Becker's Clinical Quality & Infection Control

CLIC_May_June_2024

Issue link: https://beckershealthcare.uberflip.com/i/1521985

Contents of this Issue

Navigation

Page 15 of 23

16 QUALITY IMPROVEMENT & MEASUREMENT To predict pressure injuries, new tool 20% better than current 'coin flip' By Paige Twenter A machine learning model accurately predicted the risk of about 3 in 4 hospital-acquired pressure injuries, according to a new study. Every year, about 2.5 million people develop a pressure injury, and 60,000 die from them in the U.S., according to past research. is condition annually costs health systems more than $26 billion, but if a 500-bed hospital used this predictive AI model, $18 million could be saved, according to the study. Multiple machine learning methods were tested among about 35,000 EHRs spanning two academic hospitals over five years. e EHRs encompassed hospitalized patients at risk for pressure injury. "Pressure injury prevention is a costly protocol to implement on a daily basis, and the existing tool for predicting pressure injuries is barely better than a coin flip," the study's lead author, William Padula, PhD, said in a news release. "We thought, there's got to be a better way of doing this. e question became, 'Could a computer do these risk assessments better than the nurses themselves at the bedside?'" e model increased the prediction accuracy to nearly 75% — or a 20% improvement compared to current methods, including the Braden Scale. e researchers hailed from the University of Southern California in Los Angeles, Johns Hopkins University in Baltimore and University Hospitals Cleveland Medical Center. Findings were published April 9 in BMJ Open. n Only 68% of patients feel 'very safe' in hospitals: Report By Mackenzie Bean Patients' perception of hospital safety has worsened since the pandemic, according to an April 2 Press Ganey report. For the report, Press Ganey analyzed data on 12.5 million patient encounters, 1 million health system employees and more than 550,000 safety events reported in 2023. Patient experience data covers more than 500 healthcare organizations. Patients' perceptions of safety were lower in hospital settings compared to the outpatient environment. In 2023, only 68.5% of hospital patients reported feeling "very safe," down from 73.6% in 2019. Meanwhile, outpatients' perceptions of safety have increased since the pandemic, jumping from 78.1% in 2019 to 81.9% in 2023. The gap in safety perception between inpatient and outpatient settings is now 2.5 times wider than in 2019, according to Press Ganey. Hospital patients reporting negative safety experiences most often described concerns related to staff members' skills or knowledge. n NQF to update 'never event' reporting By Mackenzie Bean T he National Quality Forum is aiming to modernize and standardize serious adverse event reporting via a new patient safety effort. Through the "Focus on HARM" initiative, NQF will update the criteria for what constitutes a serious reportable event, or "never event," to better reflect today's diverse range of care settings. The organization, an affiliate of The Joint Commission, will also work to align reporting standards nationwide. NQF first created its serious reportable event list in 2002, which national and state-based reporting systems use to increase accountability and improve safety. At present, 28 states and Washington, D.C., rely on the resource for accountability reporting. "The lack of reliable, consistent, objective data standards related to measuring patient safety events limits our ability to quantify the magnitude of the problem and track our progress as we mitigate avoidable patient harm," NQF President and CEO Dana Gelb Safran said in an April 4 news release. "This work represents a critical and overdue step needed to enable systematic measurement, tracking, and improvement as we continue national efforts to make healthcare safe for every patient, every time, in every setting." n

Articles in this issue

view archives of Becker's Clinical Quality & Infection Control - CLIC_May_June_2024