Trial Review

Technical difficulties have been reported by some users of the search function and is being investigated by technical staff. Thank you for your patience and apologies for any inconvenience caused.

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
Trial registered on ANZCTR


Registration number
ACTRN12621000453886
Ethics application status
Approved
Date submitted
7/02/2021
Date registered
19/04/2021
Date last updated
2/03/2023
Date data sharing statement initially provided
19/04/2021
Type of registration
Prospectively registered

Titles & IDs
Public title
Parkinson’s Disease Spiral Analysis Project
Scientific title
Parkinson’s Disease Spiral Analysis Project: development of an artificial intelligence algorithm to identify 'on' and 'off' states in Parkinson's Disease
Secondary ID [1] 303376 0
None
Universal Trial Number (UTN)
Trial acronym
PD-SAP
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Parkinson's Disease 320648 0
Condition category
Condition code
Neurological 318500 318500 0 0
Parkinson's disease

Intervention/exposure
Study type
Observational
Patient registry
False
Target follow-up duration
Target follow-up type
Description of intervention(s) / exposure
Each participant will undergo a physical examination by a neurologist to determine if they are in 'on' or 'off' state. 'On' state is defined as when the patient's Parkinson's Disease symptoms are under adequate control; 'off' state is defined as a state when the symptoms are under suboptimal control. Then they will be asked to wear a smart watch with an accelerometer on their writing hand and draw a spiral.
They will be asked to do this in the 'on' and 'off' state. Each session is expected to take ~30 min maximum and can take place on the same day, or up to 1 month apart, depending on the participant's preference.. An individual's participation will be considered complete when there is one spiral from both of the 'on' and 'off' state. Multiple sessions, if a patient is deemed to be in the same state as the previous session, may be required to achieve this outcome.
The photo of the spiral, and the accelerometer data, will be entered into a machine learning algorithm to determine if this algorithm can determine whether a spiral was produced in 'on' or 'off' state.
Intervention code [1] 319685 0
Not applicable
Comparator / control treatment
Nil applicable
Control group
Uncontrolled

Outcomes
Primary outcome [1] 326455 0
The positive predictive value (PPV) for detecting 'on' state of Parkinson's Disease in participants using an artificial intelligence algorithm will be determined by comparing the rate of 'on' state participants as assessed by a neurologist (reference standard) compared to the rate of 'on' state participants assessed by analysis of a drawing assessed by the artificial intelligence algorithm
Timepoint [1] 326455 0
12 months post baseline.
Secondary outcome [1] 391544 0
The positive predictive value (PPV) for detecting 'off' state of Parkinson's Disease in participants using an artificial intelligence algorithm will be determined by comparing the rate of 'off' state participants as assessed by a neurologist (reference standard) compared to the rate of 'off' state participants assessed by analysis of a drawing assessed by the artificial intelligence algorithm
Timepoint [1] 391544 0
12 months post baseline

Eligibility
Key inclusion criteria
1. Parkinson’s Disease patients on appropriate therapy
2. Able to hold a pen and draw while wearing a wrist watch
3. Able to read, follow instructions, and communicate with others in English
4. No cognitive impairment
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Presence of any comorbidities or conditions, in the opinion of the investigator, that would preclude successful completion of the study

Study design
Purpose
Screening
Duration
Longitudinal
Selection
Defined population
Timing
Both
Statistical methods / analysis
The statistical analysis will consist of analyzing the accuracy of the algorithm. This will simply consist of checking how many spirals the algorithm identifies correctly by dividing the number of correctly identified spirals by the total number of spirals tested to obtain accuracy as percentage. There will be no interim analyses. Machine learning experts have advised that ~400 of spirals of each state would be required, and 200 from each state to validate - ie total of 1200 spiral proudction.

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
4/04/2022
Actual
2/05/2022
Date of last participant enrolment
Anticipated
Actual
Date of last data collection
Anticipated
Actual
Sample size
Target
200
Accrual to date
150
Final
Recruitment in Australia
Recruitment state(s)
NSW
Recruitment hospital [1] 18587 0
Gosford Hospital - Gosford
Recruitment postcode(s) [1] 32960 0
2250 - Gosford

Funding & Sponsors
Funding source category [1] 307789 0
Hospital
Name [1] 307789 0
Gosford Hospital
Country [1] 307789 0
Australia
Primary sponsor type
Individual
Name
Yun Hwang
Address
Department of Neurology
Gosford Hospital
Corner Racecourse Rd and Holden St
Gosford NSW 2250
Country
Australia
Secondary sponsor category [1] 308499 0
None
Name [1] 308499 0
Address [1] 308499 0
Country [1] 308499 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 307805 0
Hunter New England Human Research Ethics Committee
Ethics committee address [1] 307805 0
Hunter New England Human Research Ethics Committee
Hunter New England Local Health District
Level 3, POD, HMRI,
Lot 1 Kookaburra Circuit
New Lambton Heights NSW 2305
Ethics committee country [1] 307805 0
Australia
Date submitted for ethics approval [1] 307805 0
Approval date [1] 307805 0
17/11/2020
Ethics approval number [1] 307805 0
2020/ETH02373

Summary
Brief summary
This study attempts to harness advances in machine learning and artificial intelligence to faciliate monitoring of symptom fluctuations in Parkinson's disease. Participants will be asked to draw a spiral while wearing a smart watch with accelerometer function in both 'on' and 'off' state, based on clinical assessment. These samples will be used to train the algorithm, and an independent set of samples used for validation of the algorithm.
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 108562 0
Dr Yun Tae Hwang
Address 108562 0
Department of Neurology
Gosford Hospital
Corner Racecourse Rd and Holden St
Gosford NSW 2250
Country 108562 0
Australia
Phone 108562 0
+61243202404
Fax 108562 0
+61243203783
Email 108562 0
yun.hwang@health.nsw.gov.au
Contact person for public queries
Name 108563 0
Dr Yun Tae Hwang
Address 108563 0
Department of Neurology
Gosford Hospital
Corner Racecourse Rd and Holden St
Gosford NSW 2250
Country 108563 0
Australia
Phone 108563 0
+61243202404
Fax 108563 0
+61243203783
Email 108563 0
yun.hwang@health.nsw.gov.au
Contact person for scientific queries
Name 108564 0
Dr Yun Tae Hwang
Address 108564 0
Department of Neurology
Gosford Hospital
Corner Racecourse Rd and Holden St
Gosford NSW 2250
Country 108564 0
Australia
Phone 108564 0
+61243202404
Fax 108564 0
+61243203783
Email 108564 0
yun.hwang@health.nsw.gov.au

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
No/undecided IPD sharing reason/comment


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.