AI system
- System
-
NHS AI Lab Skunkworks bed-allocation proof of concept (Bayesian demand forecasting with greedy and Monte Carlo tree search allocation agents and a web user interface)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
Faculty (applied AI company) with NHS AI Lab Skunkworks (NHSX) and Kettering General Hospital, through the Home Office Accelerated Capability Environment
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Five years of pseudonymized patient administration data and one to two years of patient-flow data under an information governance process. A virtual hospital modeled on key wards with a Bayesian demand forecast. A greedy allocation agent integrated into a web interface with explainable suggestions. Skunkworks funding and an ACE-procured supplier for a 14-week build.
- Human oversight
-
Not assessed
- Relation to AI
-
The AI components forecast demand and suggest beds with an explanation, while the scheduler makes the final decision. Only the greedy agent was integrated, and the tool was tested and reviewed by the hospital rather than deployed. All read accounts come from the sponsoring public bodies (NHS AI Lab case study, GOV.UK ACE case study) and the NHSX GitHub README. So this is the deployer side describing its own pilot. No vendor-authored or independent evaluation is among the sources. The NHS page is available only through the Internet Archive because the transform.england.nhs.uk domain no longer resolves.
- AI contribution
-
The AI components forecast demand and suggest beds with an explanation, while the scheduler makes the final decision. Only the greedy agent was integrated, and the tool was tested and reviewed by the hospital rather than deployed. All read accounts come from the sponsoring public bodies (NHS AI Lab case study, GOV.UK ACE case study) and the NHSX GitHub README. So this is the deployer side describing its own pilot. No vendor-authored or independent evaluation is among the sources. The NHS page is available only through the Internet Archive because the transform.england.nhs.uk domain no longer resolves.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
14-week NHS AI Skunkworks/Faculty proof of concept (2021) forecasting demand and suggesting beds at Kettering General Hospital; tested by the hospital, open-sourced, not in live use.
- Category
-
Improved Organizational Efficiency
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Not assessed
- Comparison
-
Not assessed
- Results
-
Not assessed
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Faculty (applied AI company) with NHS AI Lab Skunkworks (NHSX) and Kettering General Hospital, through the Home Office Accelerated Capability Environment. Operator: Kettering General Hospital NHS Foundation Trust (proof-of-concept testing only).
- Jurisdictions
-
Benefit: Kettering, Northamptonshire, England. Developer:
United Kingdom. Operator: United Kingdom. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Centralized, real-time patient-flow and admissions data across all specialties, which the hospital lacked. Reconfigurability by staff for changes in beds, ward layouts and admission peaks. Compliance with the UK Medical Device Regulations 2002 before any deployment. Funding to develop and operationalize the system beyond the proof of concept.
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
Neither the GOV.UK case study of 12 October 2023 nor the NHS AI Lab Skunkworks project pages report deployment, further funding or results after the proof of concept, and the GitHub repository carries no archive notice.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0339-source-0001–0005
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
People: No patient outcome is documented. Organizations: The proof of concept was tested and reviewed but not used in live bed management. Society: The code is open source but no reuse outcome is documented.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The makers' claim
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Healthcare operations: hospital bed management. NHS acute hospital trust.
- Purpose
-
Built to forecast bed demand and suggest bed allocations to the hospital's bed-management team. The proof of concept demonstrated that purpose without a measured outcome.
- Dates
-
Date basis unassessed: 2021 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 139a2684abf1…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
Press release Developer
NHS Transformation Directorate, NHS AI Lab Skunkworks (2021). Improving hospital bed allocation using AI. Case study, 10 Dec 2021.
The resulting proof of concept was then tested and reviewed by Kettering General Hospital.
Kettering General Hospital will be working with Faculty to bid for further funding to develop and operationalise the bed allocation system.
-
Press release Developer
Accelerated Capability Environment, Home Office (2023). Using AI to improve patient bed allocation decisions in hospital. GOV.UK case study, 12 Oct 2023.
schedulers to make the final bed allocation decision
-
Other Developer
is not intended for deployment in a clinical or non-clinical setting without further development and compliance with the UK Medical Device Regulations 2002.
The greedy allocation agent is the only agent integrated into the UI due to performance issues with the MCTS approach