RehaPlus: AI-Powered Identification of Complex Rehabilitation Cases in Public Health Insurance

This information was sourced from the European Commission, Joint Research Centre (2026): PSTW: Public Sector Tech Watch latest dataset of selected cases. [Dataset] doi: 10.2905/JRC.J1MWC9R PID: http://data.europa.eu/89h/e8e7bddd-8510-4936-9fa6-7e1b399cbd92. Licensed under Creative Commons Attribution 4.0 (CC BY 4.0).

The statutory accident insurer BG ETEM introduced RehaPlus to improve the early identification of complex rehabilitation cases requiring intensive case management. Previously, such cases were often detected late through manual reminders, leading to delayed interventions, higher treatment costs and longer recovery times. RehaPlus applies explainable machine learning models to continuously monitor case data and flag potential high-risk cases weeks earlier than before. This has replaced the outdated manual reminder process with proactive, automated monitoring, while ensuring case officers remain in control of final decisions. The result is improved efficiency, fewer documents to screen or complete, earlier interventions, and better recovery outcomes for insured workers.

Since going live in 2021, RehaPlus has delivered high user satisfaction, with more than 90 per cent of staff rating it positively for improving efficiency and quality of work. Built with open-source components such as Python, XGBoost, Scikit-learn, Pandas and Docker, the solution is lightweight, explainable, cost-efficient and fully compliant with GDPR. Its modular architecture makes it portable across infrastructures and scalable to other social accident insurers, with the first reuse planned for 2026. By combining automation with transparency and human oversight, RehaPlus demonstrates how AI can create both internal efficiency gains (G2G) and societal value (G2C) through better rehabilitation outcomes.

Budget: Not disclosed