{ "id": "AIBD-0339", "title": "NHS AI Lab Skunkworks and Faculty build a 14-week proof-of-concept AI bed-allocation tool for Kettering General Hospital; tested and reviewed, released as open source, not deployed", "summary": "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.", "date_observed": "2021-12-10", "date_basis": "unassessed", "date_precision": "unassessed", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Kettering General Hospital, a National Health Service (NHS) foundation trust, asked the NHS AI Lab Skunkworks team (NHSX) for support exploring AI for bed management. The Skunkworks funded a 14-week project with Faculty, an applied AI supplier selected through the Home Office's Accelerated Capability Environment (ACE). The team used five years of pseudonymized patient administration data and one to two years of patient-flow data. It built a virtual hospital and a Bayesian model forecasting how many patients with given characteristics would present. It compared greedy allocation, Monte Carlo tree search and reinforcement learning for suggesting beds. Only the greedy agent was integrated into the web interface because of performance issues with the tree search. Reinforcement learning was not developed within the project. The resulting proof of concept was tested and reviewed by the hospital. A human scheduler still makes the final bed-allocation decision. It was released as open source on the NHSX GitHub pages. The README places it at Technology Readiness Level 4, not intended for deployment without further development and compliance with the UK Medical Device Regulations 2002. The NHS case study (10 December 2021) says the hospital would work with Faculty to bid for funding to develop and operationalize the system. The GOV.UK ACE case study (12 October 2023) lists potential benefits only. No quantified results and no live use are documented, so this is a general benefit. The GitHub README gives a 12-week initiative launched in May 2021, while the NHS and GOV.UK pages say 14 weeks.", "category": "general benefit", "unexpected": false, "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.", "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_version": null, "developer": "Faculty (applied AI company) with NHS AI Lab Skunkworks (NHSX) and Kettering General Hospital, through the Home Office Accelerated Capability Environment", "deployer": "Kettering General Hospital NHS Foundation Trust (proof-of-concept testing only)", "location": "Kettering, Northamptonshire, England", "domain": "Healthcare operations: hospital bed management", "segment": "NHS acute hospital trust", "benefit_type": "Improved Organizational Efficiency", "taxonomy_note": "The intended good is bed allocation and demand forecasting; the proof of concept was tested but never deployed and reports no result.", "registry_ids": {}, "ratings": [ { "group": "personal", "depth": null, "reason": "No patient outcome is documented." }, { "group": "organizational", "depth": null, "reason": "The proof of concept was tested and reviewed but not used in live bed management." }, { "group": "societal", "depth": null, "reason": "The code is open source but no reuse outcome is documented." } ], "ai_role": { "status": "assessed", "statement": "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." }, "evidence": [ { "kind": "press release", "citation": "NHS Transformation Directorate, NHS AI Lab Skunkworks (2021). Improving hospital bed allocation using AI. Case study, 10 Dec 2021.", "title": "Improving hospital bed allocation using AI", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "The resulting proof of concept was then tested and reviewed by Kettering General Hospital." }, { "kind": "press release", "citation": "NHS Transformation Directorate (2021). Improving hospital bed allocation using AI, section 'What next?'.", "title": "Improving hospital bed allocation using AI (What next?)", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "Kettering General Hospital will be working with Faculty to bid for further funding to develop and operationalise the bed allocation system." }, { "kind": "press release", "citation": "Accelerated Capability Environment, Home Office (2023). Using AI to improve patient bed allocation decisions in hospital. GOV.UK case study, 12 Oct 2023.", "title": "Using AI to improve patient bed allocation decisions in hospital", "url": "https://www.gov.uk/government/case-studies/using-ai-to-improve-patient-bed-allocation-decisions-in-hospital", "date": "2023-10-12", "written_by": "makers", "quote": "schedulers to make the final bed allocation decision" }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README. GitHub repository nhsx/skunkworks-bed-allocation.", "title": "nhsx/skunkworks-bed-allocation README", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "date": null, "written_by": "makers", "quote": "is not intended for deployment in a clinical or non-clinical setting without further development and compliance with the UK Medical Device Regulations 2002." }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README, note on the allocation agents.", "title": "nhsx/skunkworks-bed-allocation README (allocation agents)", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "date": null, "written_by": "makers", "quote": "The greedy allocation agent is the only agent integrated into the UI due to performance issues with the MCTS approach" } ], "replication": { "produced_by": [ "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" ], "must_hold": [ "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" ], "echoes": [ { "date": null, "setting": "Planned bid by Kettering General Hospital with Faculty for funding to develop and operationalize the system (NHS case study, “What next?”); no later outcome read", "model_version": null, "outcome": "unknown", "source": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/" } ] }, "paired_incident": null, "headline": "Faculty's Kettering bed tool is open-sourced but not deployed", "metric": null, "comparator": null, "later": { "status": "unknown", "date": null, "note": "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.", "quote": null, "url": null }, "value": null, "developer_country": "United Kingdom", "deployer_country": "United Kingdom", "unrated_because": null, "brief_notes": null, "brief": null, "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://faculty.ai/contact; https://en.wikipedia.org/wiki/Kettering_General_Hospital", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" } ], "confidence": "claimed", "shade": "low", "claim_status": "The makers' claim", "claim_basis": "Sources: two press releases from the makers and the makers' other. The cited evidence includes no independent source and no finding by a regulator or court.", "profile": { "case_id": "AIBD-0339", "catalog_version": "1.0.0", "source_fingerprint": "139a2684abf1fbea40d45c7a776ff7f0fca3fc04be32229b5b3d2ad436b6f60e", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0339-source-0001", "AIBD-0339-source-0002", "AIBD-0339-source-0003", "AIBD-0339-source-0004", "AIBD-0339-source-0005" ], "families": { "strategic assessments": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "evaluations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "monetary observations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "institutional decisions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] } }, "fields": { "actors[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "developer": "Faculty (applied AI company) with NHS AI Lab Skunkworks (NHSX) and Kettering General Hospital, through the Home Office Accelerated Capability Environment", "deployer": "Kettering General Hospital NHS Foundation Trust (proof-of-concept testing only)" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "developer", "deployer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "actors[].ownership_control": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "ai_contribution": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ai_role": { "status": "assessed", "statement": "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." