This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

ImportanceSelection of antiseizure medications (ASMs) for epilepsy remains largely a trial-and-error approach. Under this approach, many patients have to endure sequential trials of ineffective treatments until the “right drugs” are prescribed.ObjectiveTo develop and validate a deep learning model using readily available clinical information to predict treatment success with the first ASM for individual patients.Design, Setting, and ParticipantsThis cohort study developed and validated a prognostic model. Patients were treated between 1982 and 2020. All patients were followed up for a minimum of 1 year or until failure of the first ASM. A total of 2404 adults with epilepsy newly treated at specialist clinics in Scotland, Malaysia, Australia, and China between 1982 and 2020 were considered for inclusion, of whom 606 (25.2%) were excluded from the final cohort because of missing information in 1 or more variables.ExposuresOne of 7 antiseizure medications.Main Outcomes and MeasuresWith the use of the transformer model architecture on 16 clinical factors and ASM information, this cohort study first pooled all cohorts for model training and testing. The model was trained again using the largest cohort and externally validated on the other 4 cohorts. The area under the receiver operating characteristic curve (AUROC), weighted balanced accuracy, sensitivity, and specificity of the model were all assessed for predicting treatment success based on the optimal probability cutoff. Treatment success was defined as complete seizure freedom for the first year of treatment while taking the first ASM. Performance of the transformer model was compared with other machine learning models.ResultsThe final pooled cohort included 1798 adults (54.5% female; median age, 34 years [IQR, 24-50 years]). The transformer model that was trained using the pooled cohort had an AUROC of 0.65 (95% CI, 0.63-0.67) and a weighted balanced accuracy of 0.62 (95% CI, 0.60-0.64) on the test set. The model that was trained using the largest cohort only had AUROCs ranging from 0.52 to 0.60 and a weighted balanced accuracy ranging from 0.51 to 0.62 in the external validation cohorts. Number of pretreatment seizures, presence of psychiatric disorders, electroencephalography, and brain imaging findings were the most important clinical variables for predicted outcomes in both models. The transformer model that was developed using the pooled cohort outperformed 2 of the 5 other models tested in terms of AUROC.Conclusions and RelevanceIn this cohort study, a deep learning model showed the feasibility of personalized prediction of response to ASMs based on clinical information. With improvement of performance, such as by incorporating genetic and imaging data, this model may potentially assist clinicians in selecting the right drug at the first trial.

No abstract

This survey was performed to determine the availability of epilepsy surgery, and understand the limiting factors to epilepsy surgery in ASEAN countries with total of 640 million population. Method: A cross-sectional survey was completed by national representatives in all ASEAN countries (Brunei,

Antiseizure medication can potentially cause severe cutaneous adverse reactions, and certain antiseizure medication‐induced severe cutaneous adverse reactions are associated with specific human leukocyte antigen alleles. This caused a change in antiseizure medication prescribing patterns, which may influence the incidence of antiseizure medication‐induced severe cutaneous adverse reactions. Thus, we aimed to determine the incidence of antiseizure medication‐induced severe cutaneous adverse reactions and its change over 15 years (2006‐2019) in Malaysia. This retrospective analysis combined antiseizure medication‐induced SCAR cases from the national adverse drug reaction database in the National Pharmaceutical Regulatory Agency, antiseizure medication usage data from the Malaysian Statistics of Medicine, and prescribing data from University Malaya Medical Centre, a national‐level tertiary hospital to calculate antiseizure medication‐induced SCAR incidence in Malaysia. We observed an upward trend in reported antiseizure medication‐induced SCAR cases from 28 cases in 2006 to 92 in 2016. The incidence of carbamazepine (CBZ)‐induced severe cutaneous adverse reactions increased from 7.5 per 1000 person‐years (2006) to 17.8 per 1000 person‐years (2016) but dropped to 7.2 per 1000 person‐years subsequently (2019). Concurrently, there was an increase in the incidence of severe cutaneous adverse reactions secondary to phenytoin and lamotrigine. The prevalent users of CBZ had reduced from 22.8% (2006) to 14.1% (2016), whereas the levetiracetam and sodium valproate users increased by 5.5% and 4.8%, respectively. The incidence of CBZ‐induced severe cutaneous adverse reactions had reduced since 2016, probably related to the implementation of human leukocyte antigen‐B*1502 screening in Malaysia or substitution of CBZ with other antiseizure medications. However, this was accompanied by an increase in SCAR incidence related to phenytoin and lamotrigine.