Journal of Preventive Medicine and Public Health

Original Article

Development of Machine Learning Models to Predict Health Insurance Claim Costs Among Older Indonesians: A Retrospective Predictive Modeling Study: Yeni Mahwati, Dhihram Tenrisau, Syarif Rahman Hasibuan, Bhirau Wilaksono, Yeni Indriyani, Andi Afdal Abdullah, Halik Malik, Andi Alfian Zainuddin; J Prev Med Public Health. 2026;59(2):132-142. Published online January 6, 2026; DOI: https://doi.org/10.3961/jpmph.25.350

756 View
100 Download

Abstract Summary PDF: Objectives
The objective of this study was to develop machine learning models to predict health insurance claim costs among older adults in Indonesia.
Methods
This study utilized secondary data from the Indonesian National Health Insurance program (Jaminan Kesehatan Nasional [JKN]) spanning 2017 to 2023. Three modeling techniques—linear regression, random forest, and XGBoost—were employed to predict individual claim costs. Model performance was assessed using the root mean square error (RMSE), coefficient of determination (R²), and mean absolute error (MAE). Additionally, variable importance analysis was conducted to identify key predictors.
Results
XGBoost with 500 boosting rounds yielded the best performance, with an RMSE of 11 360 283, an R² of 0.81, and an MAE of 4 485 917, outperforming both linear regression (RMSE, 13 710 035; R²=0.72) and random forest (RMSE, 12 434 238; R²=0.78). Notably, outpatient care was identified as the most consistent predictor across all models. Other significant predictors included length of stay (LOS), diagnosis type (International Classification of Diseases, 10th revision chapter), facility type, facility classification, and severity of illness, particularly for moderate cases. Although LOS and diagnosis type were important predictors, these findings should be interpreted in the context of Indonesia’s fixed Indonesian Case-Based Groups payment system.
Conclusions
XGBoost provides reliable predictions of claim costs among older adults, capturing clinical, utilization, and structural drivers. These findings can inform targeted interventions, improve chronic disease management, optimize the referral system, and support integration of predictive tools into JKN to enhance responsiveness and promote sustainable, equitable financing.; Summary

Key Message
Machine learning models, particularly XGBoost, demonstrated superior performance in predicting healthcare costs among older adults in Indonesia. Nonlinear relationships between outpatient visits, severity, and diagnoses highlight the limitations of conventional linear approaches. These findings support the integration of advanced predictive models into national health insurance systems to improve cost management and resource allocation.

Review

The Next Frontiers in Preventive and Personalized Healthcare: Artificial Intelligent-powered Solutions: Rasit Dinc, Nurittin Ardic; J Prev Med Public Health. 2025;58(5):441-452. Published online May 29, 2025; DOI: https://doi.org/10.3961/jpmph.25.080

3,117 View
305 Download
3 Web of Science
5 Crossref

Artificial intelligence (AI)-enabled technologies have the potential to significantly increase diagnostic accuracy, optimize treatment strategies, and improve patient outcomes. They are revolutionizing the field of preventive and personalized medicine by providing data-driven insights. AI is capable of analyzing large and complex datasets such as genomic, environmental, and lifestyle information much faster and more conveniently than traditional methods. Advanced algorithmic architectures in AI can predict disease risks, identify biomarkers, and tailor interventions to individual needs. The enabling role of AI in real-time monitoring, predictive analysis, and drug discovery demonstrates its transformative potential in healthcare. The role of AI in multi-omics integration, wearable technologies, and precision therapies promises to redefine global healthcare paradigms, making personalized medicine more accessible and effective. However, ethical concerns that need to be addressed to ensure fair and transparent implementation include data privacy, algorithmic bias, and regulatory gaps. This article examines the integration of AI technologies with personalized healthcare. The study also highlights the need for interdisciplinary collaboration to maximize the benefits of AI in preventive and personalized healthcare and overcome barriers.

