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
ACTRN12623000209695
Ethics application status
Approved
Date submitted
12/02/2023
Date registered
27/02/2023
Date last updated
23/06/2024
Date data sharing statement initially provided
27/02/2023
Type of registration
Prospectively registered

Titles & IDs
Public title
PERsonalised Selection Of medication for Newly diagnosed Adult epiLepsy - the PERSONAL Trial
Scientific title
Effectiveness of a machine learning model for personalised drug selection in newly diagnosed epilepsy: a randomised controlled trial
Secondary ID [1] 308948 0
None
Universal Trial Number (UTN)
Trial acronym
PERSONAL
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Epilepsy
 328982 0
Condition category
Condition code
Neurological 325966 325966 0 0
Epilepsy

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
A machine learning based clinical decision support software (CDSS) to assist the neurologist in recommending the initial anti-seizure medication prescription for newly diagnosed epilepsy.
The CDSS has been designed specifically for use in this study. The CDSS functions through input of 16 baseline clinical factors by the neurologist including patient demographics, medical history, family history, epilepsy risk factors, number of pre-treatment seizures, EEG results and MRI results. It also uses the input of deidentified report text from a routine EEG and brain MRI report. The model will provide a recommendation of a single anti-seizure medication with which the participant has the highest probability of attaining seizure freedom.
Training required to utilise the model will be provided by the main site study coordinator in a single remote session taking approximately 30 minutes. This training will detail what is required to access the data entry point for the model, the format of the data required and how the recommendation will be displayed.
It is anticipated that it will take approximately 15 minutes per participant to input the data and receive the recommendation from the program.
Data entry for the model and the recommendation produced are intrinsically tied to the study REDCap database which is updated anytime the model is utilised. This database has auditing tools for tracking changes made to entries and as such can be used to monitor model utilisation.
Intervention code [1] 325412 0
Treatment: Devices
Comparator / control treatment
Control group is usual care with anti-seizure prescription made by the neurologist only using their clinical judgement.
Control group
Active

Outcomes
Primary outcome [1] 333810 0
Proportion of patients who are seizure-free while taking the first anti-seizure medication assessed through use of a participant seizure diary that is reviewed at each of the epilepsy clinic visits.
Timepoint [1] 333810 0
Assessed for any seizures at each of the study site visits up to 52-weeks post intervention commencement
Secondary outcome [1] 418374 0
Treatment failure as reported by the neurologist while reviewing the participant at each of the study site visits.
Timepoint [1] 418374 0
Time to stop the initial anti-seizure medication due to inadequate seizure control or intolerable side-effects, or both, or the addition of another anti-seizure medication, whichever is earliest.
Secondary outcome [2] 418375 0
Seizures
Timepoint [2] 418375 0
Review of seizure diary at baseline, 8 weeks, 16 weeks, 28 weeks, 40 weeks and 52 weeks post intervention commencement.
Secondary outcome [3] 418415 0
Direct healthcare costs
Timepoint [3] 418415 0
Review of patient managed cost diary at 28-weeks and 52-weeks post intervention commencement
Secondary outcome [4] 418416 0
Indirect healthcare costs measured in terms of productivity loss
Timepoint [4] 418416 0
Work Productivity and Activity Impairment - General Health questionnaire conducted at baseline, 28 weeks and 52 weeks post intervention commencement.
Secondary outcome [5] 418417 0
Depression
Timepoint [5] 418417 0
Hospital Anxiety and Depression Scale questionnaire conducted at baseline, 28 weeks and 52 weeks post intervention commencement.
Secondary outcome [6] 418418 0
Quality of life
Timepoint [6] 418418 0
EQ-5L conducted at baseline, 28 weeks and 52 weeks post intervention commencement.
Secondary outcome [7] 418419 0
Clinical acceptance
Timepoint [7] 418419 0
Review of Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) conducted prior to trial commencement and at trial completion as a study-specific questionnaire distributed to participants and neurologists.
Secondary outcome [8] 418701 0
Anxiety
Timepoint [8] 418701 0
Hospital Anxiety and Depression Scale questionnaire conducted at baseline, 28 weeks and 52 weeks post intervention commencement.
Secondary outcome [9] 418702 0
Quality of life
Timepoint [9] 418702 0
Quality of Life in Epilepsy Inventory-31 conducted at baseline, 28 weeks and 52 weeks post intervention commencement.

