Forecasting
AuraScore 83/100

Hospital Inpatient Bed Census and Surge Forecasting Plan

Design an operational forecasting plan to project department-level bed occupancy and seasonal surge staffing in acute care hospitals.

Use this template when healthcare operations need to forecast inpatient census fluctuations and ward capacity constraints. It establishes clear baseline data inputs, statistical modeling approaches, and contingency escalation protocols.

Template

Role: Principal Healthcare Operations Modeler with fifteen years of experience in acute care demand planning.

Context

  • Facility identity: {{hospital_name}}
  • Historical analysis baseline: {{historical_census_window}}
  • Targeted units: {{clinical_departments}}
  • Seasonal epidemiological drivers: {{seasonal_epidemic_factors}}
  • Planning window: {{target_forecast_horizon}}
  • Escalation trigger level: {{surge_threshold_percentage}}

Task

Develop an actionable operational forecasting plan that projects department-specific bed census volumes, quantifies capacity breach risks, and aligns nurse-to-patient staffing thresholds across {{target_forecast_horizon}} for {{hospital_name}}.

Method

  1. Ingest historical admission, discharge, and transfer (ADT) logs from {{historical_census_window}} to compute department-level average length of stay (ALOS).
  2. Isolate routine daily variability from extreme variance driven by {{seasonal_epidemic_factors}} across {{clinical_departments}}.
  3. Define an autoregressive integrated moving average (ARIMA) and Poisson arrival modeling architecture to forecast admissions.
  4. Project daily bed occupancy rates across the {{target_forecast_horizon}} timeline with 80% and 95% confidence intervals.
  5. Calibrate warning thresholds when forecasted bed utilization exceeds {{surge_threshold_percentage}} of licensed capacity.
  6. Translate bed occupancy projections into required nursing shift allocations by clinical specialty.
  7. Formulate a dynamic operational trigger framework for opening overflow beds and deploying PRN staffing pools.

Constraints

  • MUST separate scheduled elective surgical admissions from emergency department arrivals.
  • MUST NOT exceed the maximum licensed bed count defined per unit in {{clinical_departments}}.
  • Recommendations MUST include a data refresh cadence of at least weekly updates.
  • Projections must account for weekend discharge bottlenecks and weekday admission surges.

Output format

  1. Executive Summary (under 150 words)
  2. Baseline Modeling Architecture (bulleted listing model assumptions and data inputs)
  3. Departmental Demand Projections Table (Columns: Department, Forecasted Bed Mean, Peak Utilization %, Surge Risk Level)
  4. Operational Trigger & Staffing Escalation Matrix
  5. Model Governance & Re-estimation Protocol

Self-review

  • Are all units listed in {{clinical_departments}} explicitly modeled in the output?
  • Does the escalation protocol directly address the {{surge_threshold_percentage}} trigger point?
  • Is the mathematical distinction between scheduled and emergency arrivals clearly maintained?
AuraScore breakdown
83/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-forecasting
healthcare-life-sciences
healthcare
capacity-planning
bed-census