A Semantic Framework for Patient Digital Twins in Chronic Care

Personalized chronic care requires the integration of multimodal health data to enable precise, adaptive, and preventive decision-making. Yet most current digital twin (DT) applications remain organ-specific or tied to isolated data types, lacking a unified and privacy-preserving foundation. This paper introduces the Patient Medical Digital Twin (PMDT), an ontology-driven in silico patient framework that integrates physiological, psychosocial, behavioral, and genomic information into a coherent, extensible model. Implemented in OWL 2.0, the PMDT ensures semantic interoperability, supports automated reasoning, and enables reuse across diverse clinical contexts. Its ontology is structured around modular Blueprints (patient, disease and diagnosis, treatment and follow-up, trajectories, safety, pathways, and adverse events), formalized through dedicated conceptual views. These were iteratively refined and validated through expert workshops, questionnaires, and a pilot study in the EU H2020 QUALITOP project with real-world immunotherapy patients. Evaluation confirmed ontology coverage, reasoning correctness, usability, and GDPR compliance. Results demonstrate the PMDT's ability to unify heterogeneous data, operationalize competency questions, and support descriptive, predictive, and prescriptive analytics in a federated, privacy-preserving manner. By bridging gaps in data fragmentation and semantic standardization, the PMDT provides a validated foundation for next-generation digital health ecosystems, transforming chronic care toward proactive, continuously optimized, and equitable management.