HOW IT WORKS
Muse considers more than 800 assessment points from nearly 1 million visits to identify which hospice patients are most likely to transition within 7-10 days. The model continues to learn and improve with each new patient visit. The science is considered a true neural network--the only one of its kind in the hospice space.
Muse categories and emphasizes patients according to their needs. From there, it alerts clinical supervisors when a patient would benefit from additional scheduled skilled visits. The clinical supervisor can then easily schedule the appropriate visits from Muse's EMR interface.
When hospice care providers can more accurately predict when their patients will transition, they can ensure their patients and their patients' families receive the care that matters most in the final days and final hours of a patients life.
The mission of hospice is to offer peaceful, holistic care that leaves patients and their loved ones in control, comfortable and pain-free at the end of life. While hospice patient satisfaction overall remains high, there's room for vast improvement – especially in the final critical days. A patient’s last two days of life, when symptoms escalate, can be a trying time for patients and their families. According to a recent JAMA study, 12.3% of patients on routine hospice care in the home received no skilled visits in the last two days of life. Patients who died on a Sunday had the worst luck: they were more than three times less likely to have a skilled visit than those who died on a Tuesday. Muse was born to ensure that every patient receives the care and comfort they need in their final days and that ultimately – no patient transitions alone.
At Muse we want to empower hospice providers with world-class analytics to ensure every hospice patient transitions with unparalleled quality and dignity. We want to ensure no patient transitions alone.
Muse technology is powered by state-of-the-art machine learning techniques that uncover features from a variety of structured and unstructured data points including skilled and unskilled assessment data, socio-economic indicators, vital signs, medications, patient logs, supplies and care-plan orders. The deep learning model is constantly learning new variables and correlations that adapts to patient trends. Not only is the technology's predictive capability unparalleled, but it's also easily integrated and therefore accessible through an agency's EMR – which enables effortless adoption and therefore improved end-of-life care quality that's easily measured and managed.
"This tool provides the clinical team with additional insights they need to identify a patient's final days. Anything that enables us as caregivers to positively intervene earlier - at a critical and intimate point in a hospice patient's life - is of utmost value."
Dr. Andrew Mayo / St. Croix Hospice / Chief Medical Officer