SavedAdd your journal

Journals / Aurum Journal of Health Sciences / 2026 / Cilt: 8 Sayı: 2

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN HEALTHCARE: A REGION FIXED-EFFECTS APPROACH TO THE GLOBAL HEALTH IMPACT OF OBESITY AND ITS NEAR-TERM FORECASTING

Sağlık Hizmetlerinde Yapay Zekâ ve Makine Öğrenmesi: Obezitenin Küresel Sağlık Etkisine Bölge Sabit Etkili Yaklaşım ve Kısa Vadeli Tahminleme

Onur Gürcan Ergen(ALTINBAŞ ÜNİVERSİTESİ)0000-0001-5756-2168
Mehmet Görgülü(ALTINBAŞ ÜNİVERSİTESİ)0000-0002-3616-6294
İnci Oktay(ALTINBAŞ ÜNİVERSİTESİ)4349-0617-0002-0000
Pages
19–30
Publication Date
2026-08-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Region fixed-effects panel regression delivers high accuracy and interpretability for near-term obesity forecasting and yields region-specific insights translatable into policy under the 6P framework.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study examines the global health impact of obesity at the World Health Organization (WHO) regional level and generates near-term forecasts of adult obesity prevalence for 2020–2022 using a region fixed-effects multiple linear regression model on a regional-year panel.
📊
Key Findings & Data:Region-year observations (n = 60) for the six WHO regions were retrieved automatically from the WHO Global Health Observatory OData API for 2010–2019 via a Python 3.11 script.
💡
Conclusion & Impact:Region fixed-effects panel regression delivers high accuracy and interpretability for near-term obesity forecasting and yields region-specific insights translatable into policy under the 6P framework.
🔬Design:Modeling & Simulation
📍Scope:2020–2022 Verileri
⚙️Variables:Obezite · yapay zekâ · panel veri analizi

Abstract

This study examines the global health impact of obesity at the World Health Organization (WHO) regional level and generates near-term forecasts of adult obesity prevalence for 2020–2022 using a region fixed-effects multiple linear regression model on a regional-year panel. Region-year observations (n = 60) for the six WHO regions were retrieved automatically from the WHO Global Health Observatory OData API for 2010–2019 via a Python 3.11 script. A two-stage strategy was applied: four predictors (overweight, underweight, physical inactivity, raised blood pressure) were projected to 2020–2022 by simple linear regression; obesity prevalence was then modeled with region fixed-effects multiple linear regression. Out-of-sample accuracy was assessed through a time-ordered backtest (training: 2010–2017; test: 2018–2019). The model achieved R² = 0.9989 and a backtest mean absolute percentage error of 4.02%. Overweight (β = +0.7385), underweight (β = +0.8094), and physical inactivity (β = +0.2232) showed significant positive associations with obesity (all p < 0.01). Forecast 2022 prevalences were 32.96% (Americas), 27.94% (Eastern Mediterranean), 22.13% (Europe), 11.23% (Africa), 9.66% (Western Pacific), and 7.53% (South-East Asia). Region fixed-effects panel regression delivers high accuracy and interpretability for near-term obesity forecasting and yields region-specific insights translatable into policy under the 6P framework.

Özet

Bu çalışma, obezitenin küresel sağlık etkisini Dünya Sağlık Örgütü (DSÖ) bölgeleri düzeyinde incelemekte ve bölgesel-yıl paneli üzerinde bölge sabit etkili çoklu doğrusal regresyon modeli kullanarak 2020–2022 dönemi için yetişkin obezite prevalansının kısa vadeli tahminlerini üretmektedir. Altı DSÖ bölgesine ait bölge-yıl gözlemleri (n = 60), 2010–2019 dönemi için Python 3.11 betiği aracılığıyla DSÖ Küresel Sağlık Gözlemevi (GHO) OData API'sinden otomatik olarak çekilmiştir. İki aşamalı bir strateji uygulanmıştır: önce dört bağımsız değişken (aşırı kilo, zayıflık, fiziksel inaktivite, yüksek kan basıncı) basit doğrusal regresyon ile 2020–2022 dönemine projekte edilmiş; ardından obezite prevalansı bölge sabit etkili çoklu doğrusal regresyon ile modellenmiştir. Örneklem dışı doğruluk, zaman sıralı geriye dönük test (eğitim: 2010–2017; test: 2018–2019) ile değerlendirilmiştir. Model R² = 0,9989 değerine ve %4,02 ortalama mutlak yüzde hatasına ulaşmıştır. Aşırı kilo (β = +0,7385), zayıflık (β = +0,8094) ve fiziksel inaktivite (β = +0,2232) obezite ile anlamlı pozitif ilişkiler göstermiştir (tümü p < 0,01). 2022 yılı için tahmin edilen prevalanslar; Amerika %32,96, Doğu Akdeniz %27,94, Avrupa %22,13, Afrika %11,23, Batı Pasifik %9,66 ve Güneydoğu Asya %7,53 olarak hesaplanmıştır. Bölge sabit etkili panel regresyonu, kısa vadeli obezite tahminlemesinde yüksek doğruluk ve yorumlanabilirlik sağlamakta; 6P yaklaşımı çerçevesinde politikaya aktarılabilir bölge özelinde içgörüler sunmaktadır.

