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
ACTRN12625000881437
Ethics application status
Approved
Date submitted
13/06/2025
Date registered
13/08/2025
Date last updated
13/08/2025
Date data sharing statement initially provided
13/08/2025
Type of registration
Retrospectively registered

Titles & IDs
Public title
Collection of epilepsy anti-seizure medication response information for artificial intelligence research
Scientific title
Development of a validated data lake of multimodal epilepsy cohort variables for artificial intelligence research
Secondary ID [1] 314394 0
None
Universal Trial Number (UTN)
Trial acronym
EpiCFAIR
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Epilepsy 337400 0
Condition category
Condition code
Neurological 333778 333778 0 0
Epilepsy

Intervention/exposure
Study type
Observational
Patient registry
False
Target follow-up duration
Target follow-up type
Description of intervention(s) / exposure
This study involves the collection of retrospective outcome information for new diagnosis epilepsy patients who have for a minimum of 1-year been taking their clinically prescribed initial anti-seizure medication regimen. There is no active involvement of participants in this study, as they will not be required to complete questionnaires or physical assessments, all data collected will be from from existent medical records including: changes to anti-seizure medication regimen (cessation of regimen or commencement of substitution or combination regimen), pre-treatment clinical factors including: sex, age, history of epilepsy related comorbidities, number of pre-treatment seizure, age of commencement of treatment and commencement of seizures. No limit has been placed on the period of post-prescription observation, only a minimum of 1-year to meet assessment of seizure freedom requirements.
Intervention code [1] 331004 0
Diagnosis / Prognosis
Comparator / control treatment
No control group
Control group
Uncontrolled

Outcomes
Primary outcome [1] 341363 0
Seizure freedom
Timepoint [1] 341363 0
Time to first seizure or 12 months of seizure freedom, whichever is earliest
Secondary outcome [1] 448725 0
Time to treatment failure
Timepoint [1] 448725 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. For maximum of 12 months post commencement of anti-seizure medication.

Eligibility
Key inclusion criteria
Diagnosis of epilepsy consistent with International League Against Epilepsy Criteria, defined as either:
- At least two seizures within the past 12 months before commencing their first ASM,
or
- One seizure within the past 6 months before commencing their first ASM and
epileptiform discharges on electroencephalography (EEG), or presence of
epileptogenic lesion on computed tomography (CT) or magnetic resonance imaging
(MRI)

Initiation of ASM therapy at 2 years or older

Minimum 1-year of follow-up post ASM treatment commencement
Minimum age
2 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Consistently poor adherence to the prescribed ASM treatment

Diagnosed with functional seizures or mixed epileptic and functional seizures

Study design
Purpose
Duration
Selection
Timing
Statistical methods / analysis
Assessment of both clinical characteristics and ASM prescription pattern variability will be undertaken using both internal and external cohort analysis.
The internal cohort analysis will evaluate the frequency of individual clinical variables over time within a given cohort in addition to the frequency of individual ASM prescriptions over time.
The external analysis will compare the findings of the internal analysis between cohorts to assess both geographic and temporal differences in the collected data.
The ability of the ML model to predict treatment success with the prescribed ASM regimens will be evaluated with a series of metrics, including sensitivity, specificity, accuracy, and AUC.
Sensitivity (true positive rate) and specificity (true negative rate) reflect the ability of the model to make true positive and true negative predictions, respectively. False positive rate (1-specificity) represents the rate of misclassification of positive outcomes (i.e., treatment success).
To identify the optimal probability cutoff to classify successful treatment outcomes, thresholds at intervals of 0.01 will be used to calculate these metrics. The weighted calculations of these metrics, which takes into account class imbalance by assigning different weights to each class based on its proportion in the dataset will be calculated.
The AUC will be derived by plotting the true positive rate (y-axis) against the false positive rate (x-axis). AUC measures the model's ability to distinguish the dichotomized treatment outcomes (i.e., treatment success or not). It ranges from 0 to 1, where 0.5 indicates a random guess, 1 indicates perfect predictions, and >0.7 is considered clinically useful.
The 95% confidence intervals (CIs) will be calculated using DeLong's method.


Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
Actual
Date of last participant enrolment
Anticipated
Actual
Date of last data collection
Anticipated
Actual
Sample size
Target
Accrual to date
Final
Recruitment in Australia
Recruitment state(s)
QLD,WA,VIC
Recruitment outside Australia
Country [1] 27041 0
Egypt
State/province [1] 27041 0
Country [2] 27042 0
Hungary
State/province [2] 27042 0
Country [3] 27044 0
Iran, Islamic Republic Of
State/province [3] 27044 0
Country [4] 27045 0
Malaysia
State/province [4] 27045 0
Country [5] 27049 0
United Kingdom
State/province [5] 27049 0
Country [6] 27050 0
United States of America
State/province [6] 27050 0
Country [7] 27052 0
China
State/province [7] 27052 0

Funding & Sponsors
Funding source category [1] 318913 0
Self funded/Unfunded
Name [1] 318913 0
Country [1] 318913 0
Primary sponsor type
University
Name
Monash University
Address
Country
Australia
Secondary sponsor category [1] 321376 0
None
Name [1] 321376 0
Address [1] 321376 0
Country [1] 321376 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 317528 0
Monash University Human Research Ethics Committee
Ethics committee address [1] 317528 0
Ethics committee country [1] 317528 0
Australia
Date submitted for ethics approval [1] 317528 0
28/05/2024
Approval date [1] 317528 0
03/07/2024
Ethics approval number [1] 317528 0
40732

Summary
Brief summary
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 141338 0
Prof Patrick Kwan
Address 141338 0
20 Chancellor Way, Monash University, Clayton VIC 3800
Country 141338 0
Australia
Phone 141338 0
+61 03 90762522
Fax 141338 0
Email 141338 0
Contact person for public queries
Name 141339 0
Daniel Thom
Address 141339 0
Monash University, Alfred Centre, Level 5, 99 Commercial Rd, Melbourne, VIC, 3004,
Country 141339 0
Australia
Phone 141339 0
+61 450807412
Fax 141339 0
Email 141339 0
Contact person for scientific queries
Name 141340 0
Patrick Kwan
Address 141340 0
20 Chancellor Way, Monash University, Clayton VIC 3800
Country 141340 0
Australia
Phone 141340 0
+61 03 90762522
Fax 141340 0
Email 141340 0

Data sharing statement
Will the study consider sharing individual participant data?
No


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.