How AI tools can affect quality metrics
Now more than ever, post-acute care providers are focused on outcomes. And rightfully so. Improving outcomes is not only the right thing for patients and residents, but also supports the principles of value-based care and can boost the quality metrics that CMS monitors.
AI tools can support the work to improve quality metrics. For example, being able to reduce the number of falls in your organization, or de-prescribe psychotropics when appropriate can affect outcomes, and therefore, quality ratings.
There are three main ways AI can support better outcomes in post-acute care: monitoring and alerting, proactive care or care suggestions, and active care support. We’ll look at each of these aspects of AI.
Monitoring and alerting
Today’s EHR systems collect more data than ever. But at the same time, caregivers are always busy. It’s not reasonable to think they can review resident records and pick up all the nuanced combinations of each resident’s data such as one person not eating well or another not sleeping well, and quickly understand what that data could indicate.
Using AI tools to gather data and detect patterns is one way to help alert care managers about potential risks to residents. For example, I recently had a conversation with a post-acute organization where they used AI tools to identify a resident’s risk of COPD exacerbation. Similarly, AI tools can monitor data to help alert caregivers to mental health issues, fall risks and more, without adding to caregivers’ workloads. When caregivers can prepare ahead of time to deliver needed care, it improves outcomes by reducing the number of events they need to react to.
Proactive care and care suggestions
Not only are AI tools good at monitoring data and finding patterns, it’s also good at stratifying risk. This means it can help identify steps in the care process that can be improved for the resident’s benefit. One example is mobility risks. One set of quality metrics is based on a provider’s ability to identify which individuals might have mobility issues. This can have a major impact on a facility’s overall CMS quality measures, so improving mobility across the organization by paying attention to the right residents at the right time can not only drive efficiency but also improve outcomes.
AI tools can successfully do this because they have an abundance of historical information from the EHR. These tools can evaluate what happened when some signs were ignored, as well as what happened when a caregiver took action by adding treatments or additional points of care that resulted in positive outcomes. Having that history and how past events played out gives AI the power to analyze past data and run simulations using that information. This machine learning process helps these tools identify the actions that led to the best outcomes and make recommendations for future decisions. These tools can make suggestions for actions caregivers can take on a day-to-day basis to improve outcomes and quality measures in their organization.
Active care support
While AI that monitors, alerts and offers proactive care suggestions happens passively in the background, active care support happens in real time, while the caregiver is working with a resident. For example, a resident may have instructions for a five-minute supported walk during the day to help recover from an injury or procedure. If a caregiver is with the resident and forgets to document that additional exercise, an AI tool can prompt them to check whether that care has been provided. This allows the caregiver to complete a task if it’s missed, document the care and move on to the next resident without pushing any tasks to the next day or worrying that something is overlooked.
Using tools in this way helps maximize the amount of care given and improve caregivers’ efficiency and effectiveness. This can not only contribute to better outcomes and quality metrics, but also can improve staff satisfaction and retention.
Request a demo today for a closer look at MatrixCare.
Daniel Zhu
Daniel Zhu comes from a diverse background of clinical experience and technology entrepreneurship. Having spent five years in clinical and clinical research roles with the Alberta health system and the University of Toronto health network, he has diverted his medical expertise to architecting and building technology solutions to optimize health care practice. At various organizations, he has lead engineering teams, product teams, and founded his own natural language processing start-up in the clinical research space. Stepping away from the start-up world, Daniel has spent time as a data consultant for large corporations such as Ford, Co-op, and RBI. Re-entering the health technology field, today Daniel has recently joined the ResMed and MatrixCare team to lead the productization of AI and machine learning capabilities.
See MatrixCare in action
Start by having a call with one of our experts to see our platform in action.
MatrixCare offers industry-leading software solutions. Thousands of facility-based and home-based care organizations trust us to help them improve efficiency and provide exceptional care.
© 2024 MatrixCare is a registered trademark of MatrixCare. All rights reserved.