Early Findings: Reducing Incidents
Operator Uses Fynn to Identify Early Warning Signs and Minimize Incidents
According to the U.S. Department of Health and Human Services (HHS), 23.5% of hospitalizations were preventable among adults aged 65+ who were diagnosed with Alzheimer’s disease and other dementias.
Reducing incidents through earlier detection of potential changes in acuity is one of Fynn’s major focal points. Through analyzing the behavioral data of residents in Independent Living (IL), Assisted Living (AL), and Memory Care (MC), Fynn has identified a strong correlation between declining resident behavior and incident occurrence. By recognizing meaningful shifts in resident behavioral patterns sooner, senior living staff is better able to anticipate incidents and intervene—improving both resident well-being and asset performance.
Predicting and avoiding 1 incident per month preserves $10M in asset value
Acute incidents are detrimental to short and long-term resident well-being as well as community performance. The graph below shows the behavioral patterns of a Memory Care resident leading up to an incident that occurred within 10 days of his/her initial behavioral decline.
This single incident would have cost the operator approximately $84k of revenue and resulted in the following:
- Resident 2 moving out
- Resident 2’s spouse moving out
- Unit vacancy estimated to require 90 days to back-fill
- Staff and management time required to handle the incident and related work
Predicting and avoiding a single incident per month presents major benefits to residents, families, and communities alike—preserving $504k in annual NOI and $10M in asset value. To help managers effectively address the source of the problem and potentially mitigate future incidents, Fynn performed a root cause analysis of the incident.
Fynn uses behavioral data for root cause analysis and future incident prevention
Understanding when and where a change in resident well-being occurs empowers management to dive deeper into the root cause of the issue. By analyzing each resident’s behavior continuously, Fynn identified a majority of service failures exist in two main categories: 1) friction between residents and the employees caring for them and 2) friction associated with the administration of specific ADL tasks.
The graph on the right shows Resident 2’s average behavior score (y-axis) for 6 different ADL task categories (x-axis). Based on the data, this resident generally demonstrated positive behavior for most ADL categories but had a sharp negative reaction to health checks performed every 2 hours. This repeated agitation ultimately led to the resident becoming aggressive with care staff, resulting in a costly incident.
To remove this point of operational friction, staff was coached to adjust checks to observe residents in a manner that lowered the noise level and reduced distraction from the activity at hand.
Earlier detection and prevention are key to improving resident well-being and community NOI
Providing accommodative care tailored to the individual improves the resident experience while setting employees up for success through improved awareness, coaching, and the development of new operational best practices.
Each of these insights captured by Fynn creates an opportunity for us to “close the loop” to drive improvements by leveraging algorithms to:
- comb through comprehensive resident well-being data,
- proactively identify trends and anomalies,
- tie these trends and anomalies to action in the Fynn platform, and
- monitor the results to drive overall improvements.
Fynn will continue to apply learnings from behavioral analysis to inform innovation for future features within the solution tailored to the real-world needs of users.