A pilot study to evaluate automatic deep vein thrombosis diagnostic software
| ISRCTN | ISRCTN11069056 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN11069056 |
| IRAS number | 285274 |
| Secondary identifying numbers | IRAS 285274 |
- Submission date
- 10/05/2021
- Registration date
- 21/05/2021
- Last edited
- 27/05/2025
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Circulatory System
Plain English summary of protocol
Background and study aims
Deep vein thrombosis (DVT) is a term that describes blood clots (thrombi) that can form in the deep veins. The deep leg veins are commonly affected (such as the proximal veins: the femoral vein or the popliteal vein) or the deep veins of the pelvis. The standard approach to making a diagnosis involves an algorithm combining pre-test probability, a blood test called the D-dimer test, and the patient undergoing an ultrasound of the leg veins. Ultrasound is currently completed by a trained expert (e.g. sonographer or radiologist).
However, handheld ultrasound probes have recently become available and they have enabled ‘app-based’ ultrasonography to be performed. ThinkSono has developed software (AutoDVT software) which it is hoped has the same accuracy for diagnosing DVT as the standard ultrasound. If this study has a positive outcome, it would mean that DVT could be diagnosed at the point of care by non-experts such as nurses, junior doctors, general practitioners and other healthcare staff. By diagnosing DVT early in the clinical pathway (for example, at GP practices), the technology could reduce emergency department admissions and free up specialists to focus on other clinical tasks. These improvements could also potentially reduce the financial burden of the DVT diagnostic service on the NHS.
Who can participate?
Patients aged 18 years and over, coming for a check to see if they have a DVT and have symptoms suggesting that they need an ultrasound scan
What does the study involve?
Participants undergo two compression ultrasound scans. One is carried out by a non-radiology staff member (e.g a nurse) using AI software to guide them and another ultrasound scan will be carried out as already scheduled by a sonographer or radiologist.
What are the possible benefits and risks of participating?
This study will not benefit participants directly in the short term but it may benefit patients having an ultrasound for a DVT in the future. The results from this study will improve knowledge of how software may be able to help diagnose blood clots accurately and quickly.
Ultrasound is a very safe method of confirming a DVT or not and is used already as standard care in hospitals. There are no risks of taking part. The scan does involve some pressing on the leg but if it is painful or participants want to stop they can let the researchers know.
Where is the study run from?
Nuffield Orthopaedic Centre (UK)
When is the study starting and how long is it expected to run for?
April 2021 to June 2024
Who is funding the study?
The Wellcome Trust via ThinkSono Ltd (UK)
Who is the main contact?
1. Chris Deane (trial manager, general queries), advent@nhsbt.nhs.uk
2. Fouad Al-Noor (general and technical queries), fouad@thinksono.com
3. Dr Nicola Curry (clinical queries), nicola.curry@ouh.nhs.uk
Contact information
Public
Flat 35 Mercury House
Heathcroft
London
W53BF
United Kingdom
| Phone | +44 (0)7947998867 |
|---|---|
| fouad@thinksono.com |
Scientific
Oxford Haemophilia & Thrombosis Centre
Old Road
Headington
Oxford
OX3 7LE
United Kingdom
| Phone | +44 (0)1865 225316 |
|---|---|
| nicola.curry@ouh.nhs.uk |
Public
NHSBT Clinical Trials Unit
John Radcliffe Hospital
Headley Way
Headington
Oxford
OX3 9BQ
United Kingdom
 ORCID ID |
0000-0002-9753-3799 |
|---|---|
| Phone | +44 (0)7385 387696 |
| advent@nhsbt.nhs.uk |
Study information
| Study design | Multi-centre prospective double-blinded observational study |
|---|---|
| Primary study design | Observational |
| Secondary study design | Cohort study |
| Study setting(s) | Hospital |
| Study type | Diagnostic |
| Participant information sheet | Not available in web format, please use the contact details to request a participant information sheet |
| Scientific title | A multi-centre, prospective, double-blinded, pilot study evaluating artificial intelligence driven automatic detection of proximal deep vein thrombosis |
| Study acronym | ADVENT |