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "general benefit", "ai_role": { "status": "assessed", "statement": "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." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role", "category" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].alternatives": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].assessor_date": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].depth": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "low", "evidence_word": "claimed", "claim_status": "The makers' claim", "basis": "Sources: two press releases from the makers and the makers' other. The cited evidence includes no independent source and no finding by a regulator or court.", "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review." } }, "provenance": { "kind": "curatorial", "basis": "Derived from the existing case display properties; not a new evidentiary judgment.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rationale": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No patient outcome is documented." }, { "group": "organizational", "reason": "The proof of concept was tested and reviewed but not used in live bed management." }, { "group": "societal", "reason": "The code is open source but no reuse outcome is documented." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rubric_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].status_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].target": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No patient outcome is documented." }, { "group": "organizational", "reason": "The proof of concept was tested and reviewed but not used in live bed management." }, { "group": "societal", "reason": "The code is open source but no reuse outcome is documented." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "availability": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "brief": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_kind": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_links[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_links": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_strength": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].missingness": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].proposition": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "cross_border_flows[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "decisions[].action_outcome": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].grounds": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].institution_task": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].success_criterion": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "deployment_stage": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "economics[].amount": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].costs[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].counterfactual": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].currency_price_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].gross_net": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].measure_type": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].period_unit": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].realization": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].recipient_payer": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].return_payback": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].valuation_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "evaluations[].ai_uplift": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].comparator": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].design": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].effect": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].exposure": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].measurement_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].metric": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].reproduction_materials": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].setting_sample": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].uncertainty_limitations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "external_references[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "unknown", "note": "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." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "later" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "human_oversight": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "id": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "id": "AIBD-0339" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "id" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "infrastructure_dependencies[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiaries": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiary_count": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].benefit_type": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "benefit_type": "Improved Organizational Efficiency", "taxonomy_note": "The intended good is bed allocation and demand forecasting; the proof of concept was tested but never deployed and reports no result." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "benefit_type", "taxonomy_note" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].claim": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Kettering General Hospital, a National Health Service (NHS) foundation trust, asked the NHS AI Lab Skunkworks team (NHSX) for support exploring AI for bed management. The Skunkworks funded a 14-week project with Faculty, an applied AI supplier selected through the Home Office's Accelerated Capability Environment (ACE). The team used five years of pseudonymized patient administration data and one to two years of patient-flow data. It built a virtual hospital and a Bayesian model forecasting how many patients with given characteristics would present. It compared greedy allocation, Monte Carlo tree search and reinforcement learning for suggesting beds. Only the greedy agent was integrated into the web interface because of performance issues with the tree search. Reinforcement learning was not developed within the project. The resulting proof of concept was tested and reviewed by the hospital. A human scheduler still makes the final bed-allocation decision. It was released as open source on the NHSX GitHub pages. The README places it at Technology Readiness Level 4, not intended for deployment without further