Hospital Corporation of America is wrapping up the first phase of an initiative to use real-time and near real-time analytics to better understand its clinical data. Organization representatives laid out early challenges and lessons during Health Data Management’s Healthcare Analytics Symposium in Chicago.

The project over time will become massive as HCA generates about 18 million annual encounters across its 164 hospitals and hundreds of ambulatory sites. The focus is on improving care while a patient is still in the hospital by giving physicians patient status data that is no more than four hours old and in real-time when available.

HCA only had nine percent of its enterprise data clinically valid when the initiative started and scalability to meet physician needs has been a major challenge, said Victoria Weaver, assistant vice president of clinical data management. The organization also is paying the price for local autonomy of its hospitals as it seeks to standardize basic terms and processes. The standardization struggle, she noted, “cannot be underestimated in any way, shape or form.”

The unknown has been another challenge; it’s tough to build contingencies when an organization has no real experience manipulating and analyzing clinical data, Weaver said. The first phase went over budget and extended four to five months longer than what was expected, necessitating a meeting with senior officers to explain corrective processes.

Analyses in the first phase focused on operating room turnaround times, and making sure certain lab tests--A1C, HIV, lipid panels, TSH & BNP--aren’t being over utilized. One of the goals, said Anna Daly, director of clinical data management, is to reduce clinical practice variations based on geography as HCA operates in 20 states and England.

To help analyze OR turnaround studies, some college graduates working with HCA went to the Federal Aviation Administration and got information that enables comparison of flight patterns with schedules. They then used the information to make models that assess turnaround factors starting from when a patient is wheeled into OR until wheeled out.

Today, about 75 employees work in the data management/analytics initiative, not counting those in other supportive programs. The next step, Daly said, is to begin working with predictive measures starting with sepsis.

This article originally appreared at Health Data Management.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access