Project Overview
An NHS Foundation Trust managing two acute hospitals (combined 1,400 beds) faced persistent bed occupancy pres...
Technology Stack
Compliance & Standards
The Challenge
An NHS Foundation Trust managing two acute hospitals (combined 1,400 beds) faced persistent bed occupancy pressures — average occupancy 96.4%, regular bed waits, delayed discharges averaging 4.1 days, and ambulance offload delays. The trust needed a patient flow optimisation platform: real-time bed state visibility across both hospitals, discharge prediction, and a discharge coordination workflow for ward staff, discharge nurses, and community partners. DTAC all 5 domains, UK GDPR Article 9, and NHS DSP Toolkit were mandatory. Budget: £110,000.
Our Approach
Time Bed State Integration
EPR integration (System C Medway API): patient admission, transfer, and discharge events in real-time.
Occupancy dashboard
current occupied/available beds per ward, per specialty, per hospital — refreshed every 2 minutes.
Predicted discharges today and tomorrow
consultant ward round documented discharge expectations surfaced per ward.
Discharge Prediction ML
Python gradient boosting model trained on 3 years of patient admission data.
Features
length of stay to date, diagnosis group, age, deprivation index, primary carer status, previous admissions.
Prediction
- probability of discharge in next 24, 48, and 72 hours.
- Model recalibrated monthly on new discharge data.
Clinical caveat
displayed as "discharge likelihood" not "will be discharged" — clinical decision authority remains with clinical team.
Discharge checklist
- social care referral, transport booking, medication to take away (TTA), package of care confirmation, patient and family communication.
- Each task has a responsible owner and deadline.
Automatic escalation
tasks not completed 4 hours before predicted discharge trigger nurse coordinator alert.
Community partner portal
social care and community nursing partners have read-only view of incoming discharges for their area.
DTAC Domain 1
Clinical Safety Officer (Clinical Lead for Patient Flow) as CSO.
DCB0129 Hazard Log
highest risk identified as incorrect discharge prediction causing premature discharge — mitigated by "likelihood" display, mandatory clinical sign-off before any discharge actioned.
UK GDPR
patient flow data is Article 9 special category.
NHS basis
public task (Article 9(2)(h)).
Data minimisation
patient identifiers only visible to ward staff for that patient's ward.
The Results
Platform live at 18 weeks, £102,000 — under budget.
DTAC approved all 5 domains.
Bed occupancy: 96.4% → 93.1% (3.3 percentage point improvement — equivalent to ~46 additional available beds).
Delayed discharge duration: 4.1 days → 2.8 days average.
Ambulance offload delay incidents: reduced 41%.
Community partner discharge notice: average 6.2 hours (previously same-day at discharge).
Clinical staff satisfaction: 4.1/5.
“46 equivalent additional beds without building anything — that is what 3.3 percentage points means at our scale. The delayed discharge reduction from 4.1 to 2.8 days has had a direct patient safety impact — patients are spending less time in an acute bed waiting for community support." — Chief Operating Officer, NHS Foundation Trust (name withheld)”
Project Details
Related Case Studies
View AllNHS-Connected Mental Health App — DTAC Approved
NHS-Connected Mental Health App — DTAC Approved. A UK mental health technology company needed to build a patient-facing digital therapy support app connected to NHS syst...
Workforce Management SaaS — UK Healthcare Staffing Agency
A UK healthcare staffing agency placing 2,800 NHS-registered nurses, doctors, and allied health professionals ...
NHS Outpatient Referral System — FHIR R4 Integrated
An NHS Foundation Trust needed to replace a 2007 paper-based outpatient referral system. GPs referred patients...
Ready to Transform Your Business?
Let's discuss how our technical expertise can help you achieve remarkable results.