This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
On the Effectiveness of Data Anonymization and Synthetic Data Generation for Privacy-Preserving Machine Learning in Healthcare
Corresponding Author(s) : Setio Basuki
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control,
Vol. 11, No. 4, November 2026 (Article in Progress)
Abstract
Machine learning on tabular medical data is used for clinical analysis and data-driven decision making. However, these datasets contain sensitive information, which raises privacy concerns. This calls for privacy-preserving procedures while keeping analytical utility. Anonymization and synthetic data generation have been explored extensively, but few direct comparisons across several machine learning tasks have been made. In this paper asses the effect of anonymized and synthetic data on classification, regression and clustering using six medical tabular datasets from Kaggle and UCI Machine Learning Repository ranging from 569 to 110,527 records. Anonymization was performed by a combination of pseudonymization, generalization, and attribute-based perturbation, while synthetic data were created by a Conditional Tabular Generative Adversarial Network (CTGAN). Results show that anonymization often preserves the machine learning value with respect to the original data, although the performance depends on the characteristics of the dataset and the analytical tasks. When classifying, anonymised data performed as well as original data (97.37% accuracy for the Breast Cancer dataset), whereas synthetic data showed a significant performance drop due of lower discriminative feature boundaries. Regression demonstrated the best predictive accuracy of anonymised data (R² up to 0.926) and synthetic data (largest reduction to 0.431) suggesting little preservation of complicated numerical relationships and extreme values. Anonymized data preserved data structure better, but synthetic data changed cluster distributions and reduced inherent variability.In general, anonymization provides a better balance between privacy and utility when it comes to predictive analytics in healthcare, while synthetic data is more ideal for exploratory and secondary analysis.
Keywords
Download Citation
Endnote/Zotero/Mendeley (RIS)BibTeX
- M. R. Rahman, S. Basuki, M. I. Perdana, and L. F. A. R. Cynthia, “Integrating Tabular Data and Textual Representations for Clinical Risk Prediction Using Machine Learning and Large Language Models,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, May 2026, doi: 10.22219/kinetik.v11i2.2570.
- Maulana Akmal S, Basuki S, and Wardhana Aulia A, “Exploiting vulnerabilities of machine learning models in medical text via generative adversarial attacks ,” KINETIK, vol. 10, no. 3, pp. 431–442, 2025, doi: https://doi.org/10.22219/kinetik.v10i3.2240.
- M. Irfan, S. Basuki, and Y. Azhar, “Impact of Feature Selection and Data Augmentation for Pregnancy Risk Detection in Indonesia,” vol. 12, no. 6, 2022, doi: https://doi.org/10.18517/ijaseit.12.6.16145.
- R. J. Chen, M. Y. Lu, T. Y. Chen, D. F. K. Williamson, and F. Mahmood, “Synthetic data in machine learning for medicine and healthcare,” Nat. Biomed. Eng., vol. 5, no. 6, pp. 493–497, Jun. 2021, doi: 10.1038/s41551-021-00751-8.
- Z. Zuo, M. Watson, D. Budgen, R. Hall, C. Kennelly, and N. Al Moubayed, “Data anonymization for pervasive health care: Systematic literature mapping study,” Oct. 01, 2021, JMIR Publications Inc. doi: 10.2196/29871.
- A. Goncalves, P. Ray, B. Soper, J. Stevens, L. Coyle, and A. P. Sales, “Generation and evaluation of synthetic patient data,” BMC Med. Res. Methodol., vol. 20, no. 1, May 2020, doi: 10.1186/s12874-020-00977-1.
- R. Ratra, P. Gulia, and N. S. Gill, “Evaluation of Re-identification Risk using Anonymization and Differential Privacy in Healthcare,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 2, 2022, doi: 10.14569/IJACSA.2022.0130266.
- N. Khalid, A. Qayyum, M. Bilal, A. Al-Fuqaha, and J. Qadir, “Privacy-preserving artificial intelligence in healthcare: Techniques and applications,” May 01, 2023, Elsevier Ltd. doi: 10.1016/j.compbiomed.2023.106848.
- A. Torfi, E. A. Fox, and C. K. Reddy, “Differentially private synthetic medical data generation using convolutional GANs,” Inf. Sci. (N. Y)., vol. 586, pp. 485–500, Mar. 2022, doi: 10.1016/j.ins.2021.12.018.
- J. A. Onesimu, J. Karthikeyan, J. Eunice, M. Pomplun, and H. Dang, “Privacy Preserving Attribute-Focused Anonymization Scheme for Healthcare Data Publishing,” IEEE Access, vol. 10, pp. 86979–86997, 2022, doi: 10.1109/ACCESS.2022.3199433.