development and compliance with the UK Medical Device Regulations 2002. The NHS case study (10 December 2021) says the hospital would work with Faculty to bid for funding to develop and operationalize the system. The GOV.UK ACE case study (12 October 2023) lists potential benefits only. No quantified results and no live use are documented, so this is a general benefit. The GitHub README gives a 12-week initiative launched in May 2021, while the NHS and GOV.UK pages say 14 weeks.", "benefit_type": "Improved Organizational Efficiency" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "benefit_type" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].distribution": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].duration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].stakeholder_group": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No patient outcome is documented." }, { "group": "organizational", "reason": "The proof of concept was tested and reviewed but not used in live bed management." }, { "group": "societal", "reason": "The code is open source but no reuse outcome is documented." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].status": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].tradeoffs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].unexpected": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "unexpected": false, "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." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "unexpected", "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "places[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "location": "Kettering, Northamptonshire, England", "developer_country": "United Kingdom", "deployer_country": "United Kingdom" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "location", "developer_country", "deployer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "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." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "record_dates": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "date_observed": "2021-12-10", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://faculty.ai/contact; https://en.wikipedia.org/wiki/Kettering_General_Hospital", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "date_observed", "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.attempts[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "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" ], "must_hold": [ "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" ], "echoes": [ { "setting": "Planned bid by Kettering General Hospital with Faculty for funding to develop and operationalize the system (NHS case study, “What next?”); no later outcome read", "outcome": "unknown", "source": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.conditions": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "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" ], "must_hold": [ "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" ], "echoes": [ { "setting": "Planned bid by Kettering General Hospital with Faculty for funding to develop and operationalize the system (NHS case study, “What next?”); no later outcome read", "outcome": "unknown", "source": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "revision_history[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://faculty.ai/contact; https://en.wikipedia.org/wiki/Kettering_General_Hospital", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Healthcare operations: hospital bed management", "segment": "NHS acute hospital trust" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "domain", "segment" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].access_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].citation_locator": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "press release", "citation": "NHS Transformation Directorate, NHS AI Lab Skunkworks (2021). Improving hospital bed allocation using AI. Case study, 10 Dec 2021.", "title": "Improving hospital bed allocation using AI", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "The resulting proof of concept was then tested and reviewed by Kettering General Hospital." }, { "kind": "press release", "citation": "NHS Transformation Directorate (2021). Improving hospital bed allocation using AI, section 'What next?'.", "title": "Improving hospital bed allocation using AI (What next?)", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "Kettering General Hospital will be working with Faculty to bid for further funding to develop and operationalise the bed allocation system." }, { "kind": "press release", "citation": "Accelerated Capability Environment, Home Office (2023). Using AI to improve patient bed allocation decisions in hospital. GOV.UK case study, 12 Oct 2023.", "title": "Using AI to improve patient bed allocation decisions in hospital", "url": "https://www.gov.uk/government/case-studies/using-ai-to-improve-patient-bed-allocation-decisions-in-hospital", "date": "2023-10-12", "written_by": "makers", "quote": "schedulers to make the final bed allocation decision" }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README. GitHub repository nhsx/skunkworks-bed-allocation.", "title": "nhsx/skunkworks-bed-allocation README", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "written_by": "makers", "quote": "is not intended for deployment in a clinical or non-clinical setting without further development and compliance with the UK Medical Device Regulations 2002." }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README, note on the allocation agents.", "title": "nhsx/skunkworks-bed-allocation README (allocation agents)", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "written_by": "makers", "quote": "The greedy allocation agent is the only agent integrated into the UI due to performance issues with the MCTS approach" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0339-source-0001", "AIBD-0339-source-0002", "AIBD-0339-source-0003", "AIBD-0339-source-0004", "AIBD-0339-source-0005" ], "role": "Existing evidence items, in their original order" }, "provenance": { "kind": "curatorial", "basis": "Stable within the fingerprinted record version; no source content or source review has been added.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "sources[].language": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "press release", "citation": "NHS Transformation Directorate, NHS AI Lab Skunkworks (2021). Improving hospital bed allocation using AI. Case study, 10 Dec 2021.", "title": "Improving hospital bed allocation using AI", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "The resulting proof of concept was then tested and reviewed by Kettering General Hospital." }, { "kind": "press release", "citation": "NHS Transformation Directorate (2021). Improving hospital bed allocation using AI, section 'What next?'