According to the U.S. Agency for Healthcare Research in Quality, bedsores (pressure injuries) are the fastest-rising hospital-acquired condition. This is why they have become the second most common reason for medical malpractice suits in the US.
Even though most hospital-acquired pressure injuries are reasonably preventable, about 2.5 million individuals in the US develop a pressure injury in acute care facilities every year, and 60,000 die. And the total annual cost for U.S. health systems to manage the acute needs of patients’ pressure injuries during hospitalization surpasses $26 billion. However, pressure injuries have received little attention as a public health crisis.
Researchers at USC, Johns Hopkins University, and University Hospitals Cleveland Medical Center partnered to utilize machine learning (ML) techniques to develop a new model to predict future risk of pressure injuries and better direct labor-intensive patient care.
Published in BMJ Open, the new risk-assessment model increases prediction accuracy to over 74%—a 20% increase over existing methods. Standard practices and guidelines to prevent pressure injuries are time-consuming and taxing on nurses at the bedside.
The researchers note that predictive analytics can alleviate some burden on nurses and frontline healthcare providers by automating part of the risk-assessment process. Now, acute care providers must perform a skin check and risk assessment for pressure injury upon admission and every 12 to 24 hours after that, using a standardized instrument such as the Braden Scale, which primarily assesses mobility, cognition, nutrition, and incontinence management.
The predictive algorithm developed by the team provides improved economic efficiency and substantial savings. And since a risk assessment can take anywhere from 5 to 15 minutes per patient, this could represent up to 250 labor hours in a single 500-bed facility per day and between 30,000 and 90,000 labor hours per year. And the research also fosters improvements in health equity. The existing tools don’t account for race, skin color or age.
AI Methods
With machine-learning methods, researchers mined the electronic health records of over 35,000 hospitalizations over five years at two academic hospitals to analyze changes in pressure injury risk over time. And they looked at variables including admission diagnostic codes, prescription drugs, lab orders and other factors most closely associated with pressure injury risk factors.
The investigators ran analytics using ML techniques such as random forests and neural networks to further boil down the specific weights of those variables on the changes and risk of a pressure injury case and came up with the final model. And they also identified a list of prescription drugs—beta blockers, electrolytes, phosphate replacement, zinc replacement, erythropoietin stimulating agents, thiazide/diuretics, vasopressors—that change patients’ risk for pressure injury.
This work was supported by a National Institutes of Health (NIH) grant (KL2 TR001854, PI: Padula).
KEY QUOTES:
“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. We thought, there’s got to be a better way of doing this. The question became, could a computer do these risk assessments better than the nurses themselves at the bedside?”
“If you can’t see bruising on a patient’s skin because they’re Black, Hispanic or Asian, then you’re not going to identify the greater risk factors they face as quickly. Machine-learning methods are not biased by what we see in the sun’s light. This allows us to improve equity of the delivery of healthcare when it comes to the prevention of these conditions that disparately affect underrepresented minorities.”
- William Padula, assistant professor of pharmaceutical and health economics at USC Mann and a fellow at the USC Leonard D. Schaeffer Center for Health Policy & Economics
“This data could help hospitals conserve resources within a critical period of patient vulnerability of hospital-acquired pressure injury that is not reimbursed by U.S. Medicare.”
- Peter Pronovost, chief quality and transformation officer at University Hospitals Cleveland Medical Center, formerly director of the Armstrong Institute for Patient Safety at Johns Hopkins Hospital
“AI-based early detection significantly outperforms standard of care. Hospitals can use this to initiate a quality-improvement program for pressure-injury prevention that improves outcomes and significantly lowers the burden on nursing from current monitoring approaches. Further, they can customize the algorithm to patient-specific variation by facility.”
- Suchi Saria, John C. Malone endowed chair and AI professor at Johns Hopkins and CEO of Bayesian Health, a clinical AI platform company
“This is, to our knowledge, the most advanced methodological study to our knowledge to use artificial intelligence to help better detect pressure injuries.”
- David Armstrong, professor of surgery at Keck School of Medicine of USC
