Providing data so computer systems can help with the early identification of lung diseases, leading to more rapid treatment and better survival rates

ISRCTN ISRCTN13720905
DOI https://doi.org/10.1186/ISRCTN13720905
IRAS number 301420
Secondary identifying numbers PID15885-A002-SP001, IRAS 301420, CPMS 51308
Submission date
03/03/2022
Registration date
07/04/2022
Last edited
05/05/2022
Recruitment status
No longer recruiting
Overall study status
Completed
Condition category
Cancer
Prospectively registered
Protocol
Statistical analysis plan
Results
Individual participant data
Record updated in last year

Plain English Summary

https://www.cancerresearchuk.org/about-cancer/find-a-clinical-trial/a-study-to-develop-and-test-a-computer-programme-to-help-to-improve-the-diagnosis-of-lung-cancer#undefined (added 05/05/2022)

Background and study aims
In the UK, lung cancer is common with a very low 5-year survival rate as most patients are diagnosed at a late stage. Early detection on a CT scan when the cancers are small and seen as a nodule has been shown to improve survival.

DART will work with NHS England’s ambitious Lung Cancer Screening programme using CT to collect clinical, CT and histology data for research aimed at improving lung cancer diagnosis and screening using artificial intelligence, AI.

If DART is successful, using artificial intelligence we will speed up the time to diagnose lung cancer whilst also identifying incidental harmless nodules on CT. DART aims to: remove the need for other investigations such as lung biopsies, making investigations safer and quicker; help pathologists diagnose lung cancer using; help patients by providing their doctors with more information on lung and heart function; improve patient selection for lung cancer screening.

DART aims to improve screening using AI, resulting in the avoidance of additional tests and biopsies which cause great patient anxiety, take time and are expensive.

DART will develop an AI algorithm for histology so that specimens from lung biopsies and resections can also be analysed in a similar fashion to CT scans.

Patients with lung cancer often have damaged lungs from smoking making surgery or radiation treatment unsafe. DART plans to develop an AI technique that can be used on all lung CT scans performed. As smoking can cause heart disease, patients screened for lung cancer often have heart disease. DART aims to use AI to see if we can identify this from their CT scans.

We will develop a specific risk model for Lung Cancer Screening selection, that outperforms published risk models that have been developed in academic institutions but are not used in clinical practice.

Who can participate?
To aid our research, it is important to gather data from as many people attending Lung Health Checks as possible. However, if you do not want your data included, now or at any time, please tell us using the contact details below

What does the study involve?
Computers will be to conduct additional analysis of scans and data from those attending lung health checks. It will not require any extra time or visits and will not interfere in any way with the standard health care.

Personal information will be kept private, but an NHS research laboratory will be able to link a patient’s your data (health records, scans, biopsies and resections) accurately.

What are the possible benefits and risks of participating?
There are no health risks to participating. We will anonymise data by removing the code before it is used by researchers so there is no link back to patients, who will never be identified in research or publications.

There are no immediate benefits to participants, but participation will contribute towards:
• If found at an early stage, lung cancer is curable
• DART will develop an Artificial Intelligence software programme that is faster and accurate to assist doctors to interpret CT scans and detect cancer
• This will speed up the time to diagnosis and reduce the numbers of additional scans and biopsies that might be needed in future.
• As smoking can cause heart disease, patients screened for lung cancer often have heart disease, and we aim to use AI to see if we can identify this from their CT scans as well.

Where is the study run from?
The study is run from the University of Oxford (UK)

When is the study starting and how long is it expected to run for?
Data will be collected from lung health checks between 1st October 2020 and 31st July 2023

Who is funding the study?
The study is funded by UK Research and Innovation

Who is the main contact?
Prof Fergus Gleeson, Professor of Radiology, University of Oxford, fergus.gleeson@oncology.ox.ac.uk

Study website

Contact information

Prof Fergus Gleeson
Principal Investigator

Department of Oncology
University of Oxford
Old Road Campus
Research Building
Oxford
OX3 7DQ
United Kingdom

