Please note that the copy function is not enabled for this field.
If you wish to
modify
existing outcomes, please copy and paste the current outcome text into the Update field.
LOGIN
CREATE ACCOUNT
LOGIN
CREATE ACCOUNT
MY TRIALS
REGISTER TRIAL
FAQs
HINTS AND TIPS
DEFINITIONS
Trial Review
The ANZCTR website will be unavailable from 1pm until 3pm (AEDT) on Wednesday the 30th of October for website maintenance. Please be sure to log out of the system in order to avoid any loss of data.
The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this
information for consumers
Download to PDF
Trial registered on ANZCTR
Registration number
ACTRN12624000135516
Ethics application status
Approved
Date submitted
19/12/2023
Date registered
14/02/2024
Date last updated
14/02/2024
Date data sharing statement initially provided
14/02/2024
Type of registration
Prospectively registered
Titles & IDs
Public title
Integration of Cloud Based Artificial Intelligence Assisted Medical Image and Clinical Data Analysis into Stroke Patient Workflows
Query!
Scientific title
Integration of Cloud Based Artificial Intelligence Assisted Medical Image and Clinical Data Analysis into Stroke Patient Workflows
Query!
Secondary ID [1]
311215
0
Nil Known
Query!
Universal Trial Number (UTN)
Query!
Trial acronym
Cloud AI
Query!
Linked study record
Query!
Health condition
Health condition(s) or problem(s) studied:
Stroke
332406
0
Query!
Condition category
Condition code
Stroke
329107
329107
0
0
Query!
Haemorrhagic
Query!
Stroke
329108
329108
0
0
Query!
Ischaemic
Query!
Intervention/exposure
Study type
Observational
Query!
Patient registry
False
Query!
Target follow-up duration
Query!
Target follow-up type
Query!
Description of intervention(s) / exposure
Develop Artificial Intelligence (AI) Based tools for automatic brain imaging lesion segmentation and measurement. The AI software is integrated into the current medical imaging software used in NSW Health. All radiological images from adult stroke patients will be labelled by the AI software prior to the report formulation to estimate lesion sizes in the acute stroke phase. The images are collected at hospital presentation, 24 hours after admission and on an as-needed basis. Both hemorrhagic and ischemic strokes will be included. All images are collected as part of standard of care at the discretion of the treating medical team. This is an observational study and therefore nothing is required of participants, including follow-up. No blood tests, additional radiological imaging or clinical interventions are required as part of this observational study. The AI software is trained by a neurologist and will be integrated into the radiological imaging report formulated by a radiologist.
Query!
Intervention code [1]
327673
0
Diagnosis / Prognosis
Query!
Comparator / control treatment
No control group
Query!
Control group
Uncontrolled
Query!
Outcomes
Primary outcome [1]
336925
0
Specificity of measurement of lesion volumes by a AI tool
Query!
Assessment method [1]
336925
0
Results generated by the AI tool will be included in the radiological imaging viewing platform used by NSW Health. Clinicians will view brain images and make assessments as they already do now with the added functionality of automated brain lesion identification and quantification. Clinicians will improve accuracy by approving or rejecting the label. The re-labelled images will be used to continuously train the AI model.
Query!
Timepoint [1]
336925
0
7 days post hospital presentation
Query!
Secondary outcome [1]
430176
0
Accuracy of patient outcome prediction
Query!
Assessment method [1]
430176
0
The labelled images will be combined with an AI outcome prediction model. The model will be continuously trained using outcomes at 90-days combined with the predicted lesion volume. Validated stroke severity scores, physiological variables (blood pressure, past medical history and medications), and basic blood pathology data will also be utilized in the predictive model. These are routinely collected as part of normal clinical workflow and will be sourced from medical records and radiological imaging data.
Query!
Timepoint [1]
430176
0
90 days post hospital presentation
Query!
Eligibility
Key inclusion criteria
Patients assessed for possible acute stroke
Query!
Minimum age
18
Years
Query!
Query!
Maximum age
No limit
Query!