Summary

Key Message
Artificial intelligence significantly accelerates preventive and personalized medicine by analyzing complex genomic, environmental, and lifestyle datasets to predict disease risks, identify biomarkers, and tailor interventions to individual needs. Through real-time monitoring, predictive analysis, and precision therapies, AI-enabled technologies play a critical role in increasing diagnostic accuracy, optimizing treatment strategies, and improving patient outcomes. However, successful implementation requires addressing critical challenges such as data privacy concerns, algorithmic bias, regulatory gaps, and the need for interdisciplinary collaboration to provide equitable, transparent, and accessible AI-enabled healthcare solutions.

Citations

Citations to this article as recorded by

Applications of Artificial Intelligence in Selected Internal Medicine Specialties: A Critical Narrative Review of the Latest Clinical Evidence
Aleksandra Łoś, Dorota Bartusik-Aebisher, Wiktoria Mytych, David Aebisher
Algorithms.2026; 19(1): 54. CrossRef
Can AI developers avoid bias in public health applications?
Rebekah J. Harms, Rachel A. Ankeny, Lucy Carter, Aditi Mankad, Jackie Leach Scully
Frontiers in Public Health.2026;[Epub] CrossRef
AI-enabled cardiovascular devices: a lifecycle playbook for evidence, change control, and post-market assurance
Nurittin Ardic, Rasit Dinc
Frontiers in Digital Health.2026;[Epub] CrossRef
How can artificial intelligence be used within occupational medicine to identify early worker needs and improve workplace accommodation? A narrative review
Bogdan Mihail Diaconescu, Bogdan Gurzu, Claudia Sava, Catalina Sava, Ilinca Sfarghiu, Delia Luchian, Irina Luciana Gurzu
Romanian Journal of Occupational Medicine.2025; 76(1): 6. CrossRef
Artificial intelligence application in the prevention of chronic non-communicable diseases: a systematic review of publications from 2022 to 2025
L.Yu. Drozdova, V.A. Egorov, O.M. Drapkina
Russian Journal of Preventive Medicine.2025; 28(12): 21. CrossRef

Original Articles

Development of Machine Learning Models to Categorize Life Satisfaction in Older Adults in Korea: Suyeong Bae, Mi Jung Lee, Ickpyo Hong; J Prev Med Public Health. 2025;58(2):127-135. Published online October 23, 2024; DOI: https://doi.org/10.3961/jpmph.24.324

16,964 View
524 Download
1 Web of Science
2 Crossref

Abstract Summary PDF

Objectives
This study aimed to identify factors associated with life satisfaction by developing machine learning (ML) models to predict life satisfaction in older adults living alone.
Methods
Data were extracted from 3112 older adults participating in the 2020 Korea Senior Survey. We employed 5 ML models to classify the life satisfaction of older adults living alone: logistic Lasso regression, decision tree-based classification and regression tree (CART), C5.0, random forest, and extreme gradient boost (XGBoost). The variables used as predictors included demographics, health status, functional abilities, environmental factors, and activity participation. The performance of these ML models was evaluated based on accuracy, precision, recall, F1-score, and area under the curve (AUC). Additionally, we assessed the significance of variable importance as indicated by the final classification models.
Results
Out of the 1411 older adults living alone, 45.3% expressed satisfaction with their lives. The XGBoost model surpassed the performance of other models, achieving an F1-score of 0.72 and an AUC of 0.75. According to the XGBoost model, the five most important variables influencing life satisfaction were overall community satisfaction, self-rated health, opportunities to interact with neighbors, proximity to a child, and satisfaction with residence.
Conclusions
Overall satisfaction with the community environment emerged as the most significant predictor of life satisfaction among older adults living alone. These findings indicate that enhancing the supportiveness of the community environment could improve life satisfaction for this demographic.

Summary

Korean summary
본 연구는 2020년 노인실태조사에 참여한 3,112명의 독거노인 데이터를 활용하여 이들의 삶의 만족도를 분류하는 머신러닝 모델을 개발하였다. 아울러, 해당 모델을 통해 독거노인의 삶의 만족도 분류에 영향을 미치는 주요 변수를 도출하였다. 본 연구는 독거노인의 삶의 만족도 향상을 위해 고려해야 할 핵심 요인들을 제시한다는 점에서 의의가 있다.

