Health IT Aspires to Reduce Readmissions

Efforts to keep recently discharged patients from returning for another hospital stay could mean better health for patients and save hospitals millions of dollars. Hospital readmission is a nationwide problem, as 1 out of every 5 Medicare patients returns to the hospital within 30 days. With the passage of the health care reform bill, hospitals with excessive readmission rates will soon be subject to severe financial penalties.

A project from researchers at the NC Translational and Clinical Sciences (NC TraCS) Institute could help keep those rates in check, by giving primary care doctors the information they need to effectively care for their patients once they go home. The venture makes discharge summaries available electronically and uses health informatics to mine the summaries for important information regarding follow-up.

“Let’s imagine someone gets admitted to the hospital with a really bad urinary tract infection,” explains Carlton Moore, M.D., a clinical associate professor of medicine at UNC-Chapel Hill who is helping to lead the project. “That patient would get a chest X-ray as part of their admission, and if the X-ray were to show an abnormality, the hospital physician would typically not make them stick around to get it worked up, but would allow the result to be followed as an outpatient.”

“The way the current health care system is structured, the burden lies with the patients or physicians to remember to follow up. Unfortunately, human beings are fallible and things can fall through the cracks,” continued Moore. “Now the trend is toward developing systems that absorb human fallibility so that when doctors or patients forget to follow up there is something built into the system that alerts them to follow up on an abnormal test result or doctor’s appointment.”

With a $500,000 informatics grant from the Duke Endowment, Moore and Don Spencer, M.D., vice president of ambulatory care for the UNC Health Care System, led a team that transferred complete discharge information for UNC patients to Community Care of North Carolina. Moore says UNC is the first hospital in the state to put this information into CCNC’s provider portal, an electronic system that helps case managers ensure that patients are taking their medications and following up with primary care doctors after their hospitalizations.

“The bottom line is the case managers to date have not had access to the discharge summaries to know how to best take care of their patients,” said Brent Lamm, director of information technology at NC TraCS. “Even then, these discharge summaries can be pages long, making it challenging for the case workers to read in their entirety and then glean what is relevant. So we are using informatics technology to distill down a complex discharge summary into actionable information the case managers can efficiently use in their work.”

The researchers are employing an informatics technique known as natural language processing to analyze the discharge summaries, pull out relevant textual information and flag abnormal findings for follow-up. Armed with a NC TraC$50K pilot award, Moore and his colleagues will use their approach to identify abnormal results from a test set of CAT scans, mammography and Pap smears before expanding to other types of visual data.

“I am looking at it more from a quality of care perspective, just to make sure that these abnormal results actually get followed up on,” said Moore. “The vast majority of the time these masses are benign, but every once in a while they are malignant and warrant surgery or chemotherapy. We don’t want to miss those.”

  • Created on .

View news related to policies and regulations

Have news or an announcement to share? Contact Michelle Maclay at michelle_maclay@med.unc.edu

Get NC TraCS events and news delivered to your inbox! Subscribe to our weekly email blast

NC TraCS Institute logo vertical

In partnership with:

Contact Us


Brinkhous-Bullitt, 2nd floor
160 N. Medical Drive
Chapel Hill, NC 27599

919.966.6022
This email address is being protected from spambots. You need JavaScript enabled to view it.

Social


Cite Us


CitE and SUBMit CTSA Grant number - UM1TR004406

© 2008-2024 The North Carolina Translational and Clinical Sciences (NC TraCS) Institute at The University of North Carolina at Chapel Hill
The content of this website is solely the responsibility of the University of North Carolina at Chapel Hill and does not necessarily represent the official views of the NIH   accessibility | contact