There’s a good reason to be concerned about rehospitalizations – the cost is considerable for the national healthcare system, providers, and for the patients who bounce back to the hospital from a nursing home.
Hospital readmission of Medicare patients alone cost the government $26 billion a year, according to the Robert Wood Johnson Foundation. Nursing homes with high rehospitalization rates face several consequences, from financial penalties to reduced revenue and fewer referrals from hospitals and health systems.
But the most devastating effect of readmissions is on the patients themselves. Let’s consider Simon, a 70-year-old man who was admitted to a skilled nursing community with multiple comorbidities, including congestive heart failure.
Not unusual, Simon was cared for by three different nurses on three different shifts. In the course of three days there were three very subtle changes in his condition such as slight ankle swelling, a little cough, and some weight gain—noted by different nurses on his care team. While any of these changes might not mean much as separate indicators, together they resulted in an acute condition.
Simon was rehospitalized in a matter of days with acute pulmonary edema at a cost of about $20,000 for something that could have easily been prevented with immediate intervention.
Now consider if Simon’s care team had had access to SAIVA’s artificial intelligence (AI) tool. Essentially, the technology does the work of pouring through the resident’s chart to find trends and behaviors that predict when they are at risk of decline and potentially being rehospitalized. The output is a daily report that lists those residents at highest risk of rehospitalization and their most pertinent clinical data from the EHR. The report is simply emailed to the head nurse each morning and is used to prioritize and focus resident care to prevent negative outcomes.
With SAIVA, Simon is included on the risk report. The nurse checks on him and calls the physician, who prescribes Lasix. Within two days, the swelling is down and Simon is back on track for a cost of $1. Most importantly, Simon is spared a decline and traumatic rehospitalization, remaining in the care of the skilled nursing community until he fully recovers and can return home.
The ability to detect subtle changes in condition are key to intervening early, treating in place, and avoiding the hospital. Moreover, looking for factors that are not directly related to a patient’s condition is also key. Research indicates that rehospitalizations can be caused by factors other than a recurrence of the original health event. With so many factors to consider, detecting and preventing clinical decline is a formidable challenge for the clinical team.
Take affirmative steps to master effective clinical protocols and nursing competencies. Dramatically improve care quality and operational performance by efficiently using technology to identify at-risk patients before they become acute.