemorrhage (Krishnamoorthy et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Active Versus Expectant Management of Third Stage of Labor: A Plane of Nursing Action

Elzeblawy Hassan,

Khalaf Gouda,

Shehta Said Farag

2024

Egyptian Journal of Health Care

View full text Add to dashboard Cite

Background: Expectant management of the third stage of labor is known as conservative or physiological or passive management. Active management of the third stage of labor as a prophylactic intervention is composed of a package of three components: Administration of a uterotonic agent within one minute after the baby is born; after the cord is clamped; delivery of the placenta by controlled cord traction with counter-traction on the fundus; and fundal massage after delivery of the placenta. Aim: to compare the effects of active management versus expectant management of the third stage of labor and evaluate the effect of an educational programs on nurses' knowledge about the management of the third stage of labor. Subjects and methods:-Research-designs: Two research designs were used: The first is a cross-sectional descriptive survey. The second is a quasi-experimental intervention study. Sample: A total of 300 pregnant women; group (1) 150 women using active management compared with group (2) 150 ones using expectant management were randomly recruited for this study. As well as 20 nurses. Setting: The current study was conducted at the delivery unit in Beni-Suef University Hospital. Tools: Four tools were used, namely the interview questionnaire form, maternal assessment record, partograph, and nurses' knowledge questionnaire (preand post-test). Results:The results revealed that all women in the two groups had vaginal deliveries; the third stage was shorter in the active group, but the difference was not statistically significant. Women in the active group had significantly less blood loss at the second and third stages. The active group had significantly lower hemoglobin levels before delivery, but after delivery, this difference disappeared. Conclusion: Active management of the third stage of labor is associated with a shorter duration of the third stage, less blood loss, and less decline in the hemoglobin level. Post-intervention, there was a significant improvement in the nurse's knowledge about management of the third stage of labor. Recommendations: Active management of the third stage is a safe and effective procedure that should be used in the health care setting providing delivery care services.

show abstract

Section: Discussionmentioning

confidence: 99%

Active Versus Expectant Management of Third Stage of Labor: A Plane of Nursing Action

Elzeblawy Hassan,

Khalaf Gouda,

Shehta Said Farag

2024

Egyptian Journal of Health Care

View full text Add to dashboard Cite

show abstract

“…Krishnamoorthy et al [17] presented an approach for predicting PPH by introducing the oppositional binary crow search algorithm (OBCSA) coupled with an optimal stacked autoencoder (OSAE) model, denoted as OBCSA-OSAE. This technique encompasses OBCSAbased feature selection methods strategically employed to determine an optimal subset of features.…”

Section: Indicator Explorationmentioning

confidence: 99%

“…A total of 54 indicators were collected per patient. According to previous studies [14,[17][18][19], we selected 27 indicators that were potentially clinically related to PPH. All data comes from the medical electronic case system.…”

Section: Dataset Acquisitionmentioning

confidence: 99%

Quantitative prediction of postpartum hemorrhage in cesarean section on machine learning

