ANALYSIS OF HEALTH INSURANCE UTILIZATION TRENDS AND MANAGEMENT IMPLICATIONS USING DATA FROM A PRIVATE HOSPITAL IN BINH DUONG PROVINCE, VIETNAM
Main Article Content
Abstract
Objective: To analyze trends in health insurance (HI) utilization and examine selected management implications at a private hospital in the context of ongoing healthcare payment reforms.
Methods: A convergent mixed-methods study was conducted using 173,280 electronic medical records of insured patients at Hoan Hao Thuan An Hospital from 2022 to 2024, combined with 40 in-depth interviews. Quantitative analyses included multivariable Logistic regression, ARIMA forecasting, random forest modeling following TRIPOD+AI recommendations, and interrupted time-series (ITS) analysis.
Results: The number of insured healthcare visits increased by 21.0% during the study period, with outpatient services accounting for more than 96% of total encounters. Patients in the group of 62 severe diseases had a significantly higher referral risk (OR = 5.40; p < 0.0001). Lack of MRI/MSCT services was associated with increased referral risk (OR = 2.64; p < 0.001). The ARIMA(1,1,1) model predicted an annual increase of 8.5–11.2% in insured visits during 2025–2027. The random forest model achieved a ROC-AUC of 0.885, with ICD-10 coding errors identified as the leading contributor to reimbursement denial risk. ITS analysis demonstrated a reduction in average hospital length of stay from 5.80 to 4.45 days after implementation of the diagnosis-related group (DRG) payment model (p < 0.001).
Conclusions: Increasing health insurance utilization and changes in healthcare payment mechanisms require stronger data governance and operational capacity in private healthcare facilities. Standardizing ICD-10 coding, upgrading digital infrastructure, and applying data analytics may improve health insurance management and support adaptation to emerging payment reforms.
Keywords
health insurance, private hospital, DRG, ICD-10, machine learning, healthcare management
Article Details
References
2. Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. doi:10.1136/bmj-2023-078378.
3. Ekman B, Liem NT, Duc HA, Axelson H. Health insurance reform in Vietnam: a review of recent developments and future challenges. Health Policy Plan. 2008;23(4):252-263. doi:10.1093/heapol/czn009.
4. Huang X, Zhu J, Zhang J. Impacts of DRG point-based payment system on healthcare resource utilization and provider behavior: a pilot quasi-experimental study in China. Front Public Health. 2025;13:1678259. doi:10.3389/fpubh.2025.1678259.
5. Jha S, Yang E, Almagrabi A, et al. Comparative analysis of time series model and machine learning systems for forecasting. Neural Comput Appl. 2020;33:14179-14196.
6. Ljung GM, Box GEP. On a measure of lack of fit in time series models. Biometrika. 1978;65(2):297-303.
7. Matsushima M, Yamada H. Public Health Insurance in Vietnam towards Universal Coverage. 2014.
8. Zhang H, Fu X, Wu Y, Tang Y, Jin H, Xie B. The impact of DRG-based payment reform on inpatient healthcare utilization: evidence from a natural experiment in China. Healthcare (Basel). 2025;13(19):2424. doi:10.3390/healthcare13192424.