Short birth intervals classification for Indonesia’s women

Ratih Ardiati Ningrum, Indah Fahmiyah, Aretha Levi, Muhammad Axel Syahputra

Research output: Contribution to journalArticlepeer-review

Abstract

Birth interval is closely related to maternal and infant health. According to world health organization (WHO), the birth interval between two births is at least 33 months. This study is the first to discuss the short birth interval (SBI) in Indonesia and used data from the Indonesian Demographic and Health Surveys 2017 with a total of 34,200 respondents. Birth interval means the length of time between the birth of the first child and the second child. Categorized as SBI if the distance between births is less than 33 months. The variables used include mother's age, mother's age at first giving birth, father's age, household wealth, succeeding birth interval, breastfeeding status, child sex, residence, mother's education, health insurance, mother's working status, contraception used, child alive, total children, number of living children, and household members. Machine learning algorithms including logistic regression, Naïve Bayes, lazy locally weighted learning (LWL), and sequential minimal optimization (SMO) are applied to classify SBI. Based on the values of accuracy, precision, recall, F-score, matthews correlation coefficient (MCC), receiver operator characteristic (ROC) area, precision-recall curve (PRC) area, the Naïve Bayes is the best algorithm with scores obtained 0.891, 0.889, 0.891, 0.885, 0.687, 0.972, and 0.960 respectively. Additionally, 18.25% of mothers were classified as still giving birth within a short interval.

Original languageEnglish
Pages (from-to)1543-1542
Number of pages2
JournalBulletin of Electrical Engineering and Informatics
Volume11
Issue number3
DOIs
Publication statusPublished - 2022

Keywords

  • Classification
  • Infant health
  • Machine learning
  • Maternal health
  • Naïve Bayes
  • Short birth interval

Fingerprint

Dive into the research topics of 'Short birth intervals classification for Indonesia’s women'. Together they form a unique fingerprint.

Cite this