The digital intelligent precise nursing framework: theory development in health recommender system

Background: With the rapid integration of artificial intelligence, the Internet of Things, and big data into healthcare, Health Recommender Systems (HRS) have emerged as powerful tools to support personalized care. However, their application in the nursing field lacks a theoretical foundation grounded in nursing science. Objective: This study aims to develop the Digital Intelligent Precise Nursing Framework, a theory-driven conceptual model for HRS adoption in nursing, to guide the design of intelligent recommendation systems that align with the holistic, person-centered principles of nursing. Methods: Drawing upon interdisciplinary literature and nursing paradigms, this study proposes a framework consisting of three interrelated components: multidimensional data, solution bank, and recommendation. Multidimensional data includes sensing modalities, information modalities, data types, and information sources. The solution bank is structured across two axes—target users and function types. Recommendation engines integrate data and solution strategies to generate user-centered inferential conclusions, supportive measures, and individualized action suggestions. Results: The framework enables intelligent nursing systems to synthesize heterogeneous data and deliver personalized, real-time, and context-aware interventions. It provides a foundation for moving nursing practice from evidence-based care to precision-guided decision-making. Conclusion: The Digital Intelligent Precise Nursing Framework offers a structured foundation for advancing intelligent HRSs in nursing by bridging nursing theory, health technology, and clinical reasoning. It supports the development of systems that are adaptive, interpretable, and responsive to users’ needs in diverse care settings.