Implementation of a learning healthcare system for Sickle Cell disease: List of smart data elements contained in the Epic Smartform and their SmartData types

Objective: Using Sickle Cell Disease (SCD) as a model, the objective of this study was to create a comprehensive learning healthcare system to support disease management and research. A multidisciplinary team developed a SCD clinical data dictionary to standardize bedside data entry and inform a scalable environment capable of converting complex electronic healthcare records (EHR) into knowledge accessible in real-time.

Materials and Methods: Clinicians expert in SCD care developed a data dictionary to describe important SCD associated health maintenance and adverse events. The SCD data dictionary was deployed in the EHR using Epic SmartForms, an efficient bedside data entry tool. Additional data elements were extracted from the EHR database (Clarity) using Pentaho Data Integration (PDI) and stored in a data analytics database (SQL). A custom application, the Sickle Cell Knowledgebase, was developed to improve data analysis and visualization. Utilization, accuracy and completeness of data entry were assessed.

Results: The SCD Knowledgebase facilitates generation of patient-level and aggregate data visualization, driving the translation of data into knowledge that can impact care. A single patient can be selected to monitor health maintenance, comorbidities, adverse event frequency and severity, and medication dosing/adherence.

Discussion: Disease-specific data dictionaries used at the bedside will ultimately increase the meaningful use of EHR datasets to drive consistent clinical data entry, improve data accuracy and support analytics that will facilitate quality improvement and research

Methods
The data were collected via Smartforms in Epic. The data were processed using standard extraction, load, and transfer processes as outlined in the manuscript.
Customizable EHR-based SmartForms (ESFs, structured data capture) provide the utility for capturing granular data at the bedside that could then be mapped with high quality to a data dictionary.