Cognitive Impact

Where Other Solutions Fall Short: Jvion’s Cognitive Machine Better Prevents Inpatient Falls

Inpatient falls are a problem that extends beyond just the elderly to any patient who has experienced some kind of physiological change as a result of his or her medical condition, medications, procedures, and/or testing.1 Oftentimes, preventing a fall is difficult and the challenge is complicated by variations in fall prevalence across different types of nursing units.2 What is consistent is the devastating impact that a fall can have on a patient, his or her family, and the overall healthcare system.
inpatient falls
For patients, falls are the leading cause of a move to a skilled-nursing facility, result in severe injury in 20-30% of all cases, and can result in a 10-15% reduction in life expectancy. For families, falls not only increase caregiving burdens, they also have a significant financial impact.3 And for the healthcare system as a whole, falls contribute to an average increase of 6.3 days in the hospital, add up to an additional $14,000 on average per episode, and cost Americans more than $100 billion per year.3,1
Current methods for predicting falls use scaled scores (i.e. Morse Falls Scales, Hector Davis Scale). The problem with these tools is that they tend to overestimate fall risk. They typically deliver high rates of false positives, which undermines efforts to allocate resources efficiently and more effectively prevent fall occurrences.
Jvion’s Cognitive Machine empowers clinicians with the insights that better identify at-risk patients and deliver the individualized actions that will mitigate the risk of a fall. And it does this at admission.
What we know is that best practices include the integration of an effective tool to predict falls and the development of a tailored, patient-specific care plan that addresses the unique drivers contributing to a patient’s risk.1 With Jvion’s falls vector, clinicians have access to a machine that accounts for the more than 4,500 clinical and non-clinical factors that could contribute to the likelihood that an individual will fall. At admission, providers can identify if someone is at risk of a fall within the next 12 hours and the actions that will reduce the risk. These insights can be incorporated directly in the care plan and updated every 12 hours with new data from the machine. And the Jvion solution can do this using the clinical documentation on hand—even in the absence of validated fall events.
Jvion’s falls vector helps hospitals more strategically allocate resources (i.e. patient sitters) and minimize clinician workload by implementing the right interventions on the right patients. This means that providers are able to better utilize virtual monitoring systems versus inpatient sitters; they can implement individualized interventions upon admission; and they can minimize the waste associated with overused resources. Taken together, providers can reduce their resources by ~75% using the risk and intervention outputs delivered by Jvion’s solution—the number one Cognitive Machine designed specifically for healthcare.

[1] The Joint Commission, "Preventing falls and fall-related injuries in health care facilities," Sentinel Event, no. 55, pp. 1-5, 28 September 2015.

[2] M. Erin D. Bouldin, P. Elena M. Andresen, P. Nancy E. Dunton, P. M. Michael Simon, P. Teresa M. Waters, M. Minzhao Liu, P. Michael J. Daniels, R. P. F. Lorraine C. Mion and M. Ronald I. Shorr, "Falls among Adult Patients Hospitalized in the United States: Prevalence and Trends," Journal of Patient Safety, vol. 9, no. 1, pp. 13-17, 2013.

[3] Indiana University, "Falls: How Big Is the Problem," The Trustees of Indiana University, Bloomington, 2004.

Jvion's Thinking Machine

We created a machine that thinks like a clinician. Here is how we did it.

Immerse Yourself in Cognitive Science

Take just 2.5 minutes to dive into the world of cognitive science.

Cognitive Machine in Action

See firsthand how a cognitive machine can help your patients and your organization.