Accurate diagnosis and classification of urinary incontinence (UI) and its associated complications can be challenging in clinical practice. While evidence-based clinical guidelines exist to standardize UI management, their integration into routine care remains limited. Ontology-based clinical decision support systems (CDSS) offer a promising solution by digitizing guideline recommendations, enabling real-time clinician access, and improving diagnostic and therapeutic precision. This study aimed to develop and evaluate UrInO-DSS, an ontology-driven CDSS for UI, tailored to the Iranian clinical context through adaptation of international guidelines.

The study comprised three phases: I) A UI ontology was created using Protégé 5.5.0, based on an adapted clinical practice guideline (CPG) for Iranian urologists. Key concepts included UI subtypes, diagnostic criteria, examinations, and treatments; II) A rule-based decision support system (DSS) was built using Semantic Web Rule Language (SWRL), generating 82 diagnostic and therapeutic rules. Pellet reasoner validated ontology consistency; III) The ontology’s logical integrity was assessed via reasoner-based consistency checks, while the CDSS was evaluated using the GUIDES checklist for usability, clinical relevance, and guideline alignment.

The UI ontology, structured in OWL-DL, formally represented 53 core concepts and their relationships. The SWRL rules enabled automated reasoning for UI diagnosis, risk assessment, and personalized treatment recommendations. The Pellet reasoner confirmed ontology consistency, with no logical conflicts detected. Evaluators reported high clinical acceptability (GUIDES score: <81/100), emphasizing the system’s alignment with the adapted CPG, usability in Iranian practice, and potential to reduce diagnostic variability.

UrInO-DSS leverages real-time, up-to-date data to deliver context-aware recommendations. Its modular ontology allows seamless integration of new evidence, patient-specific data, and regional guideline updates. The system’s adaptability ensures scalability for broader urological conditions and settings.

UrInO-DSS represents the first ontology-driven CDSS for UI, demonstrating feasibility in translating guidelines into actionable clinical tools. By harmonizing structured knowledge with real-world data, such systems can standardize care, reduce diagnostic variability, and foster collaborative knowledge ecosystems. Future work will focus on multicenter validation and AI-driven adaptive learning to further optimize precision in UI management.