- D. Slijepčević, M. Henzl, L. D. Klausner, T. Dam, P. Kieseberg, and M. Zeppelzauer, “$k$-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers,” Jun. 2022, doi: 10.1016/j.cose.2021.102488.
- M. Ghasemian and E. Ayday, “Privacy-Preserving Optimal Parameter Selection for Collaborative Clustering,” Jun. 2024, doi: 10.48550/arXiv.2406.05545.
- S. Pitoglou, A. Filntisi, A. Anastasiou, G. K. Matsopoulos, and D. Koutsouris, “Exploring the Utility of Anonymized EHR Datasets in Machine Learning Experiments in the Context of the MODELHealth Project,” Applied Sciences (Switzerland), vol. 12, no. 12, Jun. 2022, doi: 10.3390/app12125942.
- A. Guerra-Manzanares, L. J. L. Lopez, M. Maniatakos, and F. E. Shamout, “Privacy-Preserving Machine Learning for Healthcare: Open Challenges and Future Perspectives,” 2023, pp. 25–40. doi: 10.1007/978-3-031-39539-0_3.
- I. E. Olatunji, J. Rauch, M. Katzensteiner, and M. Khosla, “A Review of Anonymization for Healthcare Data,” Big Data, vol. 12, no. 6, pp. 538–555, Dec. 2024, doi: 10.1089/big.2021.0169.
- O. Ermis et al., “Privacy-preserving Hybrid Learning Framework for Healthcare,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 3420–3429. doi: 10.1016/j.procs.2024.09.215.
- T. Hyrup, A. D. Lautrup, A. Zimek, and P. Schneider-Kamp, “A systematic review of privacy-preserving techniques for synthetic tabular health data,” Discover Data, vol. 3, no. 1, Mar. 2025, doi: 10.1007/s44248-025-00022-w.
- Q. Razi, R. Piyush, A. Chakrabarti, A. Singh, V. Hassija, and G. S. S. Chalapathi, “Enhancing Data Privacy: A Comprehensive Survey of Privacy-Enabling Technologies,” 2025, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2025.3546618.
- W. Zhang, R. Liu, X. Zhu, X. Yu, and D. Jiang, “Enhancing privacy protection of physical examination data through synthetic algorithms based on differential privacy,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, Dec. 2025, doi: 10.1186/s12911-025-03109-1.
- Soumyabrata, “Stroke Prediction Dataset,” Github. Accessed: May 09, 2026. [Online]. Available: https://github.com/Soumyabrata/analyzing-stroke/tree/master/dataset
- W. N. S. and O. L. M. W. H. Wolberg, “Breast Cancer Wisconsin (Diagnostic) Dataset,” UCI Machine Learning Repository. Accessed: May 09, 2026. [Online]. Available: https://archive.ics.uci.edu/dataset/17/breast+cancer+wisconsin+diagnostic
- Ahmed Uzaki, “Cardiovascular Disease Risk Assessment Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/ahmeduzaki/cardiovascular-disease-risk-assessment-dataset
- Mirichi, “Medical Cost Personal Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/mirichoi0218/insurance/data
- Joni Arroba, “Medical Appointment No Shows Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/joniarroba/noshowappointments
- Fedesoriano, “Heart Failure Prediction Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/fedesoriano/heart-failure-prediction
- M. Pereira, M. Kshirsagar, S. Mukherjee, R. Dodhia, J. L. Ferres, and R. de Sousa, “Assessment of differentially private synthetic data for utility and fairness in end-to-end machine learning pipelines for tabular data,” PLoS One, vol. 19, no. 2 February, Feb. 2024, doi: 10.1371/journal.pone.0297271.
- A. Majeed, “Attribute-Centric and Synthetic Data Based Privacy Preserving Methods: A Systematic Review,” Sep. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/jcp3030030.
- U. Krishnan and P. Sangar, “A Rebalancing Framework for Classification of Imbalanced Medical Appointment No-show Data”, doi: 10.2478/jdis-2021.
- D. H. Won, K. S. Shin, and S. Youm, “Synthetic Data Augmentation for Imbalanced Tabular Data: A Comparative Study of Generation Methods,” Electronics (Switzerland), vol. 15, no. 4, Feb. 2026, doi: 10.3390/electronics15040883.