Key Message
This study developed a machine learning model to classify life satisfaction among 3,112 older adults living alone, based on data from the 2020 Korea Senior Survey. Furthermore, the study identified key variables that contribute to the classification of life satisfaction in this population. These findings provide insights into important factors that should be considered to enhance the life satisfaction of older adults living alone.

Citations

Citations to this article as recorded by

Prevalence of depression and its associated factors among Korean women: A cross-sectional study in Seoul
Thi Thanh Lan Nguyen, Van Cuong Nguyen
Archives of Psychiatric Nursing.2025; 57: 151928. CrossRef
Designing a Social Prescribing Model to Enhance the Holistic Well-Being of Older Adults in Indonesia
Sukri Palutturi , St. Rosmanelly, Mutia Nur Rahmah , Eun Woo Nam, Mi-hwa Kang
Salud, Ciencia y Tecnología.2025; 5: 2235. CrossRef

Prediction of Stunting Among Under-5 Children in Rwanda Using Machine Learning Techniques: Similien Ndagijimana, Ignace Habimana Kabano, Emmanuel Masabo, Jean Marie Ntaganda; J Prev Med Public Health. 2023;56(1):41-49. Published online January 6, 2023; DOI: https://doi.org/10.3961/jpmph.22.388

12,849 View
599 Download
20 Web of Science
25 Crossref

Abstract PDF

Objectives
Rwanda reported a stunting rate of 33% in 2020, decreasing from 38% in 2015; however, stunting remains an issue. Globally, child deaths from malnutrition stand at 45%. The best options for the early detection and treatment of stunting should be made a community policy priority, and health services remain an issue. Hence, this research aimed to develop a model for predicting stunting in Rwandan children.
Methods
The Rwanda Demographic and Health Survey 2019-2020 was used as secondary data. Stratified 10-fold cross-validation was used, and different machine learning classifiers were trained to predict stunting status. The prediction models were compared using different metrics, and the best model was chosen.
Results
The best model was developed with the gradient boosting classifier algorithm, with a training accuracy of 80.49% based on the performance indicators of several models. Based on a confusion matrix, the test accuracy, sensitivity, specificity, and F1 were calculated, yielding the model’s ability to classify stunting cases correctly at 79.33%, identify stunted children accurately at 72.51%, and categorize non-stunted children correctly at 94.49%, with an area under the curve of 0.89. The model found that the mother’s height, television, the child’s age, province, mother’s education, birth weight, and childbirth size were the most important predictors of stunting status.
Conclusions
Therefore, machine-learning techniques may be used in Rwanda to construct an accurate model that can detect the early stages of stunting and offer the best predictive attributes to help prevent and control stunting in under five Rwandan children.