Eligibility
Key inclusion criteria
- Diagnosis of epilepsy consistent with International League against Epilepsy (ILAE) criteria, defined as either:
(1) at least two seizures within the past 12 months,
or (2) one seizure within the past 6 months and epileptiform discharges on electroencephalography (EEG), or presence of epileptogenic lesion on computed tomography (CT) or magnetic resonance imaging (MRI)
- EEG and MRI brain done with 6 months prior to randomisation (MRI can be substituted with epileptogenic lesion shown on CT)
- Either naive to anti-seizure medication (ASM) treatment or has been treated with a single ASM for 14 days or less before randomisation
Minimum age
18 Years
Maximum age
65 Years
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
- Previously treated epilepsy or current use of ASM for any reason for more than 14 days
- Pregnant or breast-feeding
- Current substance abuse disorder that may affect treatment adherence or response
- Unable/failed to undergo EEG or brain CT or MRI due to contraindication
- Patient with psychogenic non-epileptic seizures
- Patients with progressive central nervous system disease, series hepatic or renal disease, or terminal cancer that would affect the assessment of response to ASMs

Study design
Purpose of the study
Treatment
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Allocation was not concealed
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Individual randomisation centralised and in blocks that are stratified by seizure type (focal vs. generalised onset) and site.
Masking / blinding
Blinded (masking used)
Who is / are masked / blinded?
The people receiving the treatment/s

The people assessing the outcomes
Intervention assignment
Parallel
Other design features
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis
• Cochran-Mantel-Haenszel test stratified by centre to compare 1-year seizure free rate; retention rate of initial treatment at 1-year and proportion of patients with clinically meaningful QoL improvement
• Cox regression to assess time to treatment failure and time to first seizure after treatment initiation
• Calculation of model sensitivity. Specificity and AUC using a probability threshold of 0.55 to classify treatment failure/success
• Calculation of quality adjusted life years (QALYs) using utility score indices from EQ-5D-5L heath states and overall QOLIE-31 score
• Calculation of 1-year seizure free-rate
• Cost differences and effect differences for 10,000 bootstrap draws from trial dataset over 1-year time horizon (possible extension if trial results demonstrate increase in seizure-free rate and quality of life, or reduction in costs)
• Plotted on a cost-effectiveness plane and cost-effectiveness acceptability curve
• Assessment of precision, sensitivity and scenario analysis
• Mixed method process evaluation to examine:
o Neurologist decision to enrol
o Neurologist decision to prescribe ML model recommended ASM
• Iterative qualitative interview of minimum 25% of neurologists and epilepsy patients to review acceptance of ML recommended ASM

