Forecasting Noncommunicable Diseases in Thailand: Evaluating the Predictive Power of Social Determinants of Health-Related Features

Peatiphat Bhoothookngoen and Nattapong Sanchan

Abstract

In Thailand, non-communicable diseases (NCDs) present a significant health and economic challenge. This study investigated machine learning (ML) for predicting NCD prevalence using social determinants of health (SDHs) under two scenarios: baseline and inference (imputing missing values). Monthly household expenditure and hospital counts emerged as pivotal features in the inference scenario. Model performance was comparable between scenarios, with slight variation for specific NCDs. Random Forest (RF) showed slightly superior predictive power (RMSE: 1.53–74.93, R²: -0.11–0.11), though interpretability remains a challenge. Addressing data limitations and enhancing interpretability are crucial for fully harnessing ML's potential in NCD prediction and prevention. The findings underscore the importance of integrating ML and SDHs into public health policy to effectively combat NCDs in Thailand, and highlight the need for continued efforts to address data disparities and enhance model interpretability.

Keywords: noncommunicable diseases, predictive power, social determinants of health, machine learning, prevalence

References

Download paper (PDF) Download BibTeX

BibTeX entry

@article{Bhoothookngoen_Sanchan_2025,
  title   = {Forecasting Noncommunicable Diseases in Thailand: Evaluating the Predictive Power of Social Determinants of Health-Related Features},
  author  = {Bhoothookngoen, Peatiphat and Sanchan, Nattapong},
  journal = {Srinakharinwirot University Engineering Journal},
  volume  = {21},
  number  = {1},
  pages   = {39--49},
  year    = {2025},
  month   = {Jun},
  address = {Bangkok, Thailand}
}

Rich-text citation (copy & paste)

Bhoothookngoen, P., & Sanchan, N. (2025). Forecasting Noncommunicable Diseases in Thailand: Evaluating the Predictive Power of Social Determinants of Health-Related Features. Srinakharinwirot University Engineering Journal, 21(1), 39–49.

More information

This paper is a continuing work in the Noncommunicable Disease Prediction project: