Design and Construction of Maternal and Infant Mortality Rate Mapping Using the K-Means Clustering Method Based on Geographic Information Systems (Case Study in Jember Regency)

Abstract

Indonesia’s population continues to grow each year, including in Jember Regency, which reached 2,584,771 people in 2023. Population density contributes to various health issues, such as the high maternal mortality rate (MMR) and infant mortality rate (IMR), with 17 maternal deaths and 81 infant deaths recorded in 2023. The primary causes of MMR include pregnancy at too young or old an age, short birth spacing, and delays in referral, while IMR is mainly caused by asphyxia and low birth weight (LBW) due to premature birth. The government has implemented a midwife and traditional birth attendant partnership program to address this issue. However, information regarding high-risk areas remains inadequately conveyed. Therefore, this study develops a Geographic Information System (GIS)-based system using the K-Means Clustering method with a predefined number of clusters to classify high-risk maternal and infant mortality areas. The results show that the K-Means Clustering method with a fixed number of clusters (k = 5) successfully groups Jember Regency into five risk-level clusters, namely very high, high, medium, low, and very low. Visualization through GIS facilitates effective access to spatial information and supports the identification of priority areas for targeted health interventions, aiming to reduce maternal and infant mortality rates more effectively.