Parkland RITE program targets prevention of hospital infections and improved sepsis care

Hospital-wide effort reduces infection rates, saves lives

DALLAS —Each year sepsis strikes approximately 1.7 million people in the U.S. and more than a quarter million die from the condition, making it a major cause of death. Healthcare-associated infections (HAI) contribute to about 25 percent of these deaths. According to infection prevention experts, many hospitals are trying different approaches to reduce healthcare-associated infections, improve care of patients presenting with sepsis, and save lives. In 2013, Parkland Health & Hospital System launched an innovative hospital-wide program to reduce HAI and sepsis-related deaths, called RITE (Reduce Infections Together in Everyone).

In the first five years, the multi-disciplinary program has achieved impressive results, reducing rates of infection each year since the program was launched. The net estimated impact of the RITE program is more than a thousand infections prevented and approximately $17,781,000 in cost avoidance.

“Providing quality care begins with providing safe care,” said Parkland’s Chief of Infection Prevention, Pranavi Sreeramoju, MD. “We targeted catheter-associated urinary tract infections and central line-associated blood stream infections hospital-wide, surgical site infections following eighteen different types of surgical procedures, and patients presenting with signs and symptoms of sepsis to our emergency department.”

Parkland’s prevention approach centered on standardizing care of patients at risk for these complications; engaging healthcare personnel by talking to them and exploring barriers to adoption of best practice; standardizing curriculum on how to prevent HAI and improve sepsis care; use of medical informatics tools such as early warning system for sepsis developed by Parkland Center for Clinical Innovation; use of best practice alerts and order sets in the electronic medical records; and improving workflows.

According to Dr. Sreeramoju who is also Associate Professor of Internal Medicine at UT Southwestern Medical Center, Parkland’s RITE initiative forged a new approach to prevention by leaning on one part medical science and two parts social science.

“It’s been said about infection prevention that we know what to do – that’s the medical science. The biggest challenge for hospitals remains getting everyone to do the right thing, all the time,” she said. “Something as basic as hand hygiene requires constant vigilance in a hospital setting. So we decided to focus on identifying the most effective ways to influence behavior and make best practices easier to adhere to.

“We took a ‘high touch’ approach to working with staff, spending time analyzing interactions among multi-disciplinary caregivers, and we gave front-line staff the opportunity to provide input that could help us improve our infection prevention strategies,” Dr. Sreeramoju explained.

The scope of the RITE initiative is massive. Parkland Memorial Hospital has more than 40,000 inpatient discharges and 244,000 emergency department visits annually. Approximately 2,500 patients present to Parkland’s ED with suspected sepsis each year.

During Sepsis Awareness Month in September, organizations like the Sepsis Alliance, one of the nation’s leading sepsis patient advocacy groups, hope to increase public and healthcare professionals’ knowledge about this dangerous and vexing health risk. In a 2016 report, the Sepsis Alliance stated that “even though hospitalizations are increasing, a majority of Americans still don’t know what sepsis is or how to treat it.” The most recent Sepsis Alliance Awareness Survey found that less than one-half of all adult Americans have ever heard of sepsis. And the number is even lower among younger adults.

To learn more about services at Parkland hospital, visit www.parklandhospital.com

Contact

Parkland Health & Hospital System
Catherine Bradley
469-419-4400 catherine.bradley@phhs.org

PCCI
Mike Crouch
214-590-3887 Michael.Crouch@PCCInnovation.org

Prevention of Sepsis Through Machine Learning

Sepsis is a word that can evoke feelings of dread for most people and yet, many fail to understand its meaning and implications fully. It is a life-threatening condition that arises when the body’s response to infection results in organ dysfunction or failure. It is one of the leading causes of deaths with 6 to 9 million deaths per year worldwide and 250,000 deaths per year in the United States. To make matters worse, sepsis is also one of the leading causes of preventable deaths worldwide. The key to prevention is early detection since every hour of delay increases the odds of death by 20%. However, sepsis can be very hard to detect especially in its early stages when it is reversible. The symptoms often point to other conditions and patients can deteriorate rapidly. Traditional risk models such as SIRS criteria to detect sepsis generate a lot of false positives leading to inefficient or ineffective care and nursing fatigue.

sepsis

Leveraging Machine Learning 

Due to PCCI’s close collaboration with Parkland Health & Hospital System, we recognized sepsis detection and prevention as an area that could benefit from an advanced machine learning-based algorithm. To be effective, the model needed to fulfill the following criteria:

  • A high enough positive predictive value (PPV) to ensure that false positives do not end up causing frustration for clinicians. It is very challenging to have a high PPV for use cases with low prevalence rates in the target population. Despite the high mortality numbers, the overall prevalence rate for sepsis in an inpatient setting (our target population) is 3% to 4%.
  • A prediction interval (how far ahead in the future can the model predict) that gives clinicians a sufficient heads-up to intervene.

PCCI developed a predictive model to fulfill the criteria identified as effective. This real-time model is designed to predict an individual’s risk of becoming septic within the next 12 hours.

Instead of relying on traditional ways of detecting the risk of sepsis through a handful of physiologic variables, we cast our net wide and started out with approximately 120 variables as potential predictors, such as socio-demographic, vital signs, co-morbidities, hospital utilization, medical conditions, clinical history, and lab results.

Testing the Lasso Logistic Regression Model

We trained and tested a Lasso Logistic Regression model, a decision tree and a neural net on 27 months-worth of Inpatient encounters from Parkland. Initial data sets included 54,629 encounters and 30,922 patients. We chose the Lasso Logistic Regression model as the final model because of its high performance and interpretability by clinical users. The resulting model that compared favorably to other community models resulted in:

  • 95% Accuracy
  • 30% PPV
  • 55% Sensitivity

Incorporating the Model into Clinical Workflows

A model is useful only if it is actionable and available at point of care. PCCI’s Sepsis model is incorporated into clinical workflows through industry-standard APIs. The model accesses EHR data in real-time every five minutes and alerts the clinician if the risk is above a certain threshold. The risk threshold can be tailored to local populations and clinical best practices of an organization. The alerting mechanism can vary based on EHR functionality, but it can include a simple alert, queuing up of order sets based on the risk threshold, and sending a real-time alert to a secure mobile device or pager for a member of the rapid response team.

Learn more about PCCI’s work, or stay up-to-date with our recent news by following us on FacebookTwitter and LinkedIn!