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
1/08/2023
Actual
2/02/2024
Date of last participant enrolment
Anticipated
1/08/2025
Actual
Date of last data collection
Anticipated
1/09/2026
Actual
Sample size
Target
234
Accrual to date
1
Final
Recruitment in Australia
Recruitment state(s)
NSW,QLD,SA,WA,VIC
Recruitment hospital [1] 24005 0
The Alfred - Melbourne
Recruitment hospital [2] 24006 0
Royal Melbourne Hospital - City campus - Parkville
Recruitment hospital [3] 24007 0
Austin Health - Austin Hospital - Heidelberg
Recruitment hospital [4] 24008 0
Box Hill Hospital - Box Hill
Recruitment hospital [5] 24009 0
Monash Medical Centre - Clayton campus - Clayton
Recruitment hospital [6] 24010 0
Royal Brisbane & Womens Hospital - Herston
Recruitment hospital [7] 24011 0
Royal Perth Hospital - Perth
Recruitment hospital [8] 24012 0
Royal Prince Alfred Hospital - Camperdown
Recruitment hospital [9] 24013 0
Prince of Wales Hospital - Randwick
Recruitment hospital [10] 24014 0
Westmead Hospital - Westmead
Recruitment hospital [11] 24016 0
The Royal Adelaide Hospital - Adelaide
Recruitment hospital [12] 24017 0
The Queen Elizabeth Hospital - Woodville
Recruitment hospital [13] 24018 0
Royal North Shore Hospital - St Leonards
Recruitment postcode(s) [1] 39500 0
2031 - Randwick
Recruitment postcode(s) [2] 39499 0
2050 - Camperdown
Recruitment postcode(s) [3] 39505 0
2065 - St Leonards
Recruitment postcode(s) [4] 39501 0
2145 - Westmead
Recruitment postcode(s) [5] 39492 0
3004 - Melbourne
Recruitment postcode(s) [6] 39493 0
3050 - Parkville
Recruitment postcode(s) [7] 39494 0
3084 - Heidelberg
Recruitment postcode(s) [8] 39495 0
3128 - Box Hill
Recruitment postcode(s) [9] 39496 0
3168 - Clayton
Recruitment postcode(s) [10] 39497 0
4029 - Herston
Recruitment postcode(s) [11] 39503 0
5000 - Adelaide
Recruitment postcode(s) [12] 39504 0
5011 - Woodville
Recruitment postcode(s) [13] 39498 0
6000 - Perth

Funding & Sponsors
Funding source category [1] 313160 0
Government body
Name [1] 313160 0
National Health and Medicine Research Council
Country [1] 313160 0
Australia
Primary sponsor type
University
Name
Monash University
Address
Wellington Road
Clayton VIC 3800
Country
Australia
Secondary sponsor category [1] 314891 0
None
Name [1] 314891 0
Address [1] 314891 0
Country [1] 314891 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 312403 0
Alfred Hospital Research Committee
Ethics committee address [1] 312403 0
The Alfred,
55 Commercial Rd,
Melbourne,
VIC 3004
Ethics committee country [1] 312403 0
Australia
Date submitted for ethics approval [1] 312403 0
01/03/2023
Approval date [1] 312403 0
12/05/2023
Ethics approval number [1] 312403 0

Summary
Brief summary
To establish the (1) effectiveness, (2) cost-effectiveness and (3) acceptability of our machine learning (ML) model compared to usual care in selecting the first anti-seizure medication (ASM).
Hypothesis: (1) seizure-free rate at 1 year of treatment with the first ASM will be higher in the machine learning group.
(2) quality of life, depression and anxiety will improve more in the ML group, and ML model will be more cost-effective.
(3) ML model will be acceptable to patients and clinicians.
This is a multicentre randomised controlled trial (RCT) across all six states of Australia. Adults will be randomised 1:1 to ML Group (ASM recommended by the ML model) or the UC Group (ASM selected by the neurologist) and followed for 12 months. A sample size of 234 (including 10% dropout) participants will allow for measure of a minimum absolute difference of 20% in 1-year seizure-free rate on the first ASM between the study group (55% ML vs. 35% UC).
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 124534 0
Prof Patrick Kwan
Address 124534 0
Monash University
Central Clinical School
99 Commercial Road
Melbourne, VIC 3004
Country 124534 0
Australia
Phone 124534 0
+61 3 90762552
Fax 124534 0
Email 124534 0
patrick.kwan@monash.edu
Contact person for public queries
Name 124535 0
Mr Daniel Thom
Address 124535 0
Monash University
Central Clinical School
99 Commercial Rd,
Melbourne, VIC 3004
Country 124535 0
Australia
Phone 124535 0
+61 450807412
Fax 124535 0
Email 124535 0
daniel.thom@monash.edu
Contact person for scientific queries
Name 124536 0
Prof Patrick Kwan
Address 124536 0
Monash University
Central Clinical School
99 Commercial Road
Melbourne, VIC 3004
Country 124536 0
Australia
Phone 124536 0
+61 3 90762552
Fax 124536 0
Email 124536 0
patrick.kwan@monash.edu

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.