Integrating electronic health record information to support integrated care

Display Omitted Multiple clinical perspectives must underpin a multi-attribute phenotyping ontology.Ontological integration of EHR elements can compensate for deficiencies in quality.Ontological approaches can improve accuracy of phenotyping algorithms.Ontologically integrated EHR and best practice guidelines can support integrated care.An integrated ontological approach to big clinical data can render them more usable and useful. BackgroundInformation in Electronic Health Records (EHRs) are being promoted for use in clinical decision support, patient registers, measurement and improvement of integration and quality of care, and translational research. To do this EHR-derived product creators need to logically integrate patient with information and knowledge from diverse sources and contexts. ObjectiveTo examine the accuracy of an ontological multi-attribute approach to create a Type 2 Diabetes Mellitus (T2DM) register to support integrated care. MethodsGuided by Australian best practice guidelines, the T2DM diagnosis and management ontology was conceptualized, contextualized and validated by clinicians; it was then specified, formalized and implemented. The algorithm was standardized against the domain ontology in SNOMED CT-AU. Accuracy of the implementation was measured in 4 datasets of varying sizes (927-12,057 patients) and an integrated dataset (23,793 patients). Results were cross-checked with sensitivity and specificity calculated with 95% confidence intervals. ResultsIncrementally integrating Reason for Visit (RFV), medication (Rx), and pathology in the algorithm identified nearly100% of T2DM cases. Incrementally integrating the four datasets improved accuracy; controlling for sample size, incompleteness and duplicates. Manual validation confirmed the accuracy of the algorithm. ConclusionIntegrating multiple elements within an EHR using ontology-based case-finding algorithms can improve the accuracy of the diagnosis and compensate for suboptimal quality, and hence creating a dataset that is more fit-for-purpose. This clinical and pragmatic application of ontologies to EHR improves the integration of and the potential for better use of to improve the quality of care.