| Study objectives | Deep vein thrombosis (DVT) is a term that describes a blood clot (thrombus) that can form in the deep veins. DVT commonly affects the proximal deep venous system of the legs: i.e. femoral vein, popliteal vein or the deep veins of the pelvis. The standard approach to making a diagnosis currently involves an algorithm combining pre-test probability, D-dimer testing, and compression ultrasonography (typically a two or three-point compression exam). This study will compare the gold standard two or three-point compression ultrasound exam with an automated DVT scan guided by novel software (AutoDVT) and with AutoDVT with an additional review by a suitably qualified clinician with more than one year of experience diagnosing DVTs (e.g. sonographer or radiologist). The aim of the study is to estimate the sensitivity and specificity of the AutoDVT software and AutoDVT with an additional review by a suitably qualified clinician with more than 1 year of experience diagnosing DVTs (e.g. sonographer or radiologist) compared to two or three-point compression ultrasound exam. |
| Ethics approval(s) | Approved 03/08/2021, East of Scotland Research Ethics Service REC 2 (Ninewells Hospital & Medical School, Tayside Medical Science Centre (TASC), Residency Block, Level 3, George Pirie Way, Dundee, DD1 9SY, UK; +44 (0)1382 383871; tay.eosres@nhs.scot), ref: 21/ES/0070 |
| Health condition(s) or problem(s) studied | Deep vein thrombosis |
| Intervention | An AutoDVT software scan and remote radiology review are compared for accuracy with a clinical ultrasound scan. The study scan will not be used for diagnosis or to direct treatment. |
| Intervention type | Device |
| Pharmaceutical study type(s) | |
| Phase | Not Applicable |
| Drug / device / biological / vaccine name(s) | AutoDVT R1 Software |
| Primary outcome measure | 1. Sensitivity of AutoDVT within a treatment algorithm for the detection of a proximal DVT by non-radiology trained staff relative to two- or three-point compression ultrasound, at initial scan and 7 days 2. Sensitivity of AutoDVT within a treatment algorithm for the detection of a proximal DVT by non-radiology trained staff and remote diagnosis by a suitably qualified clinician with more than 1 year of experience diagnosing DVTs (e.g. sonographer or radiologist) retrospectively relative to two- or three-point compression ultrasound, at initial scan and 7 days |
| Secondary outcome measures | 1. Specificity of AutoDVT relative to two- or three-point compression ultrasound, at initial scan and 7 days 2. Diagnostic image quality of AutoDVT US data (using ACEP image quality scale) across all initial and 7-day scans 3. Positive and negative predictive values of AutoDVT relative to two- or three-point compression ultrasound, at initial scan and 7 days 4. Imaging failure rates (with reasons) recorded by the software across all initial and 7-day scans 5. Numbers of discrepant results (AutoDVT vs ultrasound) recorded by comparing the software and clinical diagnoses at initial and 7-day scans 6. Interoperator variability of AutoDVT results assessed using a kappa statistic for 10% of initial scans 7. Interobserver agreement in DVT diagnosis and image quality score between 5 reviewers of each scan at initial scan and 7 days 8. Numbers of eligible patients not enrolled (with reasons) recorded by the research staff at enrolment 9. Safety: number of subsequent venous thromboembolic events and/or death related to venous thromboembolism (VTE) recorded by contacting the patient and/or General Practitioner at 3 months 10. Feasibility of recording of AutoDVT scans assessed using recruitment, user feedback and scans missed at initial scan and 7 days 11. Duration of AutoDVT scans recorded by the software at initial and 7-day scans 12. Number of indeterminate and repeat scans recorded by the software at initial and 7-day scans 13. Feedback from the research nurses on ease of use of the software (PSSUQ version 3 score and qualitative feedback) provided after they have done all scanning in the project |
| Overall study start date | 01/04/2021 |
| Completion date | 30/06/2024 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Adult |
| Lower age limit | 18 Years |
| Sex | Both |
| Target number of participants | 400 |
| Key inclusion criteria | 1. The participant has the capacity to consent and consent is obtained 2. The participant is an adult (aged 18 years or older in the UK) 3. The participant has symptoms suggestive of a deep venous thrombosis (DVT) 4. The diagnostic DVT algorithm indicates that an ultrasound is needed |
| Key exclusion criteria | 1. Pregnant women at 12 weeks or more gestation 2. A d-dimer cannot be performed (e.g. due to prior anticoagulation) 3. The participant is found to have a distal DVT during the US scan (retrospective exclusion) 4. The participant has had a previous radiologically confirmed DVT in the symptomatic leg |
| Date of first enrolment | 13/12/2021 |
| Date of final enrolment | 31/03/2024 |
Locations
Countries of recruitment
- England
- United Kingdom
Study participating centres
Sheffield
S5 7AU
United Kingdom
Headington
Oxford
OX3 7LD
United Kingdom
Aylesbury
HP21 8AL
United Kingdom
London
SE5 9RS
United Kingdom
Orpington.
