Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Formalizing Nursing Clinical Guidelines for Episodic Decision Support: A Mixed-Methods Study of Diabetes and Pressure Ulcer Care
ABSTRACT
Background:
Nurses are expected to deliver evidence-based care in complex, time-pressured environments; however, adherence to clinical guidelines (CGs) embedded in electronic medical records (EMRs) remains suboptimal. Building on the technical infrastructure established in former work, this study focuses on the clinical knowledge engineering methodology and the valid representation of nurse-led workflows within that framework.
Objective:
To develop and evaluate a mixed-methods framework for translating free text nursing CGs into a machine-comprehensible, temporally expressive model, and to assess its performance using retrospective EMR data in geriatric inpatient care.
Methods:
A sequential mixed-methods design was employed. In the qualitative phase, knowledge engineering was used via structured expert elicitation and iterative guideline disambiguation to transform two nursing CGs (in-hospital diabetes management and pressure ulcer care) into explicit procedural and declarative knowledge. These were formalized using Asbru and Temporal Abstraction Knowledge (TAK), incorporating fuzzy logic to represent temporal flexibility and clinical uncertainty. In the quantitative phase, the resulting models underwent technical validation using scenario-based simulations (diabetes n=82; pressure ulcer n=43), followed by retrospective EMR-based simulation (1,000 records per guideline) to estimate adherence under episodic decision-support conditions. Exploratory statistical analyses included group comparisons, correlations, and unit-level differences.
Results:
The formalization process included several cycles of expert’s consensus, yielded 388 procedural concepts and 510 declarative components. Technical validation demonstrated 100% correctness and high completeness (97% for pressure ulcer care; 98% for diabetes management). In retrospective simulation, adherence to CGs was estimated to improve under episodic consultation. For pressure ulcer care, average compliance increased from between 68% and 69% at baseline up to 88% to 97% depending on activation frequency, respectively. For diabetes management, weighted compliance increased from 15% to 87% under meal-time activation, with estimated improvements ranging from 46% to 72%. Unit-level variability was observed and attenuated under simulated CDSS use.
Conclusions:
A mixed-methods, co-expert-driven formalization process can bridge the gap between narrative clinical guidelines and executable decision-support models. The resulting episodic, nurse-oriented CDSS provides context-sensitive guidance and demonstrates substantial potential to improve adherence. Prospective studies are needed to evaluate real-time implementation, clinical outcomes, and workflow integration. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.