New decision support tool improves discharge outcomes

November 08, 2018

PHILADELPHIA (November 8, 2018) - In an effort to lessen readmission risk after discharge and achieve the best possible outcomes for patients, hospital-based clinicians are more intentionally planning discharge of those who require post-acute care (PAC). Yet, although hospital clinicians strive to effectively refer patients who require PAC, their discharge-planning processes often vary greatly and typically are not evidence-based.

To optimize PAC decision-making, a team led by the University of Pennsylvania School of Nursing (Penn Nursing) developed, validated, and tested a two-step clinical decision support (CDS) algorithm called Discharge Referral Expert System for Care Transitions (DIRECT). The DIRECT CDS helps clinicians identify patients most in need of PAC and suggests whether skilled home care or facility level care is best. An article in the Journal of the American Medical Directors Association (JAMDA) explains how the DIRECT CDS was evaluated in two hospitals and its promising effects on PAC referrals and improved patient outcomes.

The researchers developed the DIRECT CDS using values of structured patient data drawn from the electronic health record and knowledge elicitation from clinical experts as they reviewed de-identified case studies of actual patients. The team then conducted a four-month control phase of study without CDS with more than 3,000 patients aged 55 and older who were admitted and discharged alive, followed by a six-month intervention phase of study when clinicians received the DIRECT CDS advice for more than 5,000 patients. They compared readmission rates between the two phases after controlling for differences in patient characteristics.

"While the proportion of patients referred to PAC between the two phases did not change significantly, the algorithm may have identified those patients most in need, resulting in significantly lower inpatient readmission rates for same day, 7-, 14- and 30-day intervals," explained Kathryn H. Bowles, PhD, RN, FAAN, FACMI, Professor of Nursing, the van Ameringen Chair in Nursing Excellence, and a member of the NewCourtland Center for Transitions and Health. Bowles is the Principal Investigator and lead author of the JAMDA article "A Decision Support Algorithm for Referrals to Post-Acute Care."

"Health care providers are increasingly pressured by policies and initiatives to decrease health care utilization and contain costs. Policy requirements and bundled payment programs seeking the least costly site of care may limit options and result in patients not getting the optimal level of PAC needed to prevent poor discharge outcomes," said Bowles. "We developed DIRECT to improve the patient-centered discharge process using an evidence-based, objective tool."

During the test of the DIRECT CDS algorithm, it proved valuable in providing advice on whom to refer and the level of care. It also showed case managers the important patient characteristics that led to that advice such as fall risk, unmet caregiver needs, who declined in activities of daily living function and in which activity.

"The DIRECT CDS indicates potential as a useful tool to optimize PAC decision-making and improve patient outcomes. It may also identify patients who need PAC but are unable to receive it because of policy or insurance barriers. Future studies examining the outcomes of these patients may have policy implications," said Bowles.
-end-
Co-authors of the article include Sue Keim, PhD, Sheryl Potashnik, PhD, Emilia Flores, PhD, Christina R. Whitehouse, PhD, and Mary D. Naylor, PhD, all of Penn Nursing; Sarah J. Ratcliffe, PhD and John H. Holmes, PhD, both of the University of Pennsylvania Perelman School of Medicine; and Diane Humbrecht, DNP, of Abington Memorial Hospital. Funding for this research was provided by the National Institute of Nursing Research (R01NR007674).

About the University of Pennsylvania School of Nursing

The University of Pennsylvania School of Nursing is one of the world's leading schools of nursing. For the second year in a row, it is ranked the #1 nursing school in the world by QS University, and has four graduate programs ranked number one by U.S. News & World Report, the most of any school in the United States. Penn Nursing is currently ranked # 1 in funding from the National Institutes of Health, among other schools of nursing. Penn Nursing prepares nurse scientists and nurse leaders to meet the health needs of a global society through research, education, and practice. Follow Penn Nursing on: Facebook, Twitter, LinkedIn, Instagram & YouTube.

University of Pennsylvania School of Nursing

Related Algorithm Articles from Brightsurf:

CCNY & partners in quantum algorithm breakthrough
Researchers led by City College of New York physicist Pouyan Ghaemi report the development of a quantum algorithm with the potential to study a class of many-electron quantums system using quantum computers.

Machine learning algorithm could provide Soldiers feedback
A new machine learning algorithm, developed with Army funding, can isolate patterns in brain signals that relate to a specific behavior and then decode it, potentially providing Soldiers with behavioral-based feedback.

New algorithm predicts likelihood of acute kidney injury
In a recent study, a new algorithm outperformed the standard method for predicting which hospitalized patients will develop acute kidney injury.

New algorithm could unleash the power of quantum computers
A new algorithm that fast forwards simulations could bring greater use ability to current and near-term quantum computers, opening the way for applications to run past strict time limits that hamper many quantum calculations.

QUT algorithm could quash Twitter abuse of women
Online abuse targeting women, including threats of harm or sexual violence, has proliferated across all social media platforms but QUT researchers have developed a sophisticated statistical model to identify misogynistic content and help drum it out of the Twittersphere.

New learning algorithm should significantly expand the possible applications of AI
The e-prop learning method developed at Graz University of Technology forms the basis for drastically more energy-efficient hardware implementations of Artificial Intelligence.

Algorithm predicts risk for PTSD after traumatic injury
With high precision, a new algorithm predicts which patients treated for traumatic injuries in the emergency department will later develop posttraumatic stress disorder.

New algorithm uses artificial intelligence to help manage type 1 diabetes
Researchers and physicians at Oregon Health & Science University have designed a method to help people with type 1 diabetes better manage their glucose levels.

A new algorithm predicts the difficulty in fighting fire
The tool completes previous studies with new variables and could improve the ability to respond to forest fires.

New algorithm predicts optimal materials among all possible compounds
Skoltech researchers have offered a solution to the problem of searching for materials with required properties among all possible combinations of chemical elements.

Read More: Algorithm News and Algorithm Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.