Summary

Citations

Citations to this article as recorded by

Machine learning techniques to model child low height-for-age in the Northern Province of Rwanda: The role of climatological and environmental factors and their interactions
A. Ndagijimana, G. Nduwayezu, T. Lind, A. Mansourian
Clinical Epidemiology and Global Health.2026; 37: 102284. CrossRef
Predicting severe stunting and its determinants among under-five in Eastern African Countries: A machine learning algorithms
Halid Worku Jemil, Sonia Worku Semayneh, Altaseb Beyene Kassaw, Kassahun Dessie Gashu, Olutosin Ademola Otekunrin
PLOS One.2026; 21(1): e0340221. CrossRef
Systems biology insights into the molecular drivers of childhood stunting and implications for intervention
Genevieve Dable-Tupas, Ariane Blanch A. Maraon, Lorraine Joy L. Bernolo, Nelly Grace F. Toñacao, April Dawn M. Taylaran, Maria Angelica C. Plata, Jason C. Alcano, Richelle D. Björvang, Shamsul Mohd Zain, Vladimer Kobayashi, Melkamu Berhane Arefayine, Alem
Frontiers in Nutrition.2026;[Epub] CrossRef
The effect of Ogapudake digital education on mothers knowledge of stunting prevention
Rotua Suriany Simamora, Yonathan Tri Atmodjo Reubun, Lina Indrawati, Tri Dharma Putra, Feronika Evma Rahayu, Rahmalia Putri Khayla, Muhammad Lutfi Fajri Agustian, Aliyah Zahra
Multidisciplinary Reviews.2026; 9(9): 2026429. CrossRef
Prediction of stunting and its socioeconomic determinants among adolescent girls in Ethiopia using machine learning algorithms
Alemu Birara Zemariam, Biruk Beletew Abate, Addis Wondmagegn Alamaw, Eyob shitie Lake, Gizachew Yilak, Mulat Ayele, Befkad Derese Tilahun, Habtamu Setegn Ngusie, Oluwafemi Samson Balogun
PLOS ONE.2025; 20(1): e0316452. CrossRef
Predicting stunting status among under-5 children in Rwanda using neural network model: Evidence from 2020 Rwanda demographic and health survey
Similien Ndagijimana, Ignace Kabano, Emmanuel Masabo, Jean Marie Ntaganda
F1000Research.2025; 13: 128. CrossRef
A deep learning approach for classifying and predicting children's nutritional status in Ethiopia using LSTM-FC neural networks
Getnet Bogale Begashaw, Temesgen Zewotir, Haile Mekonnen Fenta
BioData Mining.2025;[Epub] CrossRef
Social and economic predictors of under-five stunting in Mexico: a comprehensive approach through the XGB model
Brian Fogarty, Angélica García-Martínez, Nitesh V Chawla, Edson Serván-Mori
Journal of Global Health.2025;[Epub] CrossRef
Identification of amendable risk factors for childhood stunting at individual, household and community levels in Northern Province, Rwanda – a cross-sectional population-based study
Albert Ndagijimana, Kristina Elfving, Aline Umubyeyi, Torbjörn Lind
BMC Public Health.2025;[Epub] CrossRef
Machine Learning in Predicting Child Malnutrition: A Meta-Analysis of Demographic and Health Surveys Data
Bhagyajyothi Rao, Muhammad Rashid, Md Gulzarull Hasan, Girish Thunga
International Journal of Environmental Research and Public Health.2025; 22(3): 449. CrossRef
Prevalence and associated risk factors of stunting too early: analysis of the 2020 Rwanda demographic and health survey
Raphael Ndahimana, Melissa Uwase, Roger Muragire, Alliance Uwase, Edith Uwamahoro, Bwiza Flavia, Elysee Niyonganyira, Ayinkamiye Esperance, Divine Umutesi Rusa, Marie Josée Mwiseneza, Absolomon Gashaija, Godfrey Ngabonziza, Japhet Ishimwe, Binayisa Gad, C
BMJ Nutrition, Prevention & Health.2025; 8(1): 240. CrossRef
Forecasting acute childhood malnutrition in Kenya using machine learning and diverse sets of indicators
Girmaw Abebe Tadesse, Laura Ferguson, Caleb Robinson, Shiphrah Kuria, Herbert Wanyonyi, Samuel Murage, Samuel Mburu, Rahul Dodhia, Juan M. Lavista Ferres, Bistra Dilkina, Yitagesu Habtu Aweke
PLOS One.2025; 20(5): e0322959. CrossRef
