Analysis of Association between Caesarean Delivery and Gestational Diabetes Mellitus Using Machine Learning

BACKGROUND The use of artificial intelligence (AI) has revolutionized every area of life such as business and trade, social and electronic media, education and learning, manufacturing industries, medical and sciences, and every other sector. The new reforms and advanced technologies of AI have enabled data analysts to transmute raw data generated by these sectors into meaningful insights for an effective decision-making process. Health care is one of the integral sectors where a large amount of data is generated daily, and making effective decisions based on this data is therefore a challenge. In health care, cases related to childbirth either by the traditional method of vaginal delivery or cesarean delivery have been investigated in this study. Cesarean delivery is performed to save both mother and fetal lives when complications arise related to vaginal birth. OBJECTIVE To develop reliable prediction models for a maternity care decision support system to predict mode of delivery before birth. METHODS This study is conducted in two folds for identifying the mode of delivery: firstly, to enrich the existing dataset; secondly, to investigate previous medical records about the mode of delivery using machine learning algorithms and extract meaningful insight into the unseen cases. To achieve this objective, several prediction models were trained such as Decision Tree (DT), Random Forest (RF), AdaBoostM1 (AB), Bagging, and k-Nearest Neighbor (k-NN), based on original and enriched datasets. RESULTS To achieve the objective, several prediction models were trained such as Decision Tree (DT), Random Forest (RF), AdaBoostM1 (AB), Bagging, and k-Nearest Neighbor (k-NN) based on original and enriched datasets. As an outcome, the prediction models based on enriched data performed well in terms of accuracy, sensitivity, specificity, F-measure, and ROC. Specifically, k-NN outperformed with an accuracy of 84.38%, Bagging (83.75%), RF (83.13%), DT (81.25%), and AB (80.63%). In the end, enriching the dataset improves the accuracy of the prediction process, which supports maternity care practitioners in making decisions for critical cases. CONCLUSIONS Enriching the dataset improves the accuracy of the prediction process, which supports maternity care practitioners in making decisions for critical cases. The enriched dataset in its current stage used in this study yields better results, but this could be even better if its records were increased with real clinical data.

show abstract

Analysis of Association between Caesarean Delivery and Gestational Diabetes Mellitus Using Machine Learning

Cited by 2 publications

References 13 publications

Kinetic Modelling of FeMn Pilot Experiments: Investigating the Effect of Charge Type and Pre-treatment

Kinetic Modelling of FeMn Pilot Experiments: Investigating the Effect of Charge Type and Pre-treatment

Reliable Prediction Models Based on Enriched Data for Identifying the Mode of Childbirth by Using Machine Learning Methods: Development Study (Preprint)

Contact Info

Product

Resources

About