elderly woman looks out the window

How AI tools can improve mental health in long-term care

In the past few years, we’ve seen an increased awareness about the prevalence of depression and other mental illnesses in the U.S. But usually, these reports focus on the youth and adult populations. It may surprise you to learn that by some estimates, up to 40% of those in senior living and post-acute care shows signs of depression and other mental health challenges.1

But despite the prevalence of depression in seniors, at MatrixCare we identified only 5% of the residents have a diagnosis for Depression in the EHR.2 Senior living and long-term care organizations need help to identify residents at risk for mental health challenges and to make sure these residents get the support and treatment they need. This is vital because conditions like depression make it more difficult for residents to recover from surgery, endure cancer treatment, engage in cardiac rehabilitation and participate in other treatments that improve health outcomes. And of course, appropriate mental health treatment enhances their overall quality of life.

Too often, the residents themselves may not recognize signs of an issue, or they may not be comfortable discussing what they feel. Furthermore, clinicians sometimes feel that managing a mental health diagnosis adds documentation and other complications to the care they provide. These factors both point to the need for better tools to identify, monitor, and treat residents with mental health challenges.

AI and mental health

AI tools can help. By tracking early indicators such as poor quality of sleep or loss of appetite, AI can track trends and alert caregiving staff to potential issues. Having a tool that can objectively measure behaviors, rather than relying on subjective feedback from a resident or assessments of staff members, offers a way to intervene earlier and provide appropriate care.

This helps not only with indicators that need immediate attention, but also with developing a longer-term history to see when behavioral changes may have started. We don’t expect nursing staff to go back over six months of data to determine whether a resident hasn’t been sleeping well or when their appetite started to decline. What technology can do right now is actively monitor for these patterns and provide proactive signals for the clinical team. Caregivers can get summaries that include all the data when something comes up, and any signals they need to pay attention to. They may decide to do a depression assessment, and based on those results, they may change the clinical care they provide. With AI, everything can happen without adding to a caregiver’s workload.

The need for accurate diagnoses

There’s a financial aspect to consider as well. If a facility is missing a mental health diagnosis, they’re not going to be reimbursed for any care they’re providing to help deal with depression, anxiety, or other conditions. Even if a resident is getting the care they need to address a mental health challenge, if there’s no diagnosis, there’s no reimbursement. And when you add in the factor of how mental illness often negatively affects other health outcomes, that can be another heavy financial burden on organizations. From this perspective, there’s a lot of incentive to make sure facilities are identifying these patients and making sure they receive proper care. If they’re already providing that care, they need to make sure the diagnosis is adequately documented so they are fully reimbursed, which in turn helps ensure they can be staffed and resourced appropriately to deliver mental health care.

At MatrixCare, we’re developing an AI tool to help clinicians to get a better overall picture of residents’ mental health risks. Using EHR data over time, this new tool will help clinicians see trends and patterns and flag residents who may be at risk, allowing earlier screening and treatment, when appropriate. Using AI to evaluate existing data helps make decisions about which residents to screen or treat more objective. This helps remove guesswork for clinicians and helps residents get the treatment and support they need faster.

1. https://pubmed.ncbi.nlm.nih.gov/18457336/

More information about mental health for seniors Depression in the nursing home: a cluster-randomized stepped-wedge study to probe the effectiveness of a novel case management approach to improve treatment (the DAVOS project) 7/11/2019 https://trialsjournal.biomedcentral.com/articles/10.1186/s13063-019-3534-x

Depressive symptoms in long term care facilities in Western Canada: a cross sectional study 12/2/2019 https://bmcgeriatr.biomedcentral.com/articles/10.1186/s12877-019-1298-5

Discover how MatrixCare’s AI tools can enhance resident well-being.

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.

Two office professionals looking at a laptop

See MatrixCare in action

Start by having a call with one of our experts to see our platform in action.