Can we use artificial intelligence tools for automatic analysis of bone marrow samples?
| ISRCTN | ISRCTN10382623 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN10382623 |
| Secondary identifying numbers | v2.0 |
- Submission date
- 24/11/2020
- Registration date
- 11/12/2020
- Last edited
- 13/04/2022
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Other
Plain English summary of protocol
Background and study aims
Optical microscopy remains the gold standard technique for diagnosing several tens of pathologies by manually reviewing samples under a microscope. Microscopic examination and classification of cells that form blood cells is a critical step for the diagnosis of blood diseases. However, it is a laborious, time-consuming technique and its results are subject to the expert examining the sample. Bone marrow aspiration (BMA) biopsies are carried out in order to diagnose many blood diseases, such as leukaemia.
This study aims to prove that the proposed digital solution will reduce time, costs and distances of microscopy diagnosis. To do so, we are generating a correctly annotated database that can be used to train Artificial Intelligence models that will help in blood disease diagnosis.
Who can participate?
Subjects with suspected hematological diseases attending 12 Octubre Hospital for a BMA procedure who are willing to provide a bone marrow sample. Also, professional hematologists who are expert at analyzing the bone marrow samples will participate.
What does the study involve?
Patients will provide a bone marrow sample that will be analysed using the AI system and also by a number of experts. The agreement between the expert analysis will be measured. Also the experts will fill in questionnaires assessing their satisfaction with the AI system.
What are the possible benefits and risks of participating?
None
Where is the study run from?
Hospital Universitario 12 de Octubre (Spain)
When is the study starting and how long is it expected to run for?
November 2020 to May 2022
Who is funding the study?
European Union Horizon 2020
Who is the main contact?
Dr María Linares (scientific), mlinares@ucm.es
Elisa Álamo García-Donas (public), elisa@spotlab.org
Contact information
Scientific
Paseo de Juan XXIII, 36B
Madrid
28040
Spain
 ORCID ID |
0000-0003-3180-6560 |
|---|---|
| Phone | +34 686598450 |
| mlinares@ucm.es |
Public
Paseo de Juan XXIII, 36B
Madrid
28040
Spain
| Phone | +34 675574488 |
|---|---|
| elisa@spotlab.org |
Study information
| Study design | Single center observational |
|---|---|
| Primary study design | Observational |
| Secondary study design | Cross sectional study |
| Study setting(s) | Hospital |
| Study type | Diagnostic |
| Participant information sheet | See additional file (in Spanish) |
| Scientific title | Evaluation of a digital ecosystem leveraging mobile technology and artificial intelligence for digitalization and remote analysis of bone marrow samples |
| Study acronym | MEDUL-AI |
| Study objectives | The proposed system will convert the current microscopes into digital microscopes connected to a comprehensive cloud platform that will enable images of BMA samples to be archived securely for remote review and clinical management. The possibility of a standardized digitalization of microscopy smears dramatically enhances diagnosis capabilities, as it enables remote diagnosis, second clinical opinion consultations, and helps to achieve automatization of the procedure as it serves as a way of gathering data to develop artificial intelligence tools that will ease the diagnosis process. |
| Ethics approval(s) | Approved 12/11/2020 Ethics Committee of Clinical Research Hospital Universitario 12 de Octubre (Av. de Córdoba s/n 28041 Madrid, Spain; +34 91 7792613; maria.ugalde@salud.madrid.org), ref: CEIm: 20/430 |
| Health condition(s) or problem(s) studied | Training of convolutional neural network algorithms for identification and counting of cellular lineages and specific cell types of bone marrow |
| Intervention | This is a one-centre, observational study to evaluate benefits of digitalization of collected BM samples in Hospital Universitario 12 Octubre from patients with suspected hematological disease. Generated data will be used to train convolutional neural network algorithms for identification and counting of cellular lineages and specific cell types of bone marrow. The samples will belong to patients visiting the hematology outpatient clinic for a BMA procedure at Hospital Universitario 12 Octubre (Madrid). The execution of the study consists of 2 phases: Phase 1: Digitalization of routine procedure for BMA analysis of Hospital 12 de Octubre, and generation of BMA tagged image database for AI algorithm development. Phase 2: Integration and evaluation of AI model as a tool for assisting hematologists in cell counting of BMA samples. |
| Intervention type | Device |
| Pharmaceutical study type(s) | |
| Phase | Not Applicable |
