Improving Accessibility and Usability of Clinical Data in Switzerland: Leveraging SNOMED CT for the Swiss Personalized Health Network (Preprint)

Abstract

<sec> <title>BACKGROUND</title> In large-scale research initiatives like the Swiss Personalized Health Network (SPHN), ensuring interoperability and ease of use across diverse clinical datasets is challenging. The approach taken by SPHN with the creation of a reference common dataset integrating various data structures and standards, creates complexities for researchers aiming to explore and find specific clinical concepts for assessing project feasibility. Semantic enrichment and exploration through SNOMED CT offer a potential solution by enabling structured queries that could simplify data discoverability and enhance dataset usability across Switzerland. </sec> <sec> <title>OBJECTIVE</title> This study investigates the hypothesis that a semantic layer can improve the explorability of the SPHN dataset by leveraging SNOMED CT’s structured terminology. To validate this hypothesis, we developed the Smart SNOMED Search for SPHN (S4) tool, which leverages a semantic enrichment of the dataset, facilitating semantic searches using the Expression Constraint Language (ECL) of SNOMED CT. </sec> <sec> <title>METHODS</title> The SPHN dataset underwent semantic enrichment, where concepts and attributes not already represented were systematically mapped to SNOMED CT codes and associated value sets. The S4 tool was designed to enable ECL-based queries, allowing users to retrieve relevant SPHN concepts and value sets effectively. We tested the tool using a validation dataset representing commonly encountered clinical data warehouse elements and evaluated its precision, recall, and F1 scores. </sec> <sec> <title>RESULTS</title> The S4 tool demonstrated high accuracy, with an overall precision of 95.3%, recall of 97.5%, and an F1 score of 96.4%, indicating effective retrieval and alignment of SPHN concepts with SNOMED CT codes. The enrichment also highlighted gaps within the SPHN dataset, enabling enhanced semantic connections that further supported data discoverability. </sec> <sec> <title>CONCLUSIONS</title> The S4 tool validates the hypothesis that semantic representation enhances data explorability within large frameworks like SPHN, making it more accessible for research. While effective, future work could refine search precision and improve accessibility for users less familiar with SNOMED CT, supporting SPHN’s mission to facilitate personalized healthcare research through enhanced data interoperability. </sec>

Ähnliche Arbeiten