Enhancing predictions of health insurance overspending risk through hospital departmental performance indicators

Authors

  • Yao Bu School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, China
  • Danqi Wang Big Data Center, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China
  • Xiaomao Fan College of Big Data and Internet, Shenzhen Technology University, Shenzhen, Guangdong, China
  • Jiongying Li Office of Health Insurance Administration, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China
  • Lei Hua Big Data Center, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China
  • Lin Zhang Suzhou Industrial Park Monash Research Institute of Science and Technology, Monash University, Suzhou, Jiangsu, China; Monash University-Southeast University Joint Research Institute (Suzhou), Southeast University, Suzhou, Jiangsu, China https://orcid.org/0000-0002-2064-8440
  • Wenjun Ma School of Computer Science, South China Normal University, Guangzhou, Guangdong, China
  • Liwen He Wuxi Innovation Center, Shenzhen Research Institute of Big Data, Wuxi, Jiangsu, China
  • Hao Zang School of Information and Control Engineering China University of Mining and Technology, Xuzhou, Jiangsu, China
  • Haijun Zhang Jiangsu Zhisheng Information Technology Co., LTD., Xuzhou, Jiangsu, China
  • Xingyu Liu Wuxi Health Statistics and Information Center, Wuxi, Jiangsu, China
  • Yufeng Gao Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China
  • Li Liu School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, China; Big Data Center, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China https://orcid.org/0000-0002-5582-650X

DOI:

https://doi.org/10.17305/bb.2025.12051

Keywords:

Health insurance overspending, Departmental performance indicators, Overspending risk prediction, Machine learning, Health insurance management system

Abstract

The substantial rise in health insurance expenditures, combined with delayed feedback on overspending from administrative departments, highlights the urgent need for timely reporting of such data. This study analyzed a large cohort of 549,910 discharged patients' medical records from the Wuxi Health Commission, covering the period from January 2022 to November 2023. We applied four widely recognized machine learning techniques—Logistic Regression (LR), LightGBM, Random Forest (RF), and Artificial Neural Networks (ANN)—alongside departmental performance indicators (DPIs) to develop Insurance Overspending Risk Prediction (IORP) models at both regional and hospital levels. The dataset was divided into training and testing sets in a 7:3 ratio. Experimental results showed that LightGBM outperformed the other models, achieving an accuracy of 0.82 for both regional and hospital-level predictions. Its weighted F1-score reached 0.78 at the regional level and 0.82 at the hospital level, with corresponding AUC-ROC (Area Under the Receiver Operating Characteristic Curve) values of 0.91 and 0.94, demonstrating strong performance in identifying overspending risks. The model’s high recall and precision further ensure reliable predictions and minimize misclassifications. Notably, four key DPIs—Total Amount of Discharged Patients (TADP), Average Inpatient Stay (AIS), Medicine Expenses Percentage (MEP), and Consumable Expenses Percentage (CEP)—were strongly correlated with overspending risks. The integration of IORP models into the Health Insurance Management System (HIMS) at the Affiliated Hospital of Jiangnan University has significantly improved departmental managers' ability to anticipate overspending. By effectively leveraging HIMS in combination with this advanced model, managers can perform timely, accurate assessments, thereby enhancing financial oversight and resource allocation.

Citations

Downloads

Download data is not yet available.
Enhancing predictions of health insurance overspending risk through hospital departmental performance indicators

Downloads

Additional Files

Published

28-06-2025

How to Cite

1.
Enhancing predictions of health insurance overspending risk through hospital departmental performance indicators. Biomol Biomed [Internet]. 2025 Jun. 28 [cited 2025 Aug. 18];. Available from: https://www.bjbms.org/ojs/index.php/bjbms/article/view/12051