🔖

Cite This Article

Ergen, O. G., Görgülü, M., Oktay, İ. (2026). ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN HEALTHCARE: A REGION FIXED-EFFECTS APPROACH TO THE GLOBAL HEALTH IMPACT OF OBESITY AND ITS NEAR-TERM FORECASTING. Aurum Journal of Health Sciences, Cilt: 8 Sayı: 2, 19–30. https://ajindex.com/articles/1581058

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (19)

  1. An, R., Shen, J., & Xiao, Y. (2022). Applications of artificial intelligence to obesity research: Scoping review of methodologies. Journal of Medical Internet Research, 24(12), e40589. https://doi.org/10.2196/40589
  2. Berberoğlu, Z., & Hocaoğlu, Ç. (2021). Küresel sağlık sorunu "obezite": Güncel bir gözden geçirme. Celal Bayar University Journal of Sciences and Health, 8(3), 543–552. https://doi.org/10.34087/cbusbed.886473
  3. Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70–83. https://doi.org/10.1016/j.csda.2017.11.003
  4. Bray, G. A., Kim, K. K., & Wilding, J. P. H. (2017). Obesity: A chronic relapsing progressive disease process. A position statement of the World Obesity Federation. Obesity Reviews, 18(7), 715–723. https://doi.org/10.1111/obr.12551
  5. Chen, Y., Ma, L., Han, Z., & Xiong, P. (2024). The global burden of disease attributable to high body mass index in 204 countries and territories: Findings from 1990 to 2019 and predictions to 2035. Diabetes, Obesity and Metabolism, 26(9), 3998–4010. https://doi.org/10.1111/dom.15748
  6. Choong, C., Brnabic, A., Chinthammit, C., et al. (2024). Applying machine learning approaches for predicting obesity risk using US health administrative claims database. BMJ Open Diabetes Research & Care, 12(5), e004193. https://doi.org/10.1136/bmjdrc-2024-004193
  7. Cohen, J. (1990). Things I have learned (so far). American Psychologist, 45(12), 1304–1312. https://doi.org/10.1037/0003-066X.45.12.1304
  8. Dinsa, G. D., Goryakin, Y., Fumagalli, E., & Suhrcke, M. (2012). Obesity and socioeconomic status in developing countries: A systematic review. Obesity Reviews, 13(11), 1067–1079. https://doi.org/10.1111/j.1467-789X.2012.01017.x
  9. GBD 2021 Risk Factors Collaborators. (2024). Global burden and strength of evidence for 88 risk factors in 204 countries and 811 subnational locations, 1990–2021: A systematic analysis for the Global Burden of Disease Study 2021. The Lancet, 403(10440), 2162–2203. https://doi.org/10.1016/S0140-6736(24)00933-4
  10. Grøntved, S., Kirkeby, M. J., Johnsen, S. P., et al. (2024). Towards reliable forecasting of healthcare capacity needs: A scoping review and evidence mapping. International Journal of Medical Informatics, 189, 105527. https://doi.org/10.1016/j.ijmedinf.2024.105527
  11. Haghighathoseini, A., Lin, S.-Y., Song, G., An, R., & Xue, H. (2025). A systematic review on applications of artificial intelligence for obesity prevention. Obesity Reviews, e70062. https://doi.org/10.1111/obr.70062
  12. Jakobsen, E., Olsen, K. E., Bliddal, M., et al. (2021). Forecasting lung cancer incidence, mortality, and prevalence to year 2030. BMC Cancer, 21, 985. https://doi.org/10.1186/s12885-021-08696-6
  13. NCD Risk Factor Collaboration (NCD-RisC). (2024). Worldwide trends in underweight and obesity from 1990 to 2022: A pooled analysis of 3663 population-representative studies with 222 million children, adolescents, and adults. The Lancet, 403(10431), 1027–1050. https://doi.org/10.1016/S0140-6736(23)02750-2
  14. Ölçer, E. (2024). Makine öğrenmesi temelli obezite durum tahminlemesi. Bilgisayar Bilimleri ve Mühendisliği Dergisi, 17(2), 156–164. https://doi.org/10.54525/bbmd.1469701
  15. Riley, R. D., Ensor, J., Snell, K. I. E., et al. (2019). Calculating the sample size required for developing a clinical prediction model. BMJ, 368, m441. https://doi.org/10.1136/bmj.m441
  16. Starcke, J., Spadafora, J., Spadafora, P., & Toma, M. (2025). The effect of data leakage and feature selection on machine learning performance for early Parkinson's disease detection. Bioengineering, 12(8), 845. https://doi.org/10.3390/bioengineering12080845
  17. Sterne, J. A. C., White, I. R., Carlin, J. B., et al. (2009). Multiple imputation for missing data in epidemiological and clinical research: Potential and pitfalls. BMJ, 338, b2393. https://doi.org/10.1136/bmj.b2393
  18. Wooldridge, J. M. (2010). Econometric analysis of cross section and panel data (2nd ed.). Cambridge, MA: MIT Press.
  19. World Health Organization. (n.d.). Global Health Observatory (GHO) OData API. Retrieved from https://ghoapi.azureedge.net/api/ [REPORT]