An Electronic Health Record (EHR), in addition to a clinician’s interpretations and medical decisions, has information on a patient’s health and care. What is lacking though is the background, or the context why a clinician took a particular decision. Having this information in the EHR would greatly help augment patient care.
To expand care context data through clinical notes and communication during patient visits, researchers reviewed how EHRs document clinician reasoning. Researchers discovered that EHRs rely on clinicians to document details within their notes. It was also revealed that most clinical decision support solutions that incorporate ontology in its logic do not adequately provide relationships that represent care context.
Therefore, researchers aimed to expand care context data by analyzing the transcripts of the patient visits and extracting information from clinician notes. Subsequently, researchers consolidated the results of each data set and produced 82 tuples to represent patient care context data.
Therefore, the researchers recommended creating, expanding, and validating a formal ontology. But to implement a formal ontology, researchers envisioned a next-generation EHR capable of processing a patient care context that continuously populates a Patient-Specific Knowledge Base (PSKB) in real-time.
By using a formal ontology to convert the verbal notes communicated by a clinician during a visit into structured and coded concepts, EHRs could be enhanced. It would not only facilitate data entry in real-time, but it would also auto-populate the PSKB with detail. As a result, the PSKB would continuously populate the care context to boost several EHR functions in a cycle.
The researchers also concluded that the solution proposed by them for improving the EHR will depend on improvements to and the application of constantly evolving computational methods and hence may still take several years to mature.
Brought to you by Scope e-Knowledge Center, an SPi Global Company, a trusted global partner for Digital Content Transformation Solutions, Knowledge Modeling (Taxonomies, Thesauri and Ontologies), Abstracting & Indexing (A&I), Metadata Enrichment and Entity Extraction.
Please give your feedback on this article or share a similar story for publishing by clicking here.