Query!
Sex
Both males and females
Query!
Can healthy volunteers participate?
No
Query!
Key exclusion criteria
Patients without acute stroke imaging data
Query!
Study design
Purpose
Screening
Query!
Duration
Query!
Selection
Query!
Timing
Prospective
Query!
Statistical methods / analysis
Query!
Recruitment
Recruitment status
Not yet recruiting
Query!
Date of first participant enrolment
Anticipated
4/03/2024
Query!
Actual
Query!
Date of last participant enrolment
Anticipated
5/03/2029
Query!
Actual
Query!
Date of last data collection
Anticipated
5/03/2029
Query!
Actual
Query!
Sample size
Target
5000
Query!
Accrual to date
Query!
Final
Query!
Recruitment in Australia
Recruitment state(s)
NSW
Query!
Recruitment hospital [1]
25955
0
Prince of Wales Hospital - Randwick
Query!
Recruitment postcode(s) [1]
41790
0
2031 - Randwick
Query!
Funding & Sponsors
Funding source category [1]
315475
0
Government body
Query!
Name [1]
315475
0
National Health and Medical Research Council (NHMRC)
Query!
Address [1]
315475
0
16 Marcus Clarke St CANBERRA ACT 2601
Query!
Country [1]
315475
0
Australia
Query!
Primary sponsor type
Individual
Query!
Name
Professor Ken Butcher
Query!
Address
Prince of Wales Hospital 320-346 Barker St, Randwick NSW 2031
Query!
Country
Australia
Query!
Secondary sponsor category [1]
317546
0
None
Query!
Name [1]
317546
0
Query!
Address [1]
317546
0
Query!
Country [1]
317546
0
Query!
Ethics approval
Ethics application status
Approved
Query!
Ethics committee name [1]
314384
0
South Eastern Sydney Local Health District Human Research Ethics Committee
Query!
Ethics committee address [1]
314384
0
District Executive Unit, Level 4, The Sutherland Hospital & Community Health Service, Cnr Kingsway and Kareena Road, Caringbah NSW 2229
Query!
Ethics committee country [1]
314384
0
Australia
Query!
Date submitted for ethics approval [1]
314384
0
18/11/2022
Query!
Approval date [1]
314384
0
20/02/2023
Query!
Ethics approval number [1]
314384
0
2022/ETH02428
Query!
Summary
Brief summary
The aim is to use Artificial Intelligence based tools for automated measurement of lesions/areas of ischemia in stroke patients. This data will be used for patient outcome prediction.
Query!
Trial website
Query!
Trial related presentations / publications
Query!
Public notes
Query!
Contacts
Principal investigator
Name
131386
0
Prof Ken Butcher
Query!
Address
131386
0
Prince of Wales Hospital 320-346 Barker Street, Randwick NSW 2031
Query!
Country
131386
0
Australia
Query!
Phone
131386
0
+61 29382 8891
Query!
Fax
131386
0
Query!
Email
131386
0
[email protected]
Query!
Contact person for public queries
Name
131387
0
Ken Butcher
Query!
Address
131387
0
Prince of Wales Hospital 320-346 Barker Street, Randwick NSW 2031
Query!
Country
131387
0
Australia
Query!
Phone
131387
0
+61 29382 8891
Query!
Fax
131387
0
Query!
Email
131387
0
[email protected]
Query!
Contact person for scientific queries
Name
131388
0
Ken Butcher
Query!
Address
131388
0
Prince of Wales Hospital 320-346 Barker Street, Randwick NSW 2031
Query!
Country
131388
0
Australia
Query!
Phone
131388
0
+61 2 9382 8891
Query!
Fax
131388
0
Query!
Email
131388
0
[email protected]
Query!
Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
Query!
No/undecided IPD sharing reason/comment
Query!
What supporting documents are/will be available?
No Supporting Document Provided
Results publications and other study-related documents
Documents added manually
No documents have been uploaded by study researchers.
Documents added automatically
No additional documents have been identified.
Download to PDF