Development of Ontology for Self-limited Epilepsy with Centrotemporal Spikes and Application of Data Mining...

Benign rolandic epilepsy or benign childhood epilepsy with centrotemporal spikes (BCECTS) is a common childhood epileptic syndrome. The syndrome resolves in adolescence, but 1-7% of patients have an atypical presentation, some of which require aggressive medical treatment. Early treatment may prevent complications and neurocognitive deterioration. Variants include Landau-Kleffner syndrome (LKS) and electrical status epilepticus during sleep (ESES).

To determine data driven identification of risk factors and characterization of new subtypes of BCECTS based on anontology. To use data mining analysis and correlation between the identified groups and known clinical variants.

We conducted a retrospective cohort study comprised of 104 patients with a diagnosis of BCECTS and a minimum of 2 years of follow-up, between the years 2005 and 2017. The medical records were obtained from the epilepsy service unit of the pediatric neurology department at Dana-Dwek Hospital, Tel Aviv Sourasky Medical Center. We developed a BCECTS ontology and performed data preprocessing and analysis using the R Project for Statistical Computing (https://www.r-project.org/) and machine learning tools to identify risk factors and characterize subgroups.

The ontology created a uniform and understandable infrastructure for research. With the ontology, a more precise characterization of clinical symptoms and EEG activity of BCECTS was possible. Risk factors for the development of severe atypical presentations were identified: electroencephalography (EEG) with spike wave (P < 0.05), EEG without evidence of left lateralization (P < 0.05), and EEG localization (centrotemporal, frontal, or frontotemporal) (P < 0.01).

Future use of the ontology infrastructure for expanding characterization for multicenter studies as well as future studies of the disease are needed. Identifying subgroups and adapting them to known clinical variants will enable identification of risk factors, improve prediction of disease progression, and facilitate adaptation of more accurate therapy. Early identification and frequent follow-up may have a significant impact on the prognosis of the atypical variants.