.", "title": "Improving hospital bed allocation using AI (What next?)", "url": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/", "date": "2021-12-10", "written_by": "makers", "quote": "Kettering General Hospital will be working with Faculty to bid for further funding to develop and operationalise the bed allocation system." }, { "kind": "press release", "citation": "Accelerated Capability Environment, Home Office (2023). Using AI to improve patient bed allocation decisions in hospital. GOV.UK case study, 12 Oct 2023.", "title": "Using AI to improve patient bed allocation decisions in hospital", "url": "https://www.gov.uk/government/case-studies/using-ai-to-improve-patient-bed-allocation-decisions-in-hospital", "date": "2023-10-12", "written_by": "makers", "quote": "schedulers to make the final bed allocation decision" }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README. GitHub repository nhsx/skunkworks-bed-allocation.", "title": "nhsx/skunkworks-bed-allocation README", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "written_by": "makers", "quote": "is not intended for deployment in a clinical or non-clinical setting without further development and compliance with the UK Medical Device Regulations 2002." }, { "kind": "other", "citation": "NHSX / NHS AI Lab Skunkworks (n.d.). skunkworks-bed-allocation README, note on the allocation agents.", "title": "nhsx/skunkworks-bed-allocation README (allocation agents)", "url": "https://github.com/nhsx/skunkworks-bed-allocation", "written_by": "makers", "quote": "The greedy allocation agent is the only agent integrated into the UI due to performance issues with the MCTS approach" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].upstream_sources": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "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.", "account": "Kettering General Hospital, a National Health Service (NHS) foundation trust, asked the NHS AI Lab Skunkworks team (NHSX) for support exploring AI for bed management. The Skunkworks funded a 14-week project with Faculty, an applied AI supplier selected through the Home Office's Accelerated Capability Environment (ACE). The team used five years of pseudonymized patient administration data and one to two years of patient-flow data. It built a virtual hospital and a Bayesian model forecasting how many patients with given characteristics would present. It compared greedy allocation, Monte Carlo tree search and reinforcement learning for suggesting beds. Only the greedy agent was integrated into the web interface because of performance issues with the tree search. Reinforcement learning was not developed within the project. The resulting proof of concept was tested and reviewed by the hospital. A human scheduler still makes the final bed-allocation decision. It was released as open source on the NHSX GitHub pages. The README places it at Technology Readiness Level 4, not intended for deployment without further development and compliance with the UK Medical Device Regulations 2002. The NHS case study (10 December 2021) says the hospital would work with Faculty to bid for funding to develop and operationalize the system. The GOV.UK ACE case study (12 October 2023) lists potential benefits only. No quantified results and no live use are documented, so this is a general benefit. The GitHub README gives a 12-week initiative launched in May 2021, while the NHS and GOV.UK pages say 14 weeks." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "summary", "account" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].autonomy_permissions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].component_role": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].deployment_configuration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].inputs_outputs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_name": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].product_name": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "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)" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "system" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].provider": { "state": "value_present", "value": { "kind": "structured", "data": { "application_developer": "Faculty (applied AI company) with NHS AI Lab Skunkworks (NHSX) and Kettering General Hospital, through the Home Office Accelerated Capability Environment" } }, "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "developer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "taxonomy_crosswalks[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "title": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "title": "NHS AI Lab Skunkworks and Faculty build a 14-week proof-of-concept AI bed-allocation tool for Kettering General Hospital; tested and reviewed, released as open source, not deployed", "headline": "Faculty's Kettering bed tool is open-sourced but not deployed" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "title", "headline" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "139a2684abf1fbea40d45c7a776ff7f0fca3fc04be32229b5b3d2ad436b6f60e" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Deterministic content version assigned by the local migration.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Kettering General Hospital, a National Health Service (NHS) foundation trust, asked the NHS AI Lab Skunkworks team (NHSX) for support exploring AI for bed management. The Skunkworks funded a 14-week project with Faculty, an applied AI supplier selected through the Home Office's Accelerated Capability Environment (ACE). The team used five years of pseudonymized patient administration data and one to two years of patient-flow data. It built a virtual hospital and a Bayesian model forecasting how many patients with given characteristics would present. It compared greedy allocation, Monte Carlo tree search and reinforcement learning for suggesting beds. Only the greedy agent was integrated into the web interface because of performance issues with the tree search. Reinforcement learning was not developed within the project. The resulting proof of concept was tested and reviewed by the hospital. A human scheduler still makes the final bed-allocation decision. It was released as open source on the NHSX GitHub pages. The README places it at Technology Readiness Level 4, not intended for deployment without further development and compliance with the UK Medical Device Regulations 2002. The NHS case study (10 December 2021) says the hospital would work with Faculty to bid for funding to develop and operationalize the system. The GOV.UK ACE case study (12 October 2023) lists potential benefits only. No quantified results and no live use are documented, so this is a general benefit. The GitHub README gives a 12-week initiative launched in May 2021, while the NHS and GOV.UK pages say 14 weeks.", "replication": { "produced_by": [ "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" ], "must_hold": [ "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" ], "echoes": [ { "setting": "Planned bid by Kettering General Hospital with Faculty for funding to develop and operationalize the system (NHS case study, “What next?”); no later outcome read", "outcome": "unknown", "source": "https://web.archive.org/web/20231123150115/https://transform.england.nhs.uk/ai-lab/explore-all-resources/develop-ai/improving-hospital-bed-allocation-using-ai/" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" } }, "summary": { "total": 91, "addressed": 91, "known": 28, "reviewed": 0, "record_mapped": 28, "not_assessed": 63, "complete": false, "by_state": { "value_present": 28, "not_reported": 0, "unresolved": 0, "not_assessed": 63, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }