It’s well known that sepsis is among the most vexing and persistent conditions, costing the system as whole upwards of $20 billion – the single most expensive condition in hospitals– and causing an estimated 750,000 annual deaths just in the U.S.
As a means of combating the condition, research giant Wolters Kluwer Health has launched new software, called POC Advisor, that it says can significantly mitigate the condition for hospitals, leading to better screening that can dramatically improve outcomes. It does so by harnessing real-time data contained within the EHR, then automated surveillance, specifically mining patient history, lab results, vital signs nursing notes and other data that live in the EHR.
Currently, the software is in beta mode at Huntsville Hospital in Alabama and John Muir Medical Center in California.
Health Executives on Digital Transformation in Healthcare
Hear executives from Quantum Health, Surescripts, EY, Clinical Architecture and Personify Health share their views on digital transformation in healthcare.
“Clinical staff is alerted to potentially septic patients, who are then evaluated and the best course of treatment determined based on best clinical judgment,” said Dr. Stephen Claypool, vice president of clinical development and infromatics at Wolters Kluwer Health, based in Philadelphia.
Importantly, Dr. Claypool said the notifications won’t add to another major issue for hospitals – alarm fatigue – because it factors in a patient’s specific needs.
“The alerts are highly sensitive and specific,” he said. “Our goal is to make sure alerts are only triggered when a clinician needs to know something that they do not know already, and to make sure we aren’t sending unnecessary alerts. That has been a main area of focus from the start and we have so far managed to achieve greater than 95 percent specificity and sensitivity.
Basically, we run completely different rules for patients with liver disease versus patients with end-stage renal disease,” he added. “We run different rules for patients with alcohol withdrawal. The key is to build a very accurate system so clinicians only get alerts that are helpful.”
Reducing Clinical and Staff Burnout with AI Automation
As technology advances, AI-powered tools will increasingly reduce the administrative burdens on healthcare providers.
In a pilot, one hospital reported that, within the first 30 days of using the software, 70 sepsis patients were identified, according to Wolters Kluwer. That led to compliance with patient screening to reach 89 percent, while ordering the appropriate tests hit 90 percent.
Early detection of sepsis is critical in determining a patient’s survival rate, with the chances worsening by the hour. As such, software that can assist in identifying potential cases could be a huge help for hospitals as they look to improve outcomes, which in turn would cut down on costs.
“We’re studying the financial impact of the program now. We’re hopeful that, through early detection and treatment, we can reduce the length of hospital stay and the length of ICU stay,” Dr. Claypool said.
Of course, it takes more than just software to counter the condition.
“It also requires integration of several key elements,” Dr. Claypool said. “These include clinical change management to develop best practices, including provider education and screening tools and protocols for early sepsis detection. It also requires data analytics to manage protocol compliance, report real-time data to support system-wide best practices and support performance improvement and public reporting requirements.”
The financial incentive, along with the desire for improved outcomes, is likely to accelerate in the immediate future. The National Quality Forum has endorsed sepsis as a national practice benchmark, which led CMS to include a chart-abstracted sepsis measure in the inpatient prospective payment system final rule for fiscal year 2015. The Forum has also adopted a sepsis measure that hospitals can report for meaningful use, so it’s not a stretch to say that there will be some sepsis-related formula included in future incentive programs.
The software is likely to improve the coding of sepsis, meaning hospitals will be in a better position to capture reimbursement revenues, Dr. Claypool said.
“Coders typically only code for sepsis if it’s documented in physician progress notes. Data suggests that coders do a good job of submitting correct ICD-9 codes when sepsis is documented,” he said. “Most sepsis is not reported. For a hospital, it could mean money left on the table because they are not being appropriately reimbursed.”
While the focus is on sepsis now, future applications of the software are both broad and likely. Possible condition include pneumonia, heart failure, diabetes, CLABSI and CAUTI.