This work advances the development of an autonomous patient recommendation system by leveraging knowledge graphs (KGs) to map and analyze patient journeys. We introduce the Patient Journey Ontology (PJO) to systematically represent diagnoses, treatments, and outcomes, enabling the construction of interoperable Patient Journey Knowledge Graphs (PJKGs). Using large language models, clinical dialogues are automatically transformed into structured PJKGs that capture the complete trajectory of patient care. To power recommendations, we propose the Dynamic Feature and Temporal Similarity (DFTS) framework, which integrates feature based and temporal similarity with dynamic weighting, designed to work effectively even with limited healthcare data. A case study in chronic disease management demonstrates the system’s ability to identify comparable patient journeys and generate personalized recommendations. This work establishes a foundation for autonomous, data-driven decision support that enhances patient-centered healthcare delivery.