A pre and post-study to compare the effect of AI-assisted radiology systems in detecting potentially cancerous lung nodules
ISRCTN | ISRCTN17337480 |
---|---|
DOI | https://doi.org/10.1186/ISRCTN17337480 |
Secondary identifying numbers | qXR-LN-NL-001 |
- Submission date
- 10/12/2024
- Registration date
- 09/01/2025
- Last edited
- 21/01/2025
- Recruitment status
- Recruiting
- Overall study status
- Ongoing
- Condition category
- Cancer
Plain English summary of protocol
Background and study aims
This study aims to assess whether artificial intelligence (AI) can improve the detection of lung nodules and early-stage lung cancer when used to analyze chest X-rays. By comparing data from before and after AI deployment, the study will investigate if AI assistance identifies more lung nodules and if these nodules are cancerous or require further follow-up (such as CT scans or biopsies).
Who can participate?
Patients and healthy volunteers aged 35 years old and over who are obtaining chest X-rays at the site
What does the study involve?
The AI system, qXR-LN v4.0, will be integrated into the hospital's radiology workflow. In the pre-deployment phase, the information on number of nodules and lung cancers detected will be collected. In the post-deployment phase, AI assistance will notify radiologists of potential nodules, which they can review and confirm. This process will help evaluate the AI’s ability to detect nodules, and track cases of lung cancer diagnosed through AI chest X-ray.
What are the possible benefits and risks of participating?
For patients, there are no direct benefits or risks as this is an observational study, meaning no additional procedures or interventions are required. The AI system's involvement does not change the patients' usual care or treatment. The benefit lies in the potential for early detection of lung cancer in the future, as successful AI detection could lead to earlier and more accurate diagnoses. This study will be conducted at multiple hospitals, primarily in the Netherlands, and radiologists and clinical researchers will oversee the AI deployment and monitor results.
Where is the study run from?
Erasmus Medical Center, Netherlands
When is the study starting and how long is it expected to run for?
September 2023 to December 2026
Who is funding the study?
The study is supported by Qure.ai, the developer of the AI software qXR-LN.
Who is the main contact?
Dr. Jacob Visser (PI), j.j.visser@erasmusmc.nl
Contact information
Public, Scientific, Principal Investigator
Department of Radiology and Nuclear Medicine, Erasmus Medical Center, Dr. Molewaterplein 40
Rotterdam
3015
Netherlands
Phone | +31 0107030949 |
---|---|
j.j.visser@erasmusmc.nl |
Study information
Study design | Multicentre ambispective pre- and post-deployment observational cohort study |
---|---|
Primary study design | Observational |
Secondary study design | Cohort study |
Study setting(s) | Medical and other records |
Study type | Diagnostic |
Participant information sheet | No participant information sheet available |
Scientific title | An ambispective pre and post-deployment observational cohort study to evaluate the yield of actionable lung nodules and lung cancer through chest X-rays using artificial intelligence |
Study acronym | APPEAL - AI |
Study objectives | 1. AI assistance can potentially help radiologists detect more lung nodule cases 2. AI assistance can potentially help in diagnosing more lung cancer cases 3. AI assistance can potentially help detect more early-stage lung cancer |
Ethics approval(s) |
Approved 19/09/2023, Medical Ethics Review Committee Erasmus MC (Postbus 2040, Rotterdam, 3000 CA, Netherlands; +31 107033625; metc@erasmusmc.nl), ref: MEC-2023-0534 |
Ethics approval additional information | This study will be conducted in the Netherlands and the AI to be used is ethically approved in this region. The participants' data is collected retrospectively, and no additional rules of conduct or actions are imposed on them, making this a non-Medical-Scientific Research with People Act (nWMO) project. The post-AI deployment is part of standard care, and the retrospective collection of data does not pose an extra burden on the patients nor does it require additional actions from them. As part of the nWMO approval decision, "exception informed consent" was granted. This study does not have any protocol-mandated procedure. The patients will be managed as per the treating physician’s judgement. |
Health condition(s) or problem(s) studied | Detection of actionable lung nodules and lung cancer |
Intervention | This is a pre-and post-deployment study. The study is observational at the patient level with no protocol-mandated procedures. A patient identified with a nodule will undergo management as per established guidelines which may include invasive procedures like biopsy or further imaging or follow-up which may extended up to two years. All patients receive the same standard of care in both periods. The AI system, qXR-LN v4.0, will be integrated into the hospital's radiology workflow. In the pre-deployment phase, the information on number of nodules and lung cancers detected will be collected. In the post-deployment phase, AI assistance will notify radiologists of potential nodules, which they can review and confirm. This process will help evaluate the AI’s ability to detect nodules, and track cases of lung cancer diagnosed through AI chest X-ray. Data collection takes place in two phases: a pre-deployment phase to establish baseline detection rates without AI, followed by a post-deployment phase with the AI in place. The total study duration is expected to span 2 years, with each phase involving data collection from around 100,000 patients. |
Intervention type | Device |
Pharmaceutical study type(s) | Not Applicable |
Phase | Not Applicable |
Drug / device / biological / vaccine name(s) | Qure AI qXR LN v4.0 device; qXR AI-based chest X-ray reporting |
Primary outcome measure | The following primary outcome measures are assessed using data collected from the Qure AI qXR LN v4.0 device: 1. Difference in actionable pulmonary nodule detection rate on chest X-rays between pre- and post-deployment periods 2. Difference in proportion of lung cancer cases diagnosed through nodule pathway between pre- and post-deployment periods |
Secondary outcome measures | The difference in the proportion of early-stage lung cancer among all lung cancer between pre and post-deployment periods assessed using data collected from the Qure AI qXR LN v4.0 device |
Overall study start date | 19/09/2023 |
Completion date | 15/12/2026 |
Eligibility
Participant type(s) | Healthy volunteer, Patient |
---|---|
Age group | Adult |
Lower age limit | 35 Years |
Sex | Both |
Target number of participants | 100000 |
Key inclusion criteria | All participants above the age of 35 years obtaining chest X-rays at the site |
Key exclusion criteria | Patients less than 35 years old and patients with known lung cancer at the time of chest X-ray |
Date of first enrolment | 09/01/2025 |
Date of final enrolment | 09/01/2026 |
Locations
Countries of recruitment
- Netherlands
Study participating centres
Rotterdam
3015 GD
Netherlands
5623 EJ
Netherlands
3079 DZ
Netherlands
Sponsor information
Industry
C/O RODI & Partner Legal Limited, 170 Edmund Street
Birmingham
B3 2HB
England
United Kingdom
Phone | +44 (0)22 4673 4311 |
---|---|
support@qure.ai |
Funders
Funder type
Industry
No information available
Results and Publications
Intention to publish date | 31/12/2026 |
---|---|
Individual participant data (IPD) Intention to share | No |
IPD sharing plan summary | Not expected to be made available |
Publication and dissemination plan | Planned publication in a peer-reviewed journal |
IPD sharing plan | The datasets generated during the current study are not expected to be made available due confidential nature of the data. |
Editorial Notes
21/01/2025: The following changes were made:
1. The recruitment start date was changed from 15/12/2024 to 09/01/2025.
2. The recruitment end date was changed from 15/12/2025 to 09/01/2026.
11/12/2024: Study's existence confirmed by the Medical Ethics Review Committee Erasmus MC.