Implementasi Algoritma Naïve Bayes untuk Mendeteksi Resiko Tinggi Diabetes Melitus Pada Ibu Hamil (Studi Kasus : Puskesmas Kabupaten Malang)

  • Fatmawati F
  • Wicaksono S
  • Wijoyo S
N/ACitations
Citations of this article
20Readers
Mendeley users who have this article in their library.

Abstract

Diabetes pada ibu hamil dapat meningkatkan berbagai risiko, baik maternal maupun neonatus. Terdapat gangguan homeostasis glukosa pada ibu hamil. Terjadinya malformasi kongenital, keguguran, risiko preeklampsia, CPD (Cepalo Pelvik Dispropotion), kelahiran prematur, kelainan letak, plasenta previa dan hipoglikemia neonatus. Oleh karena itu, Perhatian dan penanganan menyeluruh bagi ibu hamil yang mengalami diabetes. Data mining dapat digunakan untuk deteksi resiko tinggi diabetus mellitus pada ibu hamil. Data yang digunakan seperti nama, usia, umur kehamilan, gravida, para, riwayat kehamilan yang lalu, riwayat penyakit yang pernah diderita, faktor risiko, riwayat persalinan yang lalu untuk deteksi resiko tinggi diabetus mellitus pada ibu hamil. Tidak semua kehamilan dapat berjalan dengan normal atau fisiologis pada saat proses persalinannya ada faktor risiko yang dapat mempengaruhinya. Pada penelitian ini dapat mendeteksi resiko yang akan terjadi kepada ibu hamil dan bayi dalam kandungannya. Nilai akurasi tertinggi terdapat pada pengujian ke 4 sebesar 82.4324% dan terendah nilai akurasi pada pengujian ke 2 sebesar 75%. Nilai presisi tertinggi terdapat di uji coba ke 3 sebesar 79.2% dan nilai presisi terendah di uji coba ke 2 sebesar 76.3%. Nilai recall tertinggi terdapat di uji coba ke 4 sebesar 82.4% dan nilai recall terendah di uji coba ke 2 sebesar 75%. Nilai F-Measure tertinggi terdapat di uji coba ke 3 sebesar 79.2% dan nilai F-Measure terendah di uji coba ke 2 sebesar 74.8%. AbstractDiabetes in pregnant women can increase various risks, both maternal and neonatal. There is a disturbance of glucose homeostasis in pregnant women. Occurrence of congenital malformations, miscarriage, risk of preeclampsia, CPD (Cepalo Pelvic Disproportion), premature birth, position abnormalities, placenta previa and neonatal hypoglycemia. Therefore, attention and comprehensive treatment for pregnant women with diabetes. Data mining can be used to detect high risk of diabetes mellitus in pregnant women. The data used are name, age, gestational age, gravida, para, past pregnancy history, history of previous illness, risk factors, past delivery history to detect high risk of diabetes mellitus in pregnant women. Not all pregnancies can run normally or physiologically at the time of delivery there are risk factors that can affect it. In this study, it can detect the risks that will occur to pregnant women and their babies in the womb. In addition, recommendations from the system can support a midwife's decision making in taking action to pregnant women. The highest accuracy value is found in the 4th test of 82,4324% and the lowest accuracy value in the 2nd test is 75%. The highest precision value was found in the 3rd trial of 79.2% and the lowest precision value in the 2nd trial of 76.3%. The highest recall value was found in the 4th trial of 82.4% and the lowest recall value in the 2nd trial of 75%. The highest F-Measure value was found in the 3rd trial of 79.2% and the lowest F-Measure value in the 2nd trial of 74.8%.

Cite

CITATION STYLE

APA

Fatmawati, F., Wicaksono, S. A., & Wijoyo, S. H. (2023). Implementasi Algoritma Naïve Bayes untuk Mendeteksi Resiko Tinggi Diabetes Melitus Pada Ibu Hamil (Studi Kasus : Puskesmas Kabupaten Malang). Jurnal Teknologi Informasi Dan Ilmu Komputer, 10(4), 851–856. https://doi.org/10.25126/jtiik.20241046422

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free