SHACL-Based Report Quality Evaluation for Health IT-Induced Medication Errors [chapter]

Daniel Keuchel, Nicolai Spicher, Ju Wang, Michael Völcker, Yang Gong, Thomas M. Deserno
2022 Studies in Health Technology and Informatics  
Patient safety event (PSE) reports are an important source of information for analyzing risks in healthcare processes. However, the reports' quality is often low due to missing or imprecise information. We work towards an automatic analysis of reports and quality evaluation. To leverage a suitable data representation of health IT-induced medication error reports, we apply the Shapes Constraint Language (SHACL). We define an ontology representing these reports and construct a corresponding SHACL
more » ... graph. Three authors manually annotate and transform 20 textual reports to the SHACL representation. Furthermore, we use this representation to compute a quality score for each report. The results indicate the suitability of SHACL as a representation of health IT-induced medication error reports, which paves a path of automatically extracting information from PSE reports using text mining and transform them to SHACL for quality evaluation.
doi:10.3233/shti220108 pmid:35673047 fatcat:lshrjevcdjd2nenerdhskopnei