Abstract:

Healthcare environments are increasingly complex, requiring medical professionals to continuously update their knowledge and skills. Traditional training methods often fail to accommodate variations in experience, learning styles, and evolving clinical practices, which can reduce engagement and confidence in decision-making. Effective training must therefore be flexible, personalized, and closely aligned with real-world clinical workflows.

This study presents the design and evaluation of an adaptive learning and decision support system at CHU Batna. The system provides personalized learning content based on individual profiles and integrates real-time decision support, offering guidance and alerts for potential errors. Learner progress is continuously monitored, and content is dynamically adjusted to reinforce areas of difficulty, fostering skill development, knowledge retention, and confidence.

Development involved a multi-phase methodology, including interviews with staff, workflow observation, and analysis of training records. The platform features scenario-based simulations, progressive case studies, interactive exercises, and real-time feedback, enabling clinicians to practice safely before applying skills in patient care.

Evaluation through simulated exercises showed that participants using the system exhibited higher engagement, improved confidence, and faster knowledge acquisition compared to conventional training. Personalized content reduced cognitive overload, reinforced learning, and decision support improved preparedness for complex scenarios. Participants reported enhanced applicability to daily workflows and better readiness for unexpected clinical situations.

These findings highlight the potential of adaptive, learner-centered approaches to bridge the gap between theoretical knowledge and practical application, enhance professional development, and improve patient safety. Integrating such systems into hospital workflows ensures technology complements clinical practice and supports continuous learning in dynamic healthcare environments.

Keywords:

Adaptive learning, Medical education, Decision support systems, Artificial intelligence, Personalized learning, Healthcare training.