The accuracy of a novel stunting risk detection application based on nutrition and sanitation indicators in children aged under five years
Tria Astika Endah Permatasari, Yudi Chadirin, Ernirita Ernirita, Anisa Nurul Syafitri, Devina Alifia Fadhilah
BMC Nutrition.2025;[Epub] CrossRef
Effect of single-parent versus dual-parent households on dietary intake and growth among under-five children in Rwanda: an analysis using directed acyclic graph
Joyeuse Ukwishaka, Sekou Samadoulougou, Vincent Sezibera, Fati Kirakoya-Samadoulougou, Geneviève Lefebvre
BMC Nutrition.2025;[Epub] CrossRef
Supervised machine learning for classification and prediction of stunting among under-five Egyptian children
Abdelaziz Hendy, Rasha Kadri Ibrahim, Sally Mohammed Farghaly Abdelaliem, Ahmed Zaher, Sameer A. Alkubati, Rabab Gad Abd El-kader, Ahmed Hendy
BMC Pediatrics.2025;[Epub] CrossRef
RISE: a novel unified framework for feature relevance in malnutrition analytics integrating statistical and expert insights
S. Shruthi, Priya Govindarajan, S. R. Shalini, Pavan John Antony, A. N. Uma, Lalith Rangarajan
Frontiers in Public Health.2025;[Epub] CrossRef
Development and Validation of a Predictive Model for Individual Risk Prediction of Stunting in Ethiopia: A Predictive Modeling Study
Ahmed Fentaw Ahmed, Tewodros Yosef, Cherugeta Kebede Asfaw, Eyob Girum Weldeyes, Eskindir Melese Cherinet, Mohamed Abdu Oumer, Filimon Getaneh Assefa, Tinsae Tesfaw Tadege, Biniyam Mequanent Sileshi, Eyob Getaneh Yimer, Fuad Seid Ebrahim, Bemnet Yazew Abe
Health Science Reports.2025;[Epub] CrossRef
Data science and artificial intelligence for maternal, newborn and child health: scoping review and thematic analysis
Joseph Akuze, Grieven P. Otieno, Samson Yohannes Amare, Bancy Ngatia, Phillip Wanduru, Fati Kirakoya-Samadoulougou, Rornald Muhumuza Kananura, Agbessi Amouzou, Abiy Seifu Estifanos, Eric O. Ohuma
BMC Public Health.2025;[Epub] CrossRef
Exploring the multifactorial predictors of stunting in children under five: A systematic review of the literature, 2015–2024
Heti Ira Ayue, Nurdiana Nurdiana, Viera Wardhani, Ani Budi Astuti, Heri Prayitno, Agung Dwi Laksono, Tonny Sundjaya
Journal of Public Health Research.2025;[Epub] CrossRef
Predicting stunting in Rwanda using artificial neural networks: a demographic health survey 2020 analysis
Similien Ndagijimana, Ignace Kabano, Emmanuel Masabo, Jean Marie Ntaganda
F1000Research.2024; 13: 128. CrossRef
Development of a diagnostic predictive model for determining child stunting in Malawi: a comparative analysis of variable selection approaches
Jonathan Mkungudza, Halima S. Twabi, Samuel O. M. Manda
BMC Medical Research Methodology.2024;[Epub] CrossRef
Predicting harmful alcohol use prevalence in Sub-Saharan Africa between 2015 and 2019: Evidence from population-based HIV impact assessment
Mtumbi Goma, Wingston Felix Ng’ambi, Cosmas Zyambo, Yimam Getaneh Misganie
PLOS ONE.2024; 19(10): e0301735. CrossRef
Hybrid Machine Learning for Stunting Prevalence: A Novel Comprehensive Approach to Its Classification, Prediction, and Clustering Optimization in Aceh, Indonesia
Novia Hasdyna, Rozzi Kesuma Dinata, Rahmi, T. Irfan Fajri
Informatics.2024; 11(4): 89. CrossRef
Türkiye'de E-Ticaretin Kullanılma Durumunun Makine Öğrenmesi İle Sınıflandırılması ve Çeşitli Değişkenlerle İlişkilerinin Analizi
Yunus Emre Gür, Kamil Abdullah Eşidir, Cem Ayden
Karadeniz Sosyal Bilimler Dergisi.2024; 16(31): 582. CrossRef
Child stunting prevalence determination at sector level in Rwanda using small area estimation
Innocent Ngaruye, Joseph Nzabanita, François Niragire, Theogene Rizinde, Joseph Nkurunziza, Jean Bosco Ndikubwimana, Charles Ruranga, Ignace Kabano, Dieudonne N. Muhoza, Jeanine Ahishakiye
BMC Nutrition.2023;[Epub] CrossRef

First
Prev
Page of 1
Next
Last

Search