- S. Tasnim, M. Mamun, S. H. Chowdhury, M. I. Hussain, and M. M. Hossain, “Advancing Interpretable AI for CardiovascularRisk Assessment: A Stacking RegressionApproach in Clinical Data from Bangladesh,” Medinformatics, Dec. 2025, doi: 10.47852/bonviewmedin52027812.
- S. Shen, “Refining Medical Insurance Cost Predictions with Advanced Machine Learning Models,” INSTICC, Jan. 2026, pp. 573–580. doi: 10.5220/0013702200004670.
- C. S. Nwosu, S. Dev, P. Bhardwaj, B. Veeravalli, and D. John, “Predicting Stroke from Electronic Health Records,” in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Jul. 2019, pp. 5704–5707. doi: 10.1109/EMBC.2019.8857234.
- N. I. H. Kuo et al., “Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV,” J. Biomed. Inform., vol. 144, Aug. 2023, doi: 10.1016/j.jbi.2023.104436.
References
M. R. Rahman, S. Basuki, M. I. Perdana, and L. F. A. R. Cynthia, “Integrating Tabular Data and Textual Representations for Clinical Risk Prediction Using Machine Learning and Large Language Models,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, May 2026, doi: 10.22219/kinetik.v11i2.2570.
Maulana Akmal S, Basuki S, and Wardhana Aulia A, “Exploiting vulnerabilities of machine learning models in medical text via generative adversarial attacks ,” KINETIK, vol. 10, no. 3, pp. 431–442, 2025, doi: https://doi.org/10.22219/kinetik.v10i3.2240.
M. Irfan, S. Basuki, and Y. Azhar, “Impact of Feature Selection and Data Augmentation for Pregnancy Risk Detection in Indonesia,” vol. 12, no. 6, 2022, doi: https://doi.org/10.18517/ijaseit.12.6.16145.
R. J. Chen, M. Y. Lu, T. Y. Chen, D. F. K. Williamson, and F. Mahmood, “Synthetic data in machine learning for medicine and healthcare,” Nat. Biomed. Eng., vol. 5, no. 6, pp. 493–497, Jun. 2021, doi: 10.1038/s41551-021-00751-8.
Z. Zuo, M. Watson, D. Budgen, R. Hall, C. Kennelly, and N. Al Moubayed, “Data anonymization for pervasive health care: Systematic literature mapping study,” Oct. 01, 2021, JMIR Publications Inc. doi: 10.2196/29871.
A. Goncalves, P. Ray, B. Soper, J. Stevens, L. Coyle, and A. P. Sales, “Generation and evaluation of synthetic patient data,” BMC Med. Res. Methodol., vol. 20, no. 1, May 2020, doi: 10.1186/s12874-020-00977-1.
R. Ratra, P. Gulia, and N. S. Gill, “Evaluation of Re-identification Risk using Anonymization and Differential Privacy in Healthcare,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 2, 2022, doi: 10.14569/IJACSA.2022.0130266.
N. Khalid, A. Qayyum, M. Bilal, A. Al-Fuqaha, and J. Qadir, “Privacy-preserving artificial intelligence in healthcare: Techniques and applications,” May 01, 2023, Elsevier Ltd. doi: 10.1016/j.compbiomed.2023.106848.
A. Torfi, E. A. Fox, and C. K. Reddy, “Differentially private synthetic medical data generation using convolutional GANs,” Inf. Sci. (N. Y)., vol. 586, pp. 485–500, Mar. 2022, doi: 10.1016/j.ins.2021.12.018.
J. A. Onesimu, J. Karthikeyan, J. Eunice, M. Pomplun, and H. Dang, “Privacy Preserving Attribute-Focused Anonymization Scheme for Healthcare Data Publishing,” IEEE Access, vol. 10, pp. 86979–86997, 2022, doi: 10.1109/ACCESS.2022.3199433.
D. Slijepčević, M. Henzl, L. D. Klausner, T. Dam, P. Kieseberg, and M. Zeppelzauer, “$k$-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers,” Jun. 2022, doi: 10.1016/j.cose.2021.102488.
M. Ghasemian and E. Ayday, “Privacy-Preserving Optimal Parameter Selection for Collaborative Clustering,” Jun. 2024, doi: 10.48550/arXiv.2406.05545.
S. Pitoglou, A. Filntisi, A. Anastasiou, G. K. Matsopoulos, and D. Koutsouris, “Exploring the Utility of Anonymized EHR Datasets in Machine Learning Experiments in the Context of the MODELHealth Project,” Applied Sciences (Switzerland), vol. 12, no. 12, Jun. 2022, doi: 10.3390/app12125942.
