Presentation on theme: "Big Data Panel Good news: We dug to the bottom of the pile and found a pony!!! Kathryn H. Bowles, PhD, FAAN, FACMI vanAmeringen Professor in Nursing Excellence;"— Presentation transcript:
Big Data Panel Good news: We dug to the bottom of the pile and found a pony!!! Kathryn H. Bowles, PhD, FAAN, FACMI vanAmeringen Professor in Nursing Excellence; Director of the Center for Integrative Science in Aging, University of Pennsylvania School of Nursing Vice President of Research and Director of the Visiting Nurse Service of New York Research Center.
Acknowledgments Co-Investigators: John Holmes, Sarah Ratcliffe, Mary Naylor Funder: The project was supported by the National Institute of Nursing Research (award 2R01NR007674). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute of Nursing Research or the National Institutes of Health. The authors declare no conflicts of interest
Background and study aims Six hospitals all with an EHR from the same vendor Chose this particular EHR because of standardized assessments and evidence based tools Obtained data from the nursing admission assessment and documentation near discharge Data was used to build case studies of hospitalized patients, used to elicit discharge referral decisions
Standardized assessments Different versions had different data elements Ignorance about the validity of EB tools Variation in what was mandatory to document
Getting the data out Each site had varying skill in their ability to extract data from the EHR Sites had changed table and field names so queries written at one site could not be used at the others Data elements with one to many relationships were especially challenging (wounds)
Customization Adding detailed data elements (home care versus “St. Mary’s home care”) Removing data elements Allowing free text (wheelchair, Wheellchair, Wheelchair) Burying important elements (ADL assessment) Avoiding upgrades to avoid overwriting
Documentation Policies Charting by exception Reversing the meaning of the question! Reversing the meaning of the question! Oriented to? Disoriented to? What is required and what is optional? Timing of assessments (daily, adm/dc, once/shift?)
Interface Design Clarity of the documentation (understanding the questions) Fit within the workflow Notification about incomplete data Being able to navigate easily How to answer when the patient can’t
Advice and solutions Create a spreadsheet of all data elements of interest to understand: what is collected what is collected when is it collected when is it collected by whom by whom for what purpose for what purpose where is it stored where is it stored how to extract it how to extract it
Advice and solutions Educate clinicians and students about Big Data Data now used for broader purposes Data now used for broader purposes The consequences of missing data The consequences of missing data The consequences of customization The consequences of customization The pitfalls of using EHR data for research The pitfalls of using EHR data for research Skills in merging, cleaning, and assessing the quality of data Skills in merging, cleaning, and assessing the quality of data
Advice and solutions Avoid customization Participate and set policies in a wider user’s group Critically review your systems for workflow issues that may impact data collection Keep your system versions up to date
Advice and solutions Assure that nurse collected data is included in data warehousing efforts Seek standardized nursing languages and mapping to SNOMED for documentation systems Appoint nurses to IT committees to assure representation
Suggested reading Conducting Research Using the Electronic Health Record Across Multi-Hospital Systems Semantic Harmonization Implications for Administrators Bowles, KH, Potashnik, S, Ratcliffe, SJ, Rosenberg, M, Shih, N-W, Topaz, M, Holmes, J, Naylor, M Journal of Nursing Administration (2013) 43(6), 355-360.