Mining Electronic Health Records to Guide and Support Clinical Decision Support Systems

Mining Electronic Health Records to Guide and Support Clinical Decision Support Systems

Jitendra Jonnagaddala (University of New South Wales, Australia), Hong-Jie Dai (National Taitung University, Taiwan), Pradeep Ray (University of New South Wales, Australia) and Siaw-Teng Liaw (University of New South Wales, Australia)
DOI: 10.4018/978-1-4666-9432-3.ch012
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Clinical decision support systems require well-designed electronic health record (EHR) systems and vice versa. The data stored or captured in EHRs are diverse and include demographics, billing, medications, and laboratory reports; and can be categorized as structured, semi-structured and unstructured data. Various data and text mining techniques have been used to extract these data from EHRs for use in decision support, quality improvement and research. Mining EHRs has been used to identify cohorts, correlated phenotypes in genome-wide association studies, disease correlations and risk factors, drug-drug interactions, and to improve health services. However, mining EHR data is a challenge with many issues and barriers. The aim of this chapter is to discuss how data and text mining techniques may guide and support the building of improved clinical decision support systems.
Chapter Preview
Top

Background

In a recent perspective article published in the New England Journal of Medicine (Gandhi, Zuccotti, & Lee, 2011), the authors summarized an analysis of outpatient records for 1.7 million patients in an integrated healthcare system in the USA. The analysis highlighted that 71% of the patients who had undergone splenectomy did not have it medically coded under the ‘problems list’ in their EHR. As a result of this missing information, only a third of the patients whose records did not mention splenectomy were given pneumococcal vaccination. More interestingly, the authors reported that an alert-and-reminders-based clinical decision support system was already in place and was not of much assistance. In this example, text mining could be employed to medically code splenectomy under the ‘problems list’ in an EHR. Furthermore, data mining techniques like predictive models can be built to predict other associated problems related to splenectomy.

Complete Chapter List

Search this Book:
Reset