Automated Filtering and Visualization of Patient-Centered Data from Electronic Health Records in Emergency Care: A Scoping Review

Janek Lenz,1,* Isabel Richter,1,* Sven Meister1,2 1Health Care Informatics, Faculty of Health/School of Medicine, Witten/Herdecke University, Witten, Germany; 2Department Healthcare, Fraunhofer Institute for Software and Systems Engineering, Dortmund, Germany*These authors contributed equally to this workCorrespondence: Janek Lenz, Health Care Informatics, Faculty of Health/School of Medicine, Witten/Herdecke University, Alfred-Herrhausen-Strasse 50, Witten, 58455, Germany, Email [email protected]: As the volume and complexity of electronic health record (EHR) data continue to grow, clinicians face increasing cognitive burden when retrieving and interpreting patient data. This is particularly problematic in high-pressure environments such as emergency care, where time-critical decisions must be made based on rapidly accessible, relevant information. Across the included studies and in consistency with findings in the broader literature poor EHR usability and unfiltered data presentation contribute to inefficiencies, errors, and clinician burnout. Patient-centered dashboards and tools that automatically extract and visually organize relevant clinical data offer a promising strategy to mitigate these challenges.Purpose: This scoping review aims to map the current literature on the automated extraction and visualization of patient-centered information from EHRs for emergency settings. It investigates 1) how clinically relevant data is selected and filtered, 2) which design strategies are used in dashboard development, and 3) what information is considered essential for overview displays in acute care and comparable contexts.Methods: The review follows the PRISMA-ScR framework. A comprehensive literature search was conducted across major databases (PubMed, Scopus, IEEE Xplore) for studies published from 2010 onwards. Studies were included if they examined automated data filtering, visualization, or dashboard design using EHR data.Results: Included studies demonstrate a range of approaches to data filtering, from rule-based systems to Artificial Intelligence-driven models. They emphasize the importance of aligning visualizations with clinicians’ cognitive workflows. Relevant parameters frequently included medications, allergies, vital signs, past medical history, and care directives. Design processes often incorporated user-centered and iterative methods, though evaluation rigor varied widely. Several studies report improvements in decision-making efficiency, treatment, and cognitive load reduction.Conclusion: Automated, patient-centered dashboards can improve EHR usability and support safer, faster decision-making in acute care. However, further research is needed to evaluate clinical impact, ensure interoperability, and define core data elements across settings.Keywords: Electronic health record, information filtering, artificial intelligence, clinical dashboard, emergency medicine, information filtering, scoping review