A. Guerra-Manzanares, L. J. L. Lopez, M. Maniatakos, and F. E. Shamout, “Privacy-Preserving Machine Learning for Healthcare: Open Challenges and Future Perspectives,” 2023, pp. 25–40. doi: 10.1007/978-3-031-39539-0_3.
I. E. Olatunji, J. Rauch, M. Katzensteiner, and M. Khosla, “A Review of Anonymization for Healthcare Data,” Big Data, vol. 12, no. 6, pp. 538–555, Dec. 2024, doi: 10.1089/big.2021.0169.
O. Ermis et al., “Privacy-preserving Hybrid Learning Framework for Healthcare,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 3420–3429. doi: 10.1016/j.procs.2024.09.215.
T. Hyrup, A. D. Lautrup, A. Zimek, and P. Schneider-Kamp, “A systematic review of privacy-preserving techniques for synthetic tabular health data,” Discover Data, vol. 3, no. 1, Mar. 2025, doi: 10.1007/s44248-025-00022-w.
Q. Razi, R. Piyush, A. Chakrabarti, A. Singh, V. Hassija, and G. S. S. Chalapathi, “Enhancing Data Privacy: A Comprehensive Survey of Privacy-Enabling Technologies,” 2025, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2025.3546618.
W. Zhang, R. Liu, X. Zhu, X. Yu, and D. Jiang, “Enhancing privacy protection of physical examination data through synthetic algorithms based on differential privacy,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, Dec. 2025, doi: 10.1186/s12911-025-03109-1.
Soumyabrata, “Stroke Prediction Dataset,” Github. Accessed: May 09, 2026. [Online]. Available: https://github.com/Soumyabrata/analyzing-stroke/tree/master/dataset
W. N. S. and O. L. M. W. H. Wolberg, “Breast Cancer Wisconsin (Diagnostic) Dataset,” UCI Machine Learning Repository. Accessed: May 09, 2026. [Online]. Available: https://archive.ics.uci.edu/dataset/17/breast+cancer+wisconsin+diagnostic
Ahmed Uzaki, “Cardiovascular Disease Risk Assessment Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/ahmeduzaki/cardiovascular-disease-risk-assessment-dataset
Mirichi, “Medical Cost Personal Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/mirichoi0218/insurance/data
Joni Arroba, “Medical Appointment No Shows Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/joniarroba/noshowappointments
Fedesoriano, “Heart Failure Prediction Dataset,” Kaggle. Accessed: May 09, 2026. [Online]. Available: https://www.kaggle.com/datasets/fedesoriano/heart-failure-prediction
M. Pereira, M. Kshirsagar, S. Mukherjee, R. Dodhia, J. L. Ferres, and R. de Sousa, “Assessment of differentially private synthetic data for utility and fairness in end-to-end machine learning pipelines for tabular data,” PLoS One, vol. 19, no. 2 February, Feb. 2024, doi: 10.1371/journal.pone.0297271.
A. Majeed, “Attribute-Centric and Synthetic Data Based Privacy Preserving Methods: A Systematic Review,” Sep. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/jcp3030030.
U. Krishnan and P. Sangar, “A Rebalancing Framework for Classification of Imbalanced Medical Appointment No-show Data”, doi: 10.2478/jdis-2021.
D. H. Won, K. S. Shin, and S. Youm, “Synthetic Data Augmentation for Imbalanced Tabular Data: A Comparative Study of Generation Methods,” Electronics (Switzerland), vol. 15, no. 4, Feb. 2026, doi: 10.3390/electronics15040883.
S. Tasnim, M. Mamun, S. H. Chowdhury, M. I. Hussain, and M. M. Hossain, “Advancing Interpretable AI for CardiovascularRisk Assessment: A Stacking RegressionApproach in Clinical Data from Bangladesh,” Medinformatics, Dec. 2025, doi: 10.47852/bonviewmedin52027812.
S. Shen, “Refining Medical Insurance Cost Predictions with Advanced Machine Learning Models,” INSTICC, Jan. 2026, pp. 573–580. doi: 10.5220/0013702200004670.
C. S. Nwosu, S. Dev, P. Bhardwaj, B. Veeravalli, and D. John, “Predicting Stroke from Electronic Health Records,” in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Jul. 2019, pp. 5704–5707. doi: 10.1109/EMBC.2019.8857234.
N. I. H. Kuo et al., “Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV,” J. Biomed. Inform., vol. 144, Aug. 2023, doi: 10.1016/j.jbi.2023.104436.