Telford
BR6 8ND
United Kingdom
Leicester
LE1 5WW
United Kingdom
SK2 7JE
United Kingdom
Heath Park
Cardiff
CF14 4XW
United Kingdom
Sponsor information
Hospital/treatment centre
Old Road
Headington
Oxford
OX3 7LE
England
United Kingdom
| Phone | +44 (0)300 304 7777 |
|---|---|
| media.office@ouh.nhs.uk | |
| Website | https://www.ouh.nhs.uk/ |
"ROR" |
https://ror.org/03h2bh287 |
Funders
Funder type
Research organisation
Private sector organisation / Trusts, charities, foundations (both public and private)
- Alternative name(s)
- Wellcome, WT
- Location
- United Kingdom
Results and Publications
| Intention to publish date | 31/07/2025 |
|---|---|
| Individual participant data (IPD) Intention to share | Yes |
| IPD sharing plan summary | Available on request |
| Publication and dissemination plan | Planned publication in a high-impact peer-reviewed journal. The researchers will make the study protocol available at a later date. |
| IPD sharing plan | Access to the final dataset for additional analyses will be permitted with the agreement of the Trial Steering Committee after the end of the study. General participant-level data will be held by NHS Blood and Transplant for 10 years after the end of the study (contactable on ADVENT@nhsbt.nhs.uk). Data and images collected by the AutoDVT software will be held by Thinksono (contactable on hello@thinksono.com) indefinitely but only made available for non-commercial research use. |
Study outputs
| Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
|---|---|---|---|---|---|
| Results article | 15/09/2021 | 14/12/2021 | Yes | No | |
| HRA research summary | 26/07/2023 | No | No | ||
| Other publications | 01/03/2025 | 27/05/2025 | Yes | No |
Editorial Notes
27/05/2025: Publication reference added.
03/01/2023: Cardiff & Vale University Health Board was added to the trial participating centres.
26/10/2022: The following changes were made to the trial record and the plain English summary was updated accordingly:
1. The target number of participants has been changed from 300 to 400.
2. St George’s Hospital and Churchill Hospital have been removed from the trial participating centres.
3. Nuffield Orthopaedic Centre, Stoke Mandeville Hospital, King’s College Hospital, Princess Royal Hospital, Leicester Royal Infirmary and Stepping Hill Hospital have been added to the trial participating centres.
23/08/2022: The following changes were made to the trial record:
1. The recruitment end date was changed from 31/03/2023 to 31/03/2024.
2. The overall end date was changed from 30/06/2023 to 30/06/2024
3. The intention to publish date was changed from 31/07/2024 to 31/07/2025.
4. The plain English summary was updated to reflect these changes.
19/08/2022: The following changes have been made:
1. The recruitment end date has been changed from 01/08/2022 to 31/03/2023.
2. The overall trial end date has been changed from 01/11/2022 to 30/06/2023 and the plain English summary updated accordingly.
3. The intention to publish date has been changed from 01/12/2023 to 31/07/2024.
21/04/2022: The following changes have been made:
1. The recruitment end date has been changed from 01/04/2022 to 01/08/2022.
2. The overall trial end date has been changed from 01/08/2022 to 01/11/2022 and the plain English summary has been updated to reflect this change.
3. The intention to publish date has been changed from 01/06/2023 to 01/12/2023.
4. Wales has been added to the countries of recruitment.
5. The total final enrolment number 124 has been removed.
6. A study contact has been added and the plain English summary has been updated to reflect this change.
21/12/2021: The following changes were made to the trial record:
1. The recruitment start date was changed from 01/09/2021 to 13/12/2021.
2. The recruitment end date was changed from 31/03/2022 to 01/04/2022.
3. The overall end date was changed from 01/07/2022 to 01/08/2022.
4. The plain English summary was updated to reflect these changes.
14/12/2021: Publication reference and total final enrolment added.
13/12/2021: The recruitment end date was changed from 01/12/2021 to 31/03/2022. Ethics approval details added.
19/07/2021: The following changes were made to the trial record:
1. The recruitment start date was changed from 01/07/2021 to 01/09/2021.
2. The recruitment end date was changed from 01/10/2021 to 01/12/2021.
3. Ethics details weer added.
11/05/2021: Trial's existence confirmed by the Wellcome Trust.
