Prediction Of Daily Patient Visits At A Community Health Center Using Long Short-Term Memory (LSTM) With Laplace Differential Privacy

Azzahra Azzahra; Sudin Saepudin; Gina Syabani Yuda

doi:10.55227/ijhet.v5i3.1140

Authors

Azzahra Azzahra Universitas Nusa Putra
Sudin Saepudin Department of Information Systems, Faculty of Engineering, Computers and Design, Nusa Putra University, Sukabumi, Indonesi
Gina Syabani Yuda Department of Information Systems, Faculty of Engineering, Computers and Design, Nusa Putra University, Sukabumi, Indonesi

DOI:

https://doi.org/10.55227/ijhet.v5i3.1140

Keywords:

LSTM, Patient Visit Prediction, Differential Privacy, Laplace, Electronic Medical Records

Abstract

This study aims to analyze the performance of Long Short-Term Memory (LSTM) in predicting daily patient visits using limited-scale Electronic Medical Record (EMR) data and to evaluate the effect of applying Laplace Differential Privacy on prediction accuracy. The data were obtained from the EMR of Puskesmas in Sukabumi Regency, covering the period from January to December 2025. The data were preprocessed through cleaning, aggregation of daily patient visits, exclusion of holidays, and the construction of 14 days sequences. The LSTM model was evaluated using walk-forward validation with an expanding-window scheme consisting of five folds, while privacy protection was implemented using the Laplace mechanism with . The results showed that the baseline model achieved an RMSE of 25.08 and an MAE of 22.19. The application of Differential Privacy increased prediction errors, with higher errors levels observed at smaller Increasing from 1.0 to 2.0 resulted in the largest reduction in prediction error, while further increas provided relatively small improvements. Based on these results, provided the most acceptable balance between privacy protection and prediction performance for the dataset used in this study.

Downloads

Download data is not yet available.

References

Ab Kader, N. I., Yusof, U. K., & Khalid, M. N. A. (2023). Forecasting Inpatient and Outpatient Visits for Depressive Disorders: A Comparative Study of Deep Learning Approaches. Applications of Modelling and Simulation, 7(Vol. 7 No. 2), 168–177. https://doi.org/10.31224/osf.io/9p7m5

Aisyah, D. N., Setiawan, A. H., Mayadewi, C. A., Lokopessy, A. F., Kozlakidis, Z., & Manikam, L. (2025). Understanding Health Information Systems Utilization Across Public Health Centers in Indonesia: Cross-Sectional Study. JMIR Medical Informatics, 13, 1–15. https://doi.org/10.2196/68613

Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., Duan, Y., Abdullah, A., Farhan, L., Lu, Y., Gupta, A., Albu, F., Abbosh, A., & Gu, Y. (2023). A Survey on Deep Learning Tools Dealing with Data Scarcity: Definitions, Challenges, Solutions, Tips, and Applications. Journal of Big Data, 10(1), 1–82. https://doi.org/10.1186/s40537-023-00727-2

Bai, L., Lu, K., Dong, Y., Wang, X., Gong, Y., Xia, Y., Wang, X., Chen, L., Yan, S., Tang, Z., & Li, C. (2023). Predicting monthly hospital outpatient visits based on meteorological environmental factors using the ARIMA model. Scientific Reports, 13, 2691. https://doi.org/10.1038/s41598-023-29897-y

Blanco-Justicia, A., Sánchez, D., Domingo-Ferrer, J., & Muralidhar, K. (2023). A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning. ACM Computing Surveys, 55(8). https://doi.org/10.1145/3547139

Daroedono, E., Aurellita, N., Savero, I., Sirait, G. P., Imanuel, R., & Kuheba, E. G. (2025). The Curative Role of the Main Primary Health Facility in Indonesia: Analyzing Patient Visits at a Single PUSKESMAS with a Focus on General and Maternal-Child Health Clinics. Asian Journal of Research in Medical and Pharmaceutical Sciences, 14(2), 68–78. https://doi.org/10.9734/ajrimps/2025/v14i2306

Dinas Kesehatan Kabupaten Sukabumi. (2024). Profil Kesehatan Kabupaten Sukabumi Tahun 2024. In Buku. Dinas Kesehatan Kabupaten Sukabumi.

Lindemann, B., Müller, T., Vietz, H., Jazdi, N., & Weyrich, M. (2021). A survey on long short-term memory networks for time series prediction. Procedia CIRP, 99, 650–655. https://doi.org/10.1016/j.procir.2021.03.088

Liu, W., Zhang, Y., Yang, H., & Meng, Q. (2023). A Survey on Differential Privacy for Medical Data Analysis. Annals of Data Science, May, 1–15. https://doi.org/10.1007/s40745-023-00475-3

Mohammadi, M., Vejdanihemmat, M., Lotfinia, M., Rusu, M., Truhn, D., Maier, A., & Tayebi Arasteh, S. (2026). Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications. Npj Digital Medicine, 9(1). https://doi.org/10.1038/s41746-025-02280-z

Panggabean, M. V., & Fitria, A. (2025). Perlindungan Hukun Data Pribadi di Indonesia (Kasus Kebocoran Badan Penyelenggara Jaminan Sosial Kesehatan). Arus Jurnal Sosial Dan Humaniora, 5(3), 3678–3688. https://doi.org/10.57250/ajsh.v5i3.1741

Saputra, A., Hajar, S., & Sari, M. T. (2024). Analisis Kebijakan Kesehatan Dalam Meningkatkan Mutu Pelayanan Kesehatan Puskesmas Di Kota Medan. Jurnal Ilmu Administrasi, 15(02), 210–227. https://doi.org/10.23969/kebijakan.v15i02.10182

Shrestha, S. G., & Pradhanang, S. M. (2023). Performance of LSTM over SWAT in Rainfall-Runoff Modeling in a Small, Forested Watershed: A Case Study of Cork Brook, RI. Water, 15(4194), 1–15. https://doi.org/https://doi.org/10.3390/w15234194

Yuridis, A., Informasi, A., Studi, I., Penjualan, K., & Pasien, D. (2021). Juridical Analysis of Illegal Information Access: Case Study on Sales of Data Patients Covid ‐ 19. SOEPRA Jurnal Hukum Kesehatan, 7(1), 1–13. https://doi.org/10.24167/shk.v7i1.268

Zhao, D., Zhang, H., Cao, Q., Wang, Z., He, S., Zhou, M., & Zhang, R. (2022). The Research of ARIMA, GM(1,1), and LSTM Models for Prediction of TB cases in China. PLoS ONE, 17(2 February), 1–18. https://doi.org/10.1371/journal.pone.0262734