Bed Pressure Intelligence
Monitor ward pressure, forecast occupancy risk, surface anomalies, and support capacity decisions.
Active use caseOpen Workspace
Hospital Operations Intelligence
Use Cases
Customer-ready use case briefings
Each tab explains the business objective, source data, operating outputs, governance evidence, and source-to-decision story for a platform use case.
Business objectiveData inputsGoverned outcomes
Business Objective
What this use case is designed to change
Occupancy, forecasting, anomaly detection, and discharge decision metadata.
Current Occupancy
87.3%Across live ward footprint
7-Day Forecast
3Breach risks predicted
Active Anomalies
5Actionable signals
Data Inputs
Source data needed
bed_eventswardspatients
Ingestion pattern: MySQL source to Airbyte to Postgres raw landing, then dbt staging and analytics.
Business Outcomes
Operational outputs
Bed Pressure workspaceAdministration -> GovernanceSuperset dashboardDecision notifications
Governance Evidence
Why customers can trust it
- Owner
- Clinical Operations Analytics
- Steward
- Capacity Planning Lead
- Quality posture
- warning freshness, warning quality
- Classified columns
- 30
- Policy coverage
- 2 controls mapped
Source-To-Decision Story
How data becomes an operational decision
Source System
EHR and operational bed movement events.
Raw Landing
Raw landed events in PostgreSQL before transformation.
Standardization
Normalized event stream used by occupancy marts.
Analytics Mart
Governed occupancy fact for daily ward pressure.
Runtime Model
R runtime producing breach-risk forecasts.
Runtime Model
R runtime producing pressure anomaly signals.
KPI
Executive occupancy headline used in the workspace shell.
Dashboard
Executive-facing occupancy evidence dashboard.
Operational Workspace
Operational status, alerts, predictions, and evidence views.
Decision Action
Operational actions triggered by forecast and anomaly evidence.
Workspace Navigation