ORCiD logoORCID ID 0000-0002-5121-3917
Email fergus.gleeson@oncology.ox.ac.uk

Study information

Study designRetrospective data collection
Primary study designOther
Secondary study design
Study setting(s)Community
Study typeOther
Participant information sheet https://dartlunghealth.co.uk/patients/ see Downloadable documents
Scientific titleThe integration and analysis of Data using Artificial intelligence to impRove patient outcomes with Thoracic diseases
Study acronymDART
Study hypothesisTo develop an artificial intelligence prediction model for malignancy in pulmonary nodules detected on CT scans based on nodule characteristics including histology, and patient clinical risk profiles using machine deep learning models.
Ethics approval(s)Approved 24/02/2022, West Midlands - Black Country Research Ethics Committee (The Old Chapel, Royal Standard Place, Nottingham NG1 6FS; +44 (0)207 104 8010; blackcountry.rec@hra.nhs.uk), ref: 21/WM/0278, CAG 22/CAG/0010
ConditionEarly diagnosis of lung cancer
InterventionData will be collected retrospectively from Lung Health Check centres, with patient consent. There will be no impact on patient care.
Intervention typeOther
Primary outcome measure1. Diagnosis of cancer measured by expert opinion using Targeted Lung Health Check spreadsheets and CT scans, collected from patients attending lung health checks first visit.
2. Diagnosis of cancer measured by AI model using Digital images collected from the CT scan.
Secondary outcome measures1. Diagnosis of cancer determined by expert histology opinion from resection and biopsy specimens
2. Diagnosis of cancer determined by the AI model from the digitised resection and biopsy specimens
Overall study start date01/10/2020
Overall study end date31/07/2023

Eligibility

Participant type(s)Mixed
Age groupAdult
SexBoth
Target number of participants300,000
Participant inclusion criteriaParticipants attending NHSE targeted lung health checks
Participant exclusion criteriaPatients who request to not be included in any studies as part of the NHS opt out.
Recruitment start date01/10/2020
Recruitment end date31/07/2023

Locations

Countries of recruitment

  • England
  • United Kingdom

Study participating centres

University of Oxford
Old Road Campus Research Building
Oxford
OX3 7DQ
United Kingdom
Lancashire Teaching Hospitals NHS Foundation Trust
Preston Road
Chorley
PR7 1PP
United Kingdom
Bradford Teaching Hospitals NHS Foundation Trust
Bradford
BD9 6RJ
United Kingdom
Liverpool Heart and Chest Hospital NHS Foundation Trust
Thomas Drive
Liverpool
L14 3PE
United Kingdom
Kettering General Hospital
Rothwell Road
Kettering
NN16 8UZ
United Kingdom
University Hospitals Coventry and Warwickshire (UHCW) NHS Trust
Clifford Bridge Rd
Coventry
CV2 2DX
United Kingdom
Doncaster and Bassetlaw Teaching Hospitals NHS Foundation Trust
Doncaster Royal Infirmary
Armthorpe Road
Doncaster
DN2 5LT
United Kingdom
Hull University Teaching Hospitals NHS Trust (HUTH)
Anlaby Rd
Hull
HU3 2JZ
United Kingdom
Luton and Dunstable University Hospital NHS Foundation Trust
Lewsey Rd
Luton
LU4 0DZ
United Kingdom
Royal Brompton & Harefield Clinical Group, Part of Guy’s and St Thomas’ NHS Foundation Trust
Sydney Street
London
SW3 6NP
United Kingdom
Salford Royal Foundation Trust
Stott Lane
Salford
M6 8HD
United Kingdom
University Hospital of North Staffordshire
Princes Road
Stoke-on-trent
ST4 7LN
United Kingdom
The Newcastle upon Tyne Hospitals NHS Foundation Trust
Freeman Hospital
Freeman Road
High Heaton
Newcastle upon Tyne
NE7 7DN
United Kingdom
Gateshead Health NHS Foundation Trust Laboratory
Queen Elizabeth Hospital
Sherriff Hill
Gateshead
NE9 6SX
United Kingdom
University Hospital Southampton NHS Foundation Trust
Southampton General Hospital
Tremona Road
Southampton
SO16 6YD
United Kingdom

Sponsor information

Research Governance, Ethics & Assurance Team (RGEA), University of Oxford
University/education

Joint Research Office
1st floor, Boundary Brook House
Churchill Drive
Headington
Oxford
OX3 7GB
England
United Kingdom

Email ctrg@admin.ox.ac.uk
Website https://www.ukri.org/
ROR logo "ROR" https://ror.org/001aqnf71

Funders

Funder type

Government

UK Research and Innovation
Government organisation / National government
Alternative name(s)
UKRI
Location
United Kingdom

Results and Publications

Intention to publish date30/09/2023
Individual participant data (IPD) Intention to shareYes
IPD sharing plan summaryAvailable on request
Publication and dissemination planPlanned publication in a high-impact, peer-reviewed journal
IPD sharing planDe-identified data will be shared with academic and industrial partners as approved by the CI

Study outputs

Output type Details Date created Date added Peer reviewed? Patient-facing?
HRA research summary 28/06/2023 No No

Editorial Notes

05/05/2022: Internal review.
05/05/2022: The Cancer Research UK plain English summary has been added.
20/04/2022: The ethics approval has been added.
04/03/2022: Trial's existence confirmed by the NHS HRA