Context, complexity and process in the implementation of evidence-based innovation: a realist informed review

Abstract

Background: This review of scholarly work in health care knowledge translation advances understanding of implementation components that support the complete and timely integration of new knowledge. We adopt a realist approach to investigate what is known from the current literature about the impact of, and the potential relationships between, context, complexity and implementation process.

Methods: Informed by two distinct pathways, knowledge utilization and knowledge translation, we utilize Rogers' Diffusion of Innovations theory (DOI) and Harvey and Kitson's integrated- Promoting Action on Research Implementation in Health Service framework (PARIHS) to ground this review. Articles from 5 databases; Medline, Scopus, PsycInfo, Web of Science, and Google Scholar and a search of authors were retrieved. Themes and patterns related to these implementation components were extracted. Literature was selected for inclusion by consensus. Data extraction was iterative and was moderated by the authors.

Results: A total of 67 articles were included in the review. Context was a central component to implementation. It was not clear how and to what extent context impacted implementation. Complexity was found to be a characteristic of context, implementation process, innovations and a product of the relationship between these three elements. Social processes in particular were reported as influential however; descriptions of how these social process impact were limited. Multiple theoretical and operational models were found to ground implementation processes. We offer an emerging conceptual model to illustrate the key discoveries.

Conclusions: The review findings indicate there are dynamic relationship between context, complexity and implementation process for enhancing uptake of evidence-based knowledge in hospital settings. These are represented in a conceptual model. Limited empiric evidence was found to explain the nature of the relationships.

Keywords: Implementation; complexity; context; evidence utilization; health care; innovation; knowledge translation.

Fig. 1

Search and Section Process: This diagram outlines the process of article review and selection for inclusion in analysis

Fig. 2

Tunnel model of Implementation Context, Complexity and Process: The figure depicts an evidence-based innovation as it is introduced and moves into an acute care system. As the innovation moves into the system it is exposed to the context of that system. The innovation has intended and unintended impacts on the context of that system as a result of that exposure. The innovation is also impacted by that system as implementers and knowledge users seek to refine and ‘fit’ it to the practice reality. Complexity is represented in the textured background of the context as it is a characteristic of that context. Complexity is also generated in the relationship between the innovation, implementation process and the context. The circular arrows indicate this evolving complexity at the point of interaction between the evidence-based innovation and implementation process and the implementation process and the context. Implementation processes are situated within the context of the system. Some implementation processes refine the context of the system for improved innovation adoption while others are shaped by the existing context. As the innovation is moved through the phases of preparation, introduction, activation and integration towards adoption, intentional and organic implementation process are initiated shaping the context, the implementation processes and the evidence-based innovation. As the innovation moves further towards adoption the reciprocal relationship between context and process and process and innovation alter the shape and fit of the innovation in the new space as it is taken up. The processes fade as adoption is approached and implementation processes are less active. As adoption is achieved the innovation is transformed into an element of the system and becomes part of the context fading as it is normalized