Streamline Information, Personalize Learning: Patient-Centered Knowledge Delivery for Medical Professionals

Abstract

This paper presents a prototype recommendation system for personalized medical education, which leverages patient-specific diagnostic data to automatically identify and deliver relevant scientific literature on an individual basis. Diagnosis selectors extract key terms from practice management data, which are used as search queries in medical databases (e.g., PubMed). The relevance of the retrieved publications is calculated using a weighted Jaccard similarity and presented interactively on a companion tablet. The system is complemented by manually curated literature to ensure quality. Initial tests with synthetic data demonstrate the technical feasibility and potential to reduce workload in daily medical practice. By addressing the challenges of information overload and time constraints, the system offers a low-threshold entry point for continuing education tailored to the actual needs of a physician’s own patient population.

Keywords: Further Education, Personalized learning, Adaptive learning, Continuing medical education (CME)

DOI: 10.54941/ahfe1006985