Bridges have a long design life, but over time, their function and quality decline due to material degradation and other factors. Therefore, a bridge management system (BMS) is crucial for making appropriate maintenance decisions. This study developed a model to determine bridge maintenance priorities on the Solo-Ngawi Toll Road, which includes 70 bridges by integrating an economic feasibility evaluation (BMS) method with machine learning using the Random Forest algorithm. The bridge condition was conducted in accordance with the 2022 Bridge Inspection Guidelines, while the economic evaluation was based on the 1993 IBMS guidelines, using Net Present Value per square meter (NPV/m²) and Internal Rate of Return (IRR) indicators. The results of the economic evaluation in the form of bridge maintenance priority rankings, were used as the primary target variables for the machine learning model, enabling Random Forest to predict the order of economic priority for maintenance directly. Input variables include 13 bridge element Condition Scores summarized through the Weighted Condition Score (WCS), as well as five economic variables such as remaining service life, floor area, AADT, diversion distance, and maintenance costs. The Random Forest model produces an R² on the test data of 0.8744. Comparison of ranking results between the BMS and Random Forest methods shows good consistency in high-priority bridges and the Random Forest model is able to identify bridges with critical structural conditions that are less accommodated by the conventional BMS method, resulting in more holistic treatment recommendations.