As resident falls are still a primary source of financial loss for long-term care providers, researchers and tech companies are continuing to develop and improve on tools that predict the risk of falls.
The latest offering in clinical tools that predict falls is a risk prediction model aiming to identify residents of nursing homes at greatest risk for fall-related injuries.
According to a study published in the Journal of the American Geriatrics Society, researchers found that within two years of follow-up, 6.0 percent of residents experienced one or more fall-related injuries.
Researchers developed and tested a series of risk prediction models for nursing home residents. These models can be used to estimate the 6-month and 2-year risk of fall-related injuries among nursing home residents.
“The full models can be automatically calculated with existing clinical data, while the short tool could be used by clinicians with similar performance,” the authors of the study wrote. “We believe these models will provide researchers, clinicians, and policymakers with a useful tool to improve the quality of care in nursing homes.”
The study models use clinical assessment data from the Minimum Data Set (MDS) and Medicare claims, researchers said, while a quick-use tool “performed similarly” using 70 variables to predict a fall.
Hospitalization history, activities of daily living, a history of hip fracture and non-hip fracture were included as predictors.
Fifty-one of the 70 variables remained significant predictors of a fall-related injury in the 2-year model, while 41 of the 51 predictors remained significant in the 6-month model. The study followed a group of 733,427 long-term care residents.
Resident falls have cost the long-term care industry on average $251,067 in claims over the last 10 years, according to a general and professional liability report prepared by Oliver Wyman and Marsh, businesses of Marsh McLennan.
Marsh McLennan is a global professional services firm in risk, strategy and people.
Researchers said it’s likely that fall-related injuries will be included in capturing a measurement of the resident experience as part of the Value-Based Purchasing Program, and an automated version of the study’s model would be helpful.
A previous model, called FRAiL, was used to estimate hip fracture risk among residents. The predictions worked well among women in the original sample, but didn’t do as well with predicting non-vertebral fractures. Hip fractures make up less than half of all fall-related injuries, researchers said, leading to the need for a wider ranging model.
Researchers suggested the models could be incorporated by emergency medical record (EMR) vendors or individual facilities. The Centers for Medicare & Medicaid Services (CMS) could also modify Resident Assessment Instruments (RAI) to allow for an automated calculation of fall risk within the MDS.
“Once automated, these models could be used by facility administrators, regulatory entities, and researchers to compare predicted and observed FRI rates,” researchers said. “Aggregated facility data has the additional benefit of being able to identify high-performing facilities, which can be studied to gain insights into best practices.”