| Drug / device / biological / vaccine name(s) | |
| Primary outcome measure | 1. Number of samples analysed by web platform (TeleSpot) and analysis time per sample 2. Professionals' satisfaction measured with the new system measured by a usability report based on the results from a system usability scale (SUS) and AdaptaSpot Usability Questionnaire evaluating the remote analysis process. The SUS and the product questionnaires are completed every three months during the length of the study |
| Secondary outcome measures | 1. Number of digitized bone marrow aspirate images correctly marked and tagged 2. Accuracy of the AI algorithm developed and the % of agreement among experts and AI algorithm. Cell-type classification performance will be tested by assessing the prediction quality of the algorithm in the validation set compared to the ground truth annotated by the specialist during the labelling phase. |
| Overall study start date | 12/11/2020 |
| Completion date | 30/05/2022 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Adult |
| Sex | Both |
| Target number of participants | Assuming the hospital performs 25 BMA procedures a week, and as the data collection period is 10 months long, around 1,000 BMA samples will be eligible to participate in the study. We expect to digitize at least 150 BMA samples during the whole study |
| Key inclusion criteria | Patients: 1. Suspected hematological disease 2. Signed informed consent Bone marrow samples: 1. Good quality BMA sample (with proper staining and lump to provide sufficient quality and quantity) Professionals/experts: 1. Sanitary professionals of the National Health System (Doctors, Cytologists) working at Hematology Department of the Hospital Universitario 12 Octubre with microscopy experience on hematological diseases |
| Key exclusion criteria | Patients: 1. Individuals unwilling to participate in the study 2. Unspecified reasons that, in the opinion of the investigator or sponsor, make the subject unsuitable for enrollment Bone marrow samples: 1. BMA samples that do not have a good quality stain 2. BMA samples with insufficient lump |
| Date of first enrolment | 17/05/2021 |
| Date of final enrolment | 31/03/2022 |
Locations
Countries of recruitment
- Spain
Study participating centres
Madrid
28041
Spain
Madrid
28040
Spain
Sponsor information
Industry
Paseo de Juan XXIII, 36B
Madrid
28040
Spain
| Phone | +34 916256927 |
|---|---|
| elisa@spotlab.org | |
| Website | http://www.spotlab.org |
Funders
Funder type
Government
Government organisation / National government
- Alternative name(s)
- EU Framework Programme for Research and Innovation, Horizon 2020 - Research and Innovation Framework Programme, European Union Framework Programme for Research and Innovation
Results and Publications
| Intention to publish date | 01/05/2023 |
|---|---|
| Individual participant data (IPD) Intention to share | No |
| IPD sharing plan summary | Data sharing statement to be made available at a later date |
| Publication and dissemination plan | Any public disclosure including press releases, professional meetings, written publications, oral presentations, marketing purposes or similar shall be subject to the mutual approval of the Parties, and approval shall not be unreasonably withheld or delayed. Any written disclosure will be sent to the Parties within 20 days prior of its publication for review. The results will be made public within 24 months of reaching the end of the study. The end of the study is the time point at which the last data items are to be reported, or after the outcome data are sufficiently mature for analysis, as defined in the section on Sample Size, Accrual Rate and Study Duration. If a report is to be published in a peer-reviewed journal, that initial release may be an abstract that meets the requirements of the International Committee of Medical Journal Editors. A full report of the outcomes should be made public no later than three (3) years after the end of the study. |
| IPD sharing plan | The current data sharing plans for this study are unknown and will be available at a later date. |
Study outputs
| Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
|---|---|---|---|---|---|
| Basic results | 13/04/2022 | 13/04/2022 | No | No |
Additional files
Editorial Notes
13/04/2022: A basic results summary has been uploaded.
07/10/2021: The following changes were made to the trial record:
1. The recruitment start date was changed from 01/12/2020 to 17/05/2021.
2. The recruitment end date was changed from 31/10/2021 to 31/03/2022.
3. The overall start date was changed from 01/09/2020 to 12/11/2020.
4. The overall end date was changed from 31/12/2021 to 30/05/2022.
5. The intention to publish date was changed from 01/12/2022 to 01/05/2023.
6. The target number of participants was changed from 1000 to 150
7. The plain English summary was updated to reflect these changes.
25/11/2020: Trial’s existence confirmed by Hospital Universitario 12 de Octubre.