Wang,

Yi,

Zhang

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Cesarean section-induced postpartum hemorrhage (PPH) potentially causes anemia and hypovolemic shock in pregnant women. Hence, it is helpful for obstetricians and anesthesiologists to prepare pre-emptive prevention when predicting PPH occurrence in advance. However, current works on PPH prediction focus on whether PPH occurs rather than assessing PPH amount. To this end, this work studies quantitative PPH prediction with machine learning (ML). Methods The study cohort in this paper was selected from individuals with PPH who were hospitalized at Shijiazhuang Obstetrics and Gynecology Hospital from 2020 to 2022. In this study cohort, we built a dataset with 6,144 subjects covering clinical parameters, anesthesia operation records, laboratory examination results, and other information in the electronic medical record system. Based on our built dataset, we exploit six different ML models, including logistic regression, linear regression, gradient boosting, XGBoost, multilayer perceptron, and random forest, to automatically predict the amount of bleeding during cesarean section. Eighty percent of the dataset was used as model training, and 20$$\%$$ % was used for verification. Those ML models are constantly verified and improved by root mean squared error(RMSE) and mean absolute error(MAE). Moreover, we also leverage the importance of permutation and partial dependence plot (PDP) to discuss their feasibility. Result The experiment results show that random forest obtains the highest accuracy for PPH amount prediction compared to other ML methods. Random forest reaches the mean absolute error of 21.7, less than 5.4$$\%$$ % prediction error. It also gains the root mean squared error of 33.75, less than 9.3$$\%$$ % prediction error. On the other hand, the experimental results also disclose indicators that contributed most to PPH prediction, including Ca, hemoglobin, white blood cells, platelets, Na, and K. Conclusion It effectively predicts the amount of PPH during a cesarean section by ML methods, especially random forest. With the above insight, ML predicting PPH amounts provides early warning for clinicians, thus reducing complications and improving cesarean sections’ safety. Furthermore, the importance of ML and permutation, complemented by incorporating PDP, promises to provide clinicians with a transparent indication of individual risk prediction.

show abstract

“…The occurrence of PPH can bring a series of hazards, Some studies [3] have indicated that establishing a predictive early warning system for significant diseases, monitoring pregnant women with high-risk factors, and quantifying and scoring high-risk factors can early identification, and timely intervention, and treatment, and help reduce the occurrence of PPH. The nomogram [4]is a reliable statistical model that provides individualized and highly accurate risk assessment and is now widely used in obstetrics and gynecology, such as the nomogram for predicting survival after uterine sarcoma [5] and the nomogram for the survival of patients with cervical cancer [6], etc.…”

Section: Researchmentioning

confidence: 99%

Establishment of a predictive model for postpartum hemorrhage in twins: a retrospective study

2023

Preprint

View full text Add to dashboard Cite

Objective To explore the risk factors and develop a predictive model for postpartum hemorrhage in twin pregnancies. Methods This retrospective cohort study included 2,045 patients who met the inclusion criteria for inpatient deliveries at Ningbo Women's and Children's Hospital from January 2018 to August 2022. The patients were randomly divided into training and testing cohorts by 7:3, LASS0 regression screening variables and dichotomous logistic multifactor analysis were applied in R language to determine independent risk factors for postpartum hemorrhage in twin births nomograms were drawn to validate and evaluate the predictive efficacy of the model. Results Multifactorial Logistic regression analysis showed maternal age, assisted reproduction, platelet count, fibrinogen level, albumin level, hypertensive disorders of pregnancy, placenta praevia, number of previous cesarean deliveries, number of previous intrauterine manipulation, and neonatal weight were independent risk factors for postpartum hemorrhage in twin births. The area under curve (AUC) for the training cohort was 0.810 [95%CI (0.781, 0.839)], with a sensitivity of 76.5%, specificity of 71.0%, and positive and negative predictive values of 0.358 and 0.935, respectively, while the AUC for the testing cohorts was 0.821 [95%CI (0.781, 0.860)], with a sensitivity of 80.9%, specificity of 69.49%, and positive predictive value and negative predictive value of 0.426 and 0.929. Conclusion The predictive model can effectively and quantitatively assess the risk of postpartum hemorrhage in twin pregnancies and help clinicians to take personalized preventive measures.

show abstract

A novel oppositional binary crow search algorithm with optimal machine learning based postpartum hemorrhage prediction model

Cited by 7 publications

References 24 publications

Active Versus Expectant Management of Third Stage of Labor: A Plane of Nursing Action

Active Versus Expectant Management of Third Stage of Labor: A Plane of Nursing Action

Quantitative prediction of postpartum hemorrhage in cesarean section on machine learning

Establishment of a predictive model for postpartum hemorrhage in twins: a retrospective study

Contact Info

Product

Resources

About