EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Synthetic data generation of health and demographic surveillance systems data: a case study in a low- and middle-income country

Dorcas G Mwigereri iD, Nigel T Kamotho, Akbar K Waljee, Ryan T Rego, Eileen M Weinheimer-Haus, Farhana Alarakhiya, Anthony K Ngugi, W Nicholson Price, Ji Zhu, Stephen Peter Wong, Geoffrey H Siwo

JAMIA Open · 03.11.2025 · 8 (6)

DOI: 10.1093/jamiaopen/ooaf137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 19.11.2025. Verfasst von Dorcas G Mwigereri und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Population Health, The Aga Khan University, 30270-00100 Nairobi, Kenya. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Institutes of Health, National Institute of Biomedical Imaging and Bioengineering, the National Institute of Mental Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To evaluate effectiveness of open-source generative models in producing high-quality tabular synthetic data using a Health and Demographic Surveillance System (HDSS) dataset from rural Kenya, as a proof of concept in a low- and middle-income (LMIC) setting. Materials and Methods Three open-source models (CTGAN, TableGAN, and CopulaGAN) were used to generate synthetic data from the Kaloleni/Rabai HDSS dataset. To assess the quality of the synthetic datasets generated by each model, we performed fidelity, utility, and privacy tests.

Results

CTGAN outperformed the other models, producing synthetic data that closely mirrored the statistical properties of the real dataset while preserving privacy. Both CopulaGAN and TableGAN performed poorly, with TableGAN completely failing to generate realistic synthetic data. For the utility tests, Random Forest models trained on CTGAN-generated synthetic data achieved comparable performance to models trained on real data (accuracy: 72.4% vs 72.0%, P = .38; F1 score: 71.4% vs 68.3%, P = .22), indicating no statistically significant loss in predictive utility. The CTGAN model also yielded higher precision and recall than CopulaGAN, suggesting that the synthetic data generated by CTGAN better preserved the underlying structure of the real data.

Discussion

CTGAN demonstrated superior performance in generating high-quality synthetic tabular HDSS data. CopulaGAN and TableGAN produced lower quality data, though these results may not generalize to other datasets.

Conclusion

Synthetic data generation of tabular data using HDSS data, particularly via CTGAN, may enhance the accessibility of datasets in LMICs by creating synthetic datasets that preserve the characteristics and statistical properties of the original data, while upholding privacy and confidentiality.

Schlagwörter

Stichwörter der Autor:innen

AIHDSSgenerative adversarial networkshealth and demographic surveillance systemsmachine learningsynthetic data

Autor:innen und Institutionen

  • Department of Population Health, The Aga Khan University, 30270-00100 Nairobi, Kenya.
  • Data Innovation Office, Aga Khan Univeristy, 30270-00100 Nairobi, Kenya.
  • Center for Global Health Equity, Michigan Medicine, University of Michigan at Ann Arbor, Ann Arbor, MI 48109, United States.
  • Department of Learning Health Sciences, University of Michigan Medical School, Ann Arbor, MI 48109, United States.
  • Maximum Impact Incubator, Clinton Health Access Initiative, Boston, MA 02127, United States.
  • University of Michigan Law School, Ann Arbor, MI 48109, United States.

ORCID-Profile: Dorcas G Mwigereri

Förderung

  • National Institutes of Health
  • National Institute of Biomedical Imaging and Bioengineering
  • the National Institute of Mental Health
  • the Fogarty International Center (FIC) of the National Institutes of Health
  • Novo Nordisk Foundation

Zitieren

APA

Mwigereri, D. G., Kamotho, N. T., Waljee, A. K., Rego, R. T., Weinheimer-Haus, E. M., Alarakhiya, F., Ngugi, A. K., Price, W. N., Zhu, J., Wong, S. P., & Siwo, G. H. (2025). Synthetic data generation of health and demographic surveillance systems data: a case study in a low- and middle-income country. JAMIA Open, 8(6). https://doi.org/10.1093/jamiaopen/ooaf137

Vancouver

Mwigereri DG, Kamotho NT, Waljee AK, Rego RT, Weinheimer-Haus EM, Alarakhiya F, et al. Synthetic data generation of health and demographic surveillance systems data: a case study in a low- and middle-income country. JAMIA Open. 2025;8(6). doi:10.1093/jamiaopen/ooaf137

BibTeX
@article{Mwigereri2025,
  author = {Mwigereri, Dorcas G and Kamotho, Nigel T and Waljee, Akbar K and Rego, Ryan T and Weinheimer-Haus, Eileen M and Alarakhiya, Farhana and Ngugi, Anthony K and Price, W Nicholson and Zhu, Ji and Wong, Stephen Peter and Siwo, Geoffrey H},
  title = {Synthetic data generation of health and demographic surveillance systems data: a case study in a low- and middle-income country},
  journal = {JAMIA Open},
  year = {2025},
  volume = {8},
  number = {6},
  doi = {10.1093/jamiaopen/ooaf137}
}
Kostenlos starten →