Hospital operating profit margin(OPM), the share of operating revenue that remains after covering operating expenses, is an indicator of hospital financial stability and operational sustainability (ShepsCenter, 2003). The OPM is commonly used to compare hospitals and to assess financial distress, making it a key metric in understanding how vulnerable a hospital may be to bankruptcy (Gaffney and Michelson, 2023). Hospitals with a higher OPM are often associated with better quality of care outcomes, such as readmission rates, underscoring the importance in financial performance and patient quality of care (Ly et al., 2011). While forecasting tools are used in hospitals to facilitate scheduling, simplify billing, and identify patients who are highrisk, predictive approaches to hospital OPM remain less developed (Chang et al., 2025). Improved forecasting of OPM could assist hospitals and policy makers identify financial risks for facilities entering new markets or operating in vulnerable regions.

Given the complexity and variability in hospital financial performance, advanced predictive approaches may be valuable in identifying the factors most strongly associated with hospital financial performance. Machine learning(ML) is a branch of artificial intelligence, generally used to make predictions or classifications based on the inputted data, capturing non-linear patterns (Bergmann, 2025). Advancements in ML methods demonstrate promising changes in predicting problems within the healthcare industry, from disease diagnosis to cost predictions. Models have been developed that have improved the accuracy of hospitalization costs at the patient-level (Rao et al., 2024). Other studies have also demonstrated how ML can be used to predict hospitalization costs among coronary artery operations, pulmonary tuberculosis, and obesity (Cruz et al., 2024; Fan et al. 2024; Taloba et al., 2022). Together, these studies demonstrate that ML techniques may offer advantages for hospital-level outcomes as well.