Hospital Bed Occupancy Forecast

This dataset provides detailed forecasts of hospital bed occupancy rates by department and time, incorporating expected admissions, discharges, and resource utilization metrics. It enables healthcare administrators to anticipate capacity needs, optimize resource allocation, and improve patient care delivery through data-driven planning. The dataset supports both operational and strategic decision-making in hospital management.

  • last updated 20 Aug 2025
  • by GoMask
The brief that made it

Hospital capacity planning and surge management

Sample rows

preview · 8 of 200 rows · all 16 columns
forecast_idstringforecast_methodstringforecasted_occupied_bedsintegerdepartmentstringhospital_idstringhospital_namestringforecast_datedateforecast_timestringtotal_bedsintegerforecasted_occupancy_ratefloatexpected_admissionsintegerexpected_dischargesintegerresource_utilization_scorefloatcreated_atdatetimeupdated_atdatetimenotesstring
F20240621-001ML-based80General WardH10234Green Valley Medical Center2024-07-0308:008693.02530.932024-06-21T09:11:232024-06-21T11:05:12Routine weekday forecast with high census following holiday.
F20240621-002Expert estimate22ICUH10235Bay Area Health Institute2024-07-0416:002491.67120.922024-06-21T09:13:44blankSurge expected post-local festival; critical beds prioritized.
F20240621-003ARIMA12PediatricsH10236Lakeside Community Hospital2024-07-0512:005223.08210.192024-06-21T09:16:222024-06-21T12:30:55Low census prior to summer camp admissions.
F20240621-004ML-based60General WardH10237Riverfield Clinic2024-07-0606:006296.77850.972024-06-21T09:18:01blankPost-weekend spike; increased admissions due to flu cases.
F20240621-005Expert estimate14EmergencyH10238Sunrise Regional Hospital2024-07-0718:001593.33110.942024-06-21T09:20:122024-06-21T10:12:19Weekend event; higher trauma occupancy expected.
F20240621-006ML-based45ICUH10239Harborview Medical Center2024-07-0322:004697.83210.982024-06-21T09:22:38blankCritical occupancy; single-bed turnovers expected.
F20240621-007ARIMA38GeriatricsH10240Northside General Hospital2024-07-0810:003997.44000.972024-06-21T09:24:522024-06-21T12:14:45Stable occupancy; scheduled maintenance week.
F20240621-008Expert estimate11NICUH10241Eastside Pediatric Hospital2024-07-0909:001384.62110.852024-06-21T09:26:31blankSeasonal RSV spike; higher neonatal admissions forecasted.

What the 200 rows show

from the 200-row sample

Expert estimate (forecast method) stands out: mean forecasted_occupied_beds is 11.9, against 35.6 for the rest.

  • 18.5median forecasted_occupied_beds
  • 50forecast times
  • 30median total_beds
  • 90.7median forecasted_occupancy_rate
  • 1median expected_admissions
  • 1median expected_discharges
Mean forecasted_occupied_beds by forecast_method200 rows
0204036.5ML-based68 rows34.6ARIMA67 rows11.9Expert estim…65 rows
forecasted_occupied_beds200 rows, in bands of 10
040807233133291079114050100forecasted_occupied_beds →

Median 18.5, from 0 to 98.

department200 rows · top 10 of 12 values
  1. General Ward36
  2. ICU27
  3. Pediatrics17
  4. Rehabilitation17
  5. Oncology16
  6. Maternity16
  7. Psychiatry15
  8. Neurology15
  9. Cardiology14
  10. NICU10
16 columns by typefrom the column list below
  • string 7
  • integer 4
  • float 2
  • date 1
  • datetime 2

Columns

16 columns in three groups
blueprint · 16 columns
columntypedescriptionexample
Text 7 columns
forecast_idstringUnique identifier for each hospital bed occupancy forecast recorduniqueF20240621-001
hospital_idstringUnique identifier for the hospitalH10234
hospital_namestringName of the hospitalRiverfield Clinic
departmentstringHospital department or unit (e.g., ICU, General Ward, Pediatrics)12 departmentsGeneral Ward
forecast_timestringTime of day for the forecast (e.g., 08:00, 16:00); use 24-hour formatoptional08:00
forecast_methodstringMethod or model used for forecasting (e.g., ARIMA, ML-based, expert estimate)3 methods · optionalML-based
notesstringAdditional comments or notes about the forecastoptionalRoutine weekday forecast …
Numbers 6 columns
total_bedsintegerTotal number of beds available in the department/unit1 or more86
forecasted_occupied_bedsintegerNumber of beds expected to be occupied at the forecast time0 or more80
forecasted_occupancy_ratefloatForecasted occupancy rate as a percentage (0-100)0 to 10093.02
expected_admissionsintegerNumber of patient admissions expected during the forecast period0 or more · optional5
expected_dischargesintegerNumber of patient discharges expected during the forecast period0 or more · optional3
resource_utilization_scorefloatComposite score indicating resource utilization (e.g., staff, equipment) in the department/unit (0-1 scale)0 to 1 · optional0.93
Dates and times 3 columns
forecast_datedateDate for which the occupancy forecast is made2024-07-03
created_atdatetimeTimestamp when the forecast record was created2024-06-21T09:11:23
updated_atdatetimeTimestamp when the forecast record was last updatedoptional2024-06-21T11:05:12

Use it for

  • median forecas…18.5200 rowsmean forecasted occup…36.5ML-bas…34.6ARIMA11.9Expert…

    A healthcare dashboard

    Forecasted_occupied_beds by forecast_method and a breakdown of department. Excel, Power BI or Tableau.

  • Why do the 65 Expert estimate rows have a mean forecasted_occupied_beds of 11.9?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable forecasts with hospital_id, hospital_name and department to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 16 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows16 columns
Yours1,000 rows16 columns

blueprint · hospital-bed-occupancy-forecast

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 16 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Include daily admission and discharge records
  • Calculate average length of stay per department
  • Segment data by ward type
  • Flag high-demand periods for occupancy surges
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
hospital-bed-occupancy-forecast

What should your data show?

Preview 20 rows free
No signup. No card.