Analysis of Influencing Factors and Equity in Hospitalization Expense Reimbursement for Mobile Populations Based on Random Forest Model: A cross-sectional study from China

Lisheng Shen¹Xinan Lu²Yanyun Zhang³Lin Fei^2*Dong Bo^4*

• ¹Department of Medical Insurance Affiliated Cixi Hospital, Wenzhou Medical University, Ningbo, China
• ²Department of Respiratory and Critical Care Medicine, Affiliated Cixi Hospital, Wenzhou Medical University, NingBo, China
• ³Department of Record room, Affiliated Cixi Hospital, Wenzhou Medical University, NingBo, China
• ⁴School of Public Health, Zhejiang Chinese Medical University, hangzhou, China

Background: Continuously improving the accessibility of hospitalization expense reimbursement and reducing medical expenses for the migrant population are critical objectives in China's health insurance reforms. Existing research lacks comprehensive analyses of reimbursement status and insufficiently addresses factors influencing reimbursement and equity. This study aims to identify key factors influencing hospitalization expense reimbursement for China's migrant population and analyze reimbursement equity. Methods: Data from the 2018 China Migrants Dynamic Survey were utilized, including 3,186 individuals who incurred hospitalization expenses. First, hospitalization reimbursement status (occurrence, location, method, and amount) was analyzed using percentages and chi-square tests. Second, random forest analysis evaluated factors influencing reimbursement. Third, regression analysis quantified key influencing factors. Lastly, the concentration index assessed reimbursement equity and key factor contributions. Results: Of migrants incurring hospitalization expenses, 69.83% reimbursed their expenses, while 30.17% did not. Reimbursement locations were predominantly at household registration places (55.69%) rather than inflow areas (44.31%). Most reimbursements (88.36%) occurred through Basic Medical Insurance for Urban and Rural Residents, and 11.64% via Basic Medical Insurance for Urban Employees. Mean hospitalization expenses were USD 3,058.70, with health insurance reimbursing USD 1,213.40 (39.67%) and individuals covering USD 1,845.30 (60.33%) out-of-pocket.Random forest results identified education, health, age, income, and local insurance enrollment as key factors influencing reimbursement occurrence. Factors influencing reimbursement levels included health status, insurance type, total medical expenditure, illness status, and mobility range. Equity analysis indicated pro-rich inequity in reimbursement probability and levels. The primary factors contributing to reimbursement probability inequity were education (42.3%), income (34.1%), health (12.4%), age (8.2%), and enrollment location (3.0%). Factors contributing to reimbursement level inequity were health (58.12%), mobility range (21.74%), total healthcare expenditures (9.35%), insurance type (9.28%), and illness (1.51%). Conclusion: Significant improvements are needed in reimbursement rates for migrant populations. Future policy should enhance insurance coordination across regions, encourage local enrollment in urban employee medical insurance to increase reimbursement, and simplify reimbursement policies to improve accessibility and comprehension.