I recently heard an expert/veteran/warrior of rapid-cycle Plan-Do-Study-Act (PDSA) performance improvement speak. Her enthusiasm for the important work of iterative improvement of health care through small-scale projects was palpable. Data was the one concept that surfaced most frequently in her presentation.
As someone who started my PDSA work using golf pencils and tic marks, struggles with data were common and wrought with frustration. Regardless of whether I was using paper or digital systems, the information was not only hard to read, it was difficult to trust.
Performance improvement professionals continue to need good data to study how well they executed their plan.
Health care analytics platforms help with messy and untrustworthy data. When data from electronic health records is aggregated, appropriately mapped, normalized and validated, health care organizations can carry out their rapid-cycle performance improvement projects with confidence — regardless of the project’s scale.
For example, if users are to know the status of patients with congestive heart failure (CHF), health care analytics platforms must be able to find “ejection fraction” documentation in electronic medical records. Typically, “ejection fraction” is found in transcribed cardiology or other notes. If that data is not digitized, then a performance improvement project may be missing a sizable portion of the CHF population it needs to apply their improvement plan.
The trick is to use an analytics platform with data mapping technologies that will find structured and unstructured data. A platform that deploys natural language processing (NLP) helps process unstructured data and allows users to have a much more comprehensive data set. In cases of CHF, that means more ejection fraction values, which can then be used for PDSA projects.
Improvement is truly data-driven when the data is trusted. To be trusted, the data must be cleaned and comprehensively prepared to allow more accurate study of improvement plans. Health care improvers can then take more confident actions!
Explore more by downloading the population analytics topic spotlight “Manage Patient Populations with Data and Analytics”
About the author
Carl Johnson, MD, EdM, MSc. is a pediatrician trained at Boston Children’s Hospital. He completed a Medical Education fellowship at Harvard Medical School and was a faculty health services researcher at The Mount Sinai School of Medicine.
Before joining Optum Analytics, he worked as a physician executive at Cerner Corporation. He is a graduate of the Mount Sinai School of Medicine in New York City and has held faculty positions at Harvard Medical School, University of California at San Francisco, The Ohio State University and The Mount Sinai School of Medicine.
Dr. Johnson believes that health care can be transformed with the help of the right data. When he is not helping to transform health care, he can be found playing tennis, cooking, perfecting his French, taking photographs, reading historical fiction, listening to music and watching Ohio State Football.