Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal of Public Health Excellence (IJPHE)

Predicting the Risk of Premature Birth Using Naive Bayes Based on Maternal Health Data at Rantauprapat Regional Hospital Adawiyah, Quratih; Handayani, Rika; Nadrah, Nailatun; Nasution, Fitriyani; Ramadani, Putri
International Journal of Public Health Excellence (IJPHE) Vol. 4 No. 2 (2025): January-May
Publisher : PT Inovasi Pratama Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55299/ijphe.v4i2.1112

Abstract

Premature birth is one of the leading causes of infant mortality and complications. Early identification of pregnant women at risk of premature delivery is crucial for appropriate management. This study aims to develop a predictive model for premature birth risk using the Naïve Bayes method based on maternal health data from RSUD Rantauprapat. The data used includes variables such as mother's age, nutritional status, blood pressure, and history of premature birth. The study applies Naïve Bayes to predict the classes of premature birth risk, namely "Premature" and "Not Premature", with data divided into 70% for training and 30% for testing. The results show that the Naïve Bayes model achieved an accuracy of 78.33% in predicting premature birth risk. Additionally, the model shows precision of 89.29%, recall of 83.33%, and F1-score of 86.1%, indicating good performance in detecting pregnant women at risk of premature birth. Comparison with other models, such as Logistic Regression and Decision Tree, demonstrates that Naïve Bayes provides the best results in terms of accuracy and balance between precision and recall. This study shows that Naïve Bayes can be an effective tool for early detection of premature birth and can be implemented in medical decision-making systems at hospitals to improve the management of high-risk pregnant women. The results of this study can serve as a foundation for further research that develops predictive models by adding features or other algorithms.