Less is More: Context-relevant views of EHRs

Project Summary We propose to refine and evaluate a system for automatically creating context relevant views of electronic health recordsEHROlder patientswith multiple conditionstend to have larger amounts of data in their EHRsThis creates an information overload problem for clinicians managing their carerequiring more time and effort to find the data they need for a particular task or contextMore importantlynot all of the relevant data may be used in decision makingThe information overload problem is exacerbated for many clinicianssuch as hospitalistswho may not be familiar with a patient s health historybut must rapidly assess a patient and make decisions about managing their careWe intend to address this problem by automatically creating context relevant views of the patient s EHR using Loupea knowledge base containing concept associationsLoupewhich was previously created by ushas overmillion associations between coded concepts from clinical terminologies including ICDICDSNOMED CTRXNORMCPT and LOINCencompassing the categories of diagnosesfindingsmedicationsprocedures and laboratory testsLoupe can be used to filter EHR data based on associated conceptsThis can be used to create views of the EHR around a condition such as acute kidney injurythereby reducing the information shown to the clinicianOur proposal has two aimsThe first aim is to evaluate the performance of Loupe in filtering de identified EHR data for acute kidney injuryAKIand geriatric altered mental statusAMSBoth these conditions are significant for elderly patientsWe will use traditional information retrieval measures including precision and recall to assess the performance of LoupeThe second aim is to create and evaluate context relevant views for AKI and AMSWe will use an iterative design approach to create the viewsThe evaluation will compare the context relevant view to traditional EHR views with hospitalists as subjectsThe study will be performed in a laboratory setting at the University of California San Diego HospitalsWe will compare the ability of the hospitalists to recall patient informationthe time taken to review the patient dataand the number of mouse clicks Project Narrative This research is aimed at reducing the information overload from large electronic health records that are often associated with older patientsLarge and complex medical records make it difficult and time consuming for clinicians to find the data they need to make decisionsReducing the information overload potentially allows reduction in time spentreduction in effortand increase in the use of relevant information in decision makingWe have developed Loupea knowledge base that can be used to automatically create views of an EHR relevant to a particular contextFor examplea clinician who wants to manage a patient s heart failure can be presented with data relevant to heart failurefiltering out data that is not relevant to that context of careIn our studywe will evaluate the performance of the knowledge engine and its impact on clinical decision making in acute kidney injury and geriatric altered mental status