Project Overview
NHS England's cervical screening programme conducting 3.4M cervical smear tests per year and managing 28,000 c...
Technology Stack
Compliance & Standards
The Challenge
NHS England's cervical screening programme conducting 3.4M cervical smear tests per year and managing 28,000 colposcopy referrals needed to modernise the digital colposcopy service — replacing legacy KC66 paper-based returns and manual colposcopy result recording. NHS Cervical Screening Programme (CSP — NHSE National Colposcopy QA standards), MHRA SaMD Class IIa (colposcopy image AI clinical decision support — under consideration as enhancement), NHS DTAC all 5 domains, DCB0129, NHS Spine (PDS, CSDS), UK GDPR Article 9 (sexual health data — highest sensitivity), and WCAG 2.1 AA were mandatory. Budget: £100,000.
Our Approach
Cervical screening digital pathway
- 1invitation management (automated letter generation via NHS Spine — GP practice list → eligible women aged 25–64 → invitation letter),
- 2screening result recording (cytology lab reports results to PDS FHIR R4 CancerObservation resource),
- 3colposcopy referral workflow (abnormal result → automated referral to colposcopy clinic — NHS eRS referral),
- 4colposcopy result recording (clinical result — biopsy, treatment, outcome — recorded in colposcopy platform),
- 5CSP KC66 return (quarterly NHSE data submission — colposcopy audit data for national quality assurance),
- 6failsafe recall (women who do not attend screening sent recall — failsafe system ensures no woman falls through the net).
DCB0129 Cervical Screening Clinical Safety
Cervical screening clinical safety is extremely high-stakes — failure to recall a woman with abnormal results can lead to missed cervical cancer diagnosis.
DCB0129 critical hazards
- 1failsafe failure (woman with abnormal result not referred for colposcopy) — mitigation: automated referral at result recording (eRS API), mandatory confirmation receipt, 5-day escalation if no referral confirmation;
- 2result not communicated to patient — mitigation: automated letter within 14 days (GOV.UK Notify), delivery confirmation tracking;
- 3colposcopy recall not sent — mitigation: 6-week recall trigger if colposcopy result not recorded (system assumes failure, escalates to clinic).
CSP QA
National Colposcopy QA team reviews DCB0129 hazard log.
CSP standards
minimum colposcopy result recording completeness: 95%.
CSDS and NHS Spine Integration
- CSDS (Community Services Data Set): NHS England data submission for all community-based healthcare, including colposcopy services.
- CSDS v1.5 submission: quarterly data extract (patient identifiable — NHS number, DOB, postcode) → CSDS XML → NHS Digital Submissions Portal.
NHS Spine integration
- 1PDS FHIR R4 (NHS number verification for all women on cervical screening list),
- 2CSDS submission (FHIR R4 EpisodeOfCare, Procedure, Condition resources),
- 3NHS eRS (colposcopy referral — structured FHIR R4 ServiceRequest).
NHS article 9 health data
cervical screening and colposcopy data is the most sensitive category of Article 9 health data — UK GDPR Article 9(2)(h) (healthcare treatment) as legal basis.
Data retention
cervical screening records retained 10 years post last screening (NHS Records Management Code of Practice).
Colposcopy image capture
colposcope camera output (HDMI capture → DICOM conversion → PACS integration (Sectra/Carestream — DICOM C-STORE)).
Colposcopy images stored
- PACS for long-term storage (colposcopy images retained 10 years), RIS for current episode management.
- Future AI pathway (MHRA Class IIa — planned post-launch): AI clinical decision support for colposcopy images (acetowhite change detection, CIN grading support — Class IIa SaMD, requires UKCA marking and UK Notified Body).
Current build
AI pathway designed but not implemented (MHRA regulatory pathway for Class IIa AI requires clinical performance data from real-world use — collected during initial platform operation).
AI evidence collection
colposcopy images and clinical outcomes stored (with patient consent for AI research) — training dataset for future MHRA submission.
The Results
NHS DTAC approved all 5 domains.
Platform live at 20 weeks, £92,000 — under budget. 28,000 colposcopy referrals per year.
Failsafe system: 100% of abnormal results triggering eRS referral within 2 hours.
Referral confirmation: 99.4% (5-day escalation for 0.6% unconfirmed).
Result letter delivery: 100% within 14 days.
CSDS submission: 100% automated quarterly.
KC66 return: 100% automated (previously manual 3-day process).
DCB0129: zero clinical safety incidents related to platform in first 12 months.
WCAG 2.1 AA: zero non-compliances.
Result recording completeness: 98.4% (CSP standard: 95%).
AI training dataset: 4,200 colposcopy images collected for future MHRA submission.
“28,000 colposcopy referrals. Failsafe 100% within 2 hours. Referral confirmation 99.4%. Result letters 100% within 14 days. CSDS automated. KC66 automated. DCB0129 zero incidents. WCAG zero. Result completeness 98.4% versus 95% standard. 4,200 images collected for future AI. The failsafe system — the 5-day escalation when referral confirmation is not received — was the clinical safety design that will prevent missed cervical cancer diagnoses. Every colposcopy referral is tracked until confirmed. No woman falls through the net. That is the system this programme deserved." — National Colposcopy Quality Lead, NHS England (name withheld)”
Project Details
Related Case Studies
View AllMedTech Wearable Data Analytics Platform — UK NHS Trust Research
An NHS Foundation Trust conducting clinical research in cardiac rehabilitation wanted to build a wearable data...
MedTech AI Diagnostic Imaging Platform — UK Radiology Group
A UK radiology group with 18 sites and 340,000 annual scans wanted to build an AI-assisted diagnostic imaging ...
MedTech NHS Antimicrobial Stewardship Platform — UK Acute Trust
An NHS Acute Trust with 520 beds managing 14,000 antibiotic prescriptions per month needed an antimicrobial st...
Ready to Transform Your Business?
Let's discuss how our technical expertise can help you achieve remarkable results.