For clinical operations leaders evaluating predictive analytics in post-acute care.
Predictive analytics in home health and hospice is not a single use case. It is a set of capabilities that can be directed at different points of clinical and operational risk across the patient journey. The following examples represent Mosai's primary applications — each reflecting a different clinical decision context and a different set of downstream consequences when the prediction is accurate and acted on.
Among the highest-value applications of predictive analytics in home health is hospitalization risk modeling — and the best platforms do this at a depth most vendors do not. Mosai Pulse evaluates each patient's clinical trajectory across multiple data dimensions: vital sign trends, OASIS patterns, visit documentation, functional status changes, and clinician narrative notes processed through natural language processing. This longitudinal view generates a probability estimate for hospitalization within a defined timeframe — not based on a single threshold crossed, but on the full pattern of a patient's clinical arc.
The clinical value is the intervention window. A patient flagged as high hospitalization risk before any documented threshold is crossed gives the care team time to respond: an additional skilled visit, a care plan adjustment, a physician coordination call. Without Mosai Pulse surfacing that risk at the census level, that window does not exist — the first visible sign of deterioration may arrive only when emergency intervention is already required. Each prevented hospitalization protects the active care relationship, preserves episode revenue, and contributes positively to the readmission rate metrics that payer contracts use to set reimbursement terms.
Many patients who qualify for hospice are referred too late to receive meaningful benefit. Predictive analytics applied to a home health patient population can identify patients whose clinical trajectory suggests they may meet hospice eligibility criteria, surfacing them for clinical review and potential referral earlier. The model does not make a hospice eligibility determination — that is a physician and clinical judgment. What it does is bring forward patients whose longitudinal trajectory warrants that conversation sooner, before the referral happens under crisis conditions.
Within hospice, Mosai Muse’s predictive models identify patients approaching end of life within a near-term window — ten days from the most recent skilled visit. This allows clinical teams to adjust care intensity, initiate family preparation conversations, and ensure the right clinical resources are in place before a patient enters the active dying phase. These models require training data specific to hospice patient populations; a model trained on general healthcare data does not have the reference population to make accurate predictions here.
Hospice revocation carries both clinical and financial consequences. Mosai Muse’s predictive models trained on historical revocation patterns identify patients at elevated likelihood of disenrollment within a thirty-day window, giving care teams an opportunity to intervene before a revocation occurs. This is a distinct modeling problem from mortality or transition prediction — it requires its own training dataset and its own clinical variables.
Across both home health and hospice, one of the most operationally significant applications is clinical triage at the census level. A supervisor managing forty or sixty active patients cannot manually identify each morning which patients carry the highest clinical urgency. Mosai’s predictive models that rank the entire active census by current risk status changes the starting point of every clinical workday — from incomplete information to a structured, risk-ordered view of who needs attention and why. This does not require a new clinical workflow. It changes who initiates triage, moving that function from the clinician to the system.
Explore the full range of Mosai's predictive analytics capabilities: Mosai | Clinical Management