Okky Assetya Pratiwi
Institute Of Health Indonesia

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Hypertension prediction using machine learning algorithm among Indonesian adults Rico Kurniawan; Budi Utomo; Kemal N. Siregar; Kalamullah Ramli; Besral Besral; Ruddy J. Suhatril; Okky Assetya Pratiwi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 2: June 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v12.i2.pp776-784

Abstract

Early risk prediction and appropriate treatment are believed to be able to delay the occurrence of hypertension and attendant conditions. Many hypertension prediction models have been developed across the world, but they cannot be generalized directly to all populations, including for Indonesian population. This study aimed to develop and validate a hypertension risk-prediction model using machine learning (ML). The modifiable risk factors are used as the predictor, while the target variable on the algorithm is hypertension status. This study compared several machine-learning algorithms such as decision tree, random forest, gradient boosting, and logistic regression to develop a hypertension prediction model. Several parameters, including the area under the receiver operator characteristic curve (AUC), classification accuracy (CA), F1 score, precision, and recall were used to evaluate the models. Most of the predictors used in this study were significantly correlated with hypertension. Logistic regression algorithm showed better parameter values, with AUC 0.829, CA 89.6%, recall 0.896, precision 0.878, and F1 score 0.877. ML offers the ability to develop a quick prediction model for hypertension screening using non-invasive factors. From this study, we estimate that 89.6% of people with elevated blood pressure obtained on home blood pressure measurement will show clinical hypertension.
Families at Risk of Stunting and the Prevalence of Stunting in Indonesia: An Ecological Study Rico Kurniawan; Lina Widyastuti; Sudibyo Alimoeso; Siti Fathonah; Diaini, Meindy; Muhammad Kodir; Welcy Fine; Okky Assetya Pratiwi; Fadhilah, Hafsah Farah
Jurnal Kesehatan Masyarakat Vol. 21 No. 1 (2025)
Publisher : Universitas Negeri Semarang in collaboration with Ikatan Ahli Kesehatan Masyarakat Indonesia (IAKMI Tingkat Pusat) and Jejaring Nasional Pendidikan Kesehatan (JNPK)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/kemas.v21i1.20978

Abstract

Stunting remains a critical public health challenge in Indonesia, impacting child growth, cognitive development, and long-term productivity. The government has prioritized interventions targeting families at risk of stunting to reduce its prevalence. This study examines the relationship between families at risk of stunting and stunting prevalence in Indonesia by an ecological study design. Data were analyzed at the district/city level using correlation analysis to assess key risk factors. The findings indicate that inadequate access to safe drinking water, poor sanitation, substandard housing, and reproductive health risks among women of reproductive age are significantly correlated with higher stunting prevalence (p<0.05). The correlation coefficients for these factors are 0.14, 0.19, 0.17, and 0.33, respectively. Furthermore, a one percent reduction in families at risk of stunting is associated with a 0.19 percent decrease in stunting prevalence (R² = 16%). These results highlight the need for comprehensive interventions addressing environmental, socio-economic, and maternal health factors. Strengthening policies that improve access to clean water, sanitation, and maternal health services is crucial to accelerating stunting reduction efforts in Indonesia. Prioritizing families at risk can enhance the effectiveness of government strategies in achieving national stunting decrease targets.
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.