Dataset - Health Data Research Gateway

Bookmarks

MFT Pancreatic Cancer - Early Detection Prediction

Population Size

58,567

People

Population Size statistic card

Years

2012 - 2022

Years statistic card

Associated BioSamples

None/not available

Associated BioSamples statistic card

Geographic coverage

United Kingdom

England

Geographic coverage statistic card

Lead time

Not applicable

Lead time statistic card

Dataset

Publications using this dataset (external search)

Data Custodian

Summary

This is a carefully curated dataset of patients who have either been diagnosed with Pancreatic Cancer (PC) or are deemed high risk. Sourced from Manchester Foundation Trust systems, the dataset was curated for use in a predictive model.

DOI for dataset

https://doi.org/10.6084/m9.figshare.22094015.v1

Documentation

The dataset includes patients either diagnosed with pancreatic cancer (PC) or deemed at risk of PC. Risk factors include certain, clinician-validated features such as previous GI referrals, chronic pancreatitis diagnosis etc. The dataset includes both patient level demographic, inpatient/outpatient and laboratory data. The variables included have been carefully identified as being potentially risk factors for PC. Data has been sourced from Manchester Foundation Trust systems, and is patient level.

Dataset type

Health and disease

Dataset population size

58567

Keywords

Observations

Observed Node	Disambiguating Description	Measured Value	Measured Property	Observation Date
Persons	Number of unique subjects in dataset	58567	Count of linkable, distinct subjects in dataset	31 Oct 2025
Findings	Number of records (one record per subject)	58567	Count of findings records	31 Oct 2025

Provenance

Purpose of dataset collection

Care

Source of data extraction

EPR

Collection source setting

Secondary care - Outpatients, Secondary care - In-patients, Clinic

Patient pathway description

Secondary Care only

Image contrast

Not stated

Biological sample availability

None/not available

Structural Metadata

Details

Publishing frequency

Static

Version

1.0.0

Modified

08/10/2024

Distribution release date

29/10/2025

Citation Requirements

To inform CDSU of any publications arising from this Project Dataset and ensure CDSU and the relevant data controller responsible for initially providing data are acknowledged as data sources in all resulting reports and publications. E.g. “We acknowledge the support of the Clinical Data Science Unit, Manchester University NHS Foundation Trust for managing and supplying the pseudonymised data from the original data source.“

Coverage

Start date

04/04/2012

End date

07/09/2022

Time lag

Less than 1 week

Geographic coverage

United Kingdom, England, North West, Manchester

Maximum age range

150

Follow-up

Continuous

Accessibility

Language

Alignment with standardised data models

LOCAL

Controlled vocabulary

ICD10

Format

csv, sql

Data Access Request

Dataset pipeline status

Available

Access rights

https://research.cmft.nhs.uk/innovation-at-mft/manchester-clinical-data-science-unit

Time to dataset access

Not applicable

Access method category

Varies based on project

Access service description

MFT have both on-premise and cloud solutions for accessing data. Each application will be assessed on a case-by-case basis but th default access route is via our secure data environment analytical platform/TRE.

Jurisdiction

GB-ENG

Data use limitation

Research use only

Data use requirements

Institution-specific restrictions,Disclosure control

Data Controller

Manchester University Hospitals NHS Foundation Trust

Data Processor