EMPiRE model
A model to predict the risk of seizures in pregnant women with epilepsy on anti-epileptic medication
Research authors: John Allotey, Borja Fernandez-Felix, Javier Zamora, Ngawai Moss, Manny Bagary, Andrew Kelso, Rehan Khan, Joris A. M. van der Post, Ben W. Mol, Alexander M. Pirie, Dougall McCorry, Khalid S. Khan, Shakila Thangaratinam
Details Formula Study characteristics Files & References
Model author
Model ID
Revision date
MeSH terms
  • Epilepsy
  • Epileptic Seizure
  • Pregnancy
  • Model type
    Logistic regression (Calculation)
    No Formula defined yet
    Condition Formula

    Additional information

    Current model was developed using data from the prospective multicentre EMPiRE (AntiEpileptic drug Monitoring in PREgnancy) study, which recruited pregnant women with epilepsy on antiepileptic drugs at first antenatal visit from 50 maternity units in the UK bewteen 4 November 2011 and 17 August 2014. 

    A multidisciplinary team of neurologists, obstetricians, and researchers selected the candidate predictors for further evaluation in the prognostic model, based on existing evidence and their relevance to clinical care.

    The main outcome was the occurrence of tonic-clonic (convulsive) or non-tonic-clonic (nonconvulsive)
    seizure. Participants prospectively recorded their epileptic seizures, if any, in purpose-built seizure diaries. 

    Missing values were handled using 10-fold multiple imputation by chained equation. LASSO method was used to develop logistic regression models. 

    The displayed study characteristics concen the characteristics of the development cohort (n = 399). The model was also externally validated on a separate cohort (n = 128)

    Study Population

    Total population size: 527
    Males: {{ model.numberOfMales }}
    Females: {{ model.numberOfFemales }}

    Continuous characteristics

    Name Mean SD Unit
    Age at first seizure 16.5 7.4 years
    Gestational age at baseline 16.6 4 Weeks
    Number of tonic-clonic seizures in pregnancy prior to the baseline visit (missing n = 82) 0.7 2.8 seizures
    number of non-tonic-clonic seizures in pregnancy prior to the baseline visit 11.6 108.4 seizures
    Baseline dose of Carbamazepine 706.0 348.5 mg/day
    Baseline dose of Lamotrigine 272.1 155.6 mg/day
    Baseline dose of Levetiracetam 1641.3 886.8 mg/day

    Categorical characteristics

    Name Subset / Group Nr. of patients
    Age at first seizure (missing n = 5) ≤10 years 70
    11 - 20 years 215
    21 - 30 years 94
    31 - 40 years 15
    Hisrtory of learning difficulty or mental illness (missing n = 1) No 348
    Yes 50
    Admission to hospital for seizures in previous pregnancy (missing n = 22) No 349
    Yes 28
    Seizure classification at baseline Tonic-Clonic 155
    Non-tonic-clonic 232
    Unspecified 12
    Seizure in the 3 months before pregnancy (missing n = 83) No 217
    Tonic-Clonic 52
    Non-tonic-clonic 130
    Antiepileptic drug intake at baseline Carbamazepine 74
    Lamotrigine 200
    Levetiracetam 99
    Phenytoin 0
    Lamotrigine and carbamazepine 1
    Lamotrigine and levetiracetam 25
    EMPiRE model
    Refer to Intended Use for instructions before use
    Evidencio B.V., Irenesingel 19, 7481 GJ, Haaksbergen, the Netherlands

    Related files

    No related files available

    Supporting Publications

    The calculated predicted risk of seizures in pregnancy and up to 6 weeks after delivery is:

    {{ resultSubheader }}

    {{ model.survival.PITTitle }}

    {{ model.survival.YNETitle }}

    Notes are only visible in the result download and will not be saved by Evidencio

    The calculated predicted risk of seizures in pregnancy and up to 6 weeks after delivery is:

    {{ resultSubheader }}
    {{ chart.title }}

    Outcome stratification

    Result interval {{ additionalResult.min }} to {{ additionalResult.max }}

    Conditional information

    Result interpretation

    The calculation is the risk of the pregnant woman having any siezure in pregnancy and up to 6 weeks after delivery. Use of the model in clinical practice should be complementary to individualised advice on safety, risk assessment, adherence and triggers for seizures. 
    Women predicted to have a low risk of seizure should be informed that their risk status is subject to adherence to their anti-epileptic medication. 

    {{ file.classification }}

    Calculations alone should never dictate patient care, and are no substitute for professional judgement. See our full disclaimer.

    Please enter a comment of rating
    Comments are visible to anyone

    Model feedback

    No feedback yet 1 Comment {{ model.comments.length }} Comments
    Not rated | On {{ comment.created_at }} {{ comment.user.username }} a no longer registered author wrote:

    Please sign in to enable Evidencio print features

    In order to use the Evidencio print features, you need to be logged in.
    If you don't have an Evidencio Community Account you can create your free personal account at:


    Printed results - Examples {{ new Date().toLocaleString() }}

    Evidencio Community Account Benefits

    With an Evidencio Community account you can:

    • Create and publish your own prediction models.
    • Share your prediction models with your colleagues, research group, organization or the world.
    • Review and provide feedback on models that have been shared with you.
    • Validate your models and validate models from other users.
    • Find models based on Title, Keyword, Author, Institute, or MeSH classification.
    • Use and save prediction models and their data.
    • Use patient specific protocols and guidelines based on sequential models and decision trees.
    • Stay up-to-date with new models in your field as they are published.
    • Create your own lists of favorite models and topics.
    A personal Evidencio account is free, with no strings attached! Join us and help create clarity, transparency, and efficiency in the creation, validation, and use of medical prediction models.

    Disclaimer: Calculations alone should never dictate patient care, and are no substitute for professional judgement.