HighlightsCases with and without epilepsy were linked with anonymised primary care data.Primary care diagnosis and drug codes accurately identify the cases with epilepsy.Drug codes alone can be used to identify children with epilepsy.Combining drug and diagnosis codes for adults and children increases accuracy.

William Pickrell is a clinical lecturer in neurology. SUMMARYObjective: To investigate whether the link between epilepsy and deprivation is due to factors associated with deprivation (social causation) or factors associated with a diagnosis of epilepsy (social drift). Methods: We reviewed electronic primary health care records from 2004 to 2010, identifying prevalent and incident cases of epilepsy and recording linked deprivation scores. Logistic and Poisson regression models were used to calculate odds ratios and incidence rate ratios. The change in deprivation was measured 10 years after the initial diagnosis of epilepsy for a cohort of people. Results: Between 2004 and 2010, 8.1 million patient-years of records were reviewed. Epilepsy prevalence and incidence were significantly associated with deprivation. Epilepsy prevalence ranged from 1.13% (1.07-1.19%) in the most deprived decile to 0.49% (0.45-0.53%) in the least deprived decile (adjusted odds ratio 0.92, p < 0.001). Epilepsy incidence ranged from 40/100,000 per year in the most deprived decile to 19/ 100,000 per year in the least deprived decile (adjusted incidence rate ratio 0.94, p < 0.001). There was no statistically significant change in deprivation index decile 10 years after a new diagnosis of epilepsy (mean difference À0.04, p = 0.85). Significance: Epilepsy prevalence and incidence are strongly associated with deprivation; the deprivation score remains unchanged 10 years after a diagnosis of epilepsy. These findings suggest that increasing rates of epilepsy in deprived areas are more likely explained by social causation than by social drift. The nature of the association between incident epilepsy and social deprivation needs further exploration.

ObjectiveRoutinely collected healthcare data are a powerful research resource but often lack detailed disease-specific information that is collected in clinical free text, for example, clinic letters. We aim to use natural language processing techniques to extract detailed clinical information from epilepsy clinic letters to enrich routinely collected data.DesignWe used the general architecture for text engineering (GATE) framework to build an information extraction system, ExECT (extraction of epilepsy clinical text), combining rule-based and statistical techniques. We extracted nine categories of epilepsy information in addition to clinic date and date of birth across 200 clinic letters. We compared the results of our algorithm with a manual review of the letters by an epilepsy clinician.SettingDe-identified and pseudonymised epilepsy clinic letters from a Health Board serving half a million residents in Wales, UK.ResultsWe identified 1925 items of information with overall precision, recall and F1 score of 91.4%, 81.4% and 86.1%, respectively. Precision and recall for epilepsy-specific categories were: epilepsy diagnosis (88.1%, 89.0%), epilepsy type (89.8%, 79.8%), focal seizures (96.2%, 69.7%), generalised seizures (88.8%, 52.3%), seizure frequency (86.3%–53.6%), medication (96.1%, 94.0%), CT (55.6%, 58.8%), MRI (82.4%, 68.8%) and electroencephalogram (81.5%, 75.3%).ConclusionsWe have built an automated clinical text extraction system that can accurately extract epilepsy information from free text in clinic letters. This can enhance routinely collected data for research in the UK. The information extracted with ExECT such as epilepsy type, seizure frequency and neurological investigations are often missing from routinely collected data. We propose that our algorithm can bridge this data gap enabling further epilepsy research opportunities. While many of the rules in our pipeline were tailored to extract epilepsy specific information, our methods can be applied to other diseases and also can be used in clinical practice to record patient information in a structured manner.