Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Biostatistik, Kependudukan, dan Informatika Kesehatan
Assetya Pratiwi, Okky
Unknown Affiliation
Public Health

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Harnessing Sociodemographic and Anthropometric Insights to Predict Type 2 Diabetes Risk: A Machine Learning Approach Kurniawan, Rico; Yunanda, Rezki; Assetya Pratiwi, Okky
Jurnal Biostatistik, Kependudukan, dan Informatika Kesehatan Vol. 5, No. 2
Publisher : UI Scholars Hub

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The complexity of diabetes makes early diagnosis and effective management challenging for healthcare settings. This study developed and evaluated models using machine learning algorithms to predict the risk of diabetes. The data were primarily sourced from the Indonesia Family Life Survey (IFLS). Diabetes status was identified using A1c whole blood sample values (A1c WBS ³5.7%). Sociodemographic and anthropometric factors were set as predictors, most of which were significantly correlated with diabetes status. Discrete machine learning algorithms such as decision tree, k-nearest neighbors (KNN), random forest (RF), naïve Bayer, support vector machine (SVM), and neural network (MLP) were applied to construct and compare prediction models for classification. MLP model exhibited the highest performance with AUC 67%, Accuracy 87.1%, F1 Score 87.1%, Recall 87.1% and Precision 82.4%. Overall, machine learning models were found highly viable in predicting disease outcomes with increasing accuracy. Their usage would allow healthcare professionals to make more informed patient care decisions. Future research initiatives should attempt to further enhance these models.
Co-Authors Kurniawan, Rico Yunanda, Rezki