Extracting seizure control metrics from clinic notes of patients with epilepsy: A natural language processing approach.

OBJECTIVES: Monitoring seizure control metrics is key to clinical care of patients with epilepsy. Manually abstracting these metrics from unstructured text in electronic health records (EHR) is laborious. We aimed to abstract the date of last seizure and seizure frequency from clinical notes of patients with epilepsy using natural language processing (NLP). METHODS: We extracted seizure control metrics from notes of patients seen in epilepsy clinics from two hospitals in Boston. Extraction was performed with the pretrained model RoBERTa_for_seizureFrequency_QA, for both date of last seizure and seizure frequency, combined with regular expressions. We designed the algorithm to categorize the timing of last seizure ("today", "1-6 days ago", "1-4 weeks ago", "more than 1-3 months ago", "more than 3-6 months ago", "more than 6-12 months ago", "more than 1-2 years ago", "more than 2 years ago") and seizure frequency ("innumerable", "multiple", "daily", "weekly", "monthly", "once per year", "less than once per year"). Our ground truth consisted of structured questionnaires filled out by physicians. Model performance was measured using the areas under the receiving operating characteristic curve (AUROC) and precision recall curve (AUPRC) for categorical labels, and median absolute error (MAE) for ordinal labels, with 95 % confidence intervals (CI) estimated via bootstrapping. RESULTS: Our cohort included 1773 adult patients with a total of 5658 visits with reported seizure control metrics, seen in epilepsy clinics between December 2018 and May 2022. The cohort average age was 42 years old, the majority were female (57 %), White (81 %) and non-Hispanic (85 %). The models achieved an MAE (95 % CI) for date of last seizure of 4 (4.00-4.86) weeks, and for seizure frequency of 0.02 (0.02-0.02) seizures per day. CONCLUSIONS: Our NLP approach demonstrates that the extraction of seizure control metrics from EHR is feasible allowing for large-scale EHR research.

Quality of life and functional limitations in persons with epilepsy.

OBJECTIVE: Epilepsy can reduce quality of life (QOL), functionality, and social participation, but these effects have not been adequately quantified in large, population-based, controlled studies. We sought to evaluate the impact of epilepsy on patients' QOL and employment outcomes. METHODS: In this cross-sectional study we used nationally representative, pooled data from the Medical Expenditure Panel Survey (MEPS) household component files for 2010-2018. MEPS is a population-based survey of U.S. community-dwelling persons. We included respondents with condition file records for epilepsy. We also analyzed respondents with records for seizure. The primary outcomes were short form-12 physical and mental health scores. Secondary outcomes included self-rated health status, employment status, educational attainment, school/household/work limitations, and missed workdays. We compared these outcomes between persons with epilepsy (PWE) and age- and gender-matched controls. RESULTS: We identified 1078 people with epilepsy, 2344 seizure cases, and 3422 cases of either condition (persons with epilepsy and/or seizures). Epilepsy was associated with a decrease of - 4.0 (95% CI: -5.1 to -2.8) points in SF-12 physical health scores and - 3.1 (95% CI: -4.2 to -1.9) in SF-12 mental health scores. Epilepsy was also associated with decreases in the likelihood of reporting good/very good/excellent health status (-13.3 [95% CI: -16.1 to -10.4] percentage points). Epilepsy was also associated with adverse employment-related outcomes. Specifically, PWE were 17.9 (95% CI: 14.3-21.4) percentage points more likely to report that they had work or household limitations. The associations between outcomes and epilepsy were, in most cases, larger than those between outcomes and other common, chronic conditions. SIGNIFICANCE: Epilepsy is associated with worse quality of life and employment-related outcomes. Interventions should aim to improve functioning and patients' ability to maintain employment.

Causal inference as an emerging statistical approach in neurology: an example for epilepsy in the elderly.

The elderly population faces an increasing number of cases of chronic neurological conditions, such as epilepsy and Alzheimer's disease. Because the elderly with epilepsy are commonly excluded from randomized controlled clinical trials, there are few rigorous studies to guide clinical practice. When the elderly are eligible for trials, they either rarely participate or frequently have poor adherence to therapy, thus limiting both generalizability and validity. In contrast, large observational data sets are increasingly available, but are susceptible to bias when using common analytic approaches. Recent developments in causal inference-analytic approaches also introduce the possibility of emulating randomized controlled trials to yield valid estimates. We provide a practical example of the application of the principles of causal inference to a large observational data set of patients with epilepsy. This review also provides a framework for comparative-effectiveness research in chronic neurological conditions.

Use of transcranial direct current stimulation for the treatment of auditory hallucinations of schizophrenia - a systematic review.

INTRODUCTION: Auditory hallucinations are defined as experiences of auditory perceptions in the absence of a provoking external stimulus. They are the most prevalent symptoms of schizophrenia with high capacity for chronicity and refractoriness during the course of disease. The transcranial direct current stimulation (tDCS) - a safe, portable, and inexpensive neuromodulation technique - has emerged as a promising treatment for the management of auditory hallucinations. OBJECTIVE: The aim of this study is to analyze the level of evidence in the literature available for the use of tDCS as a treatment for auditory hallucinations in schizophrenia. METHODS: A systematic review was performed, searching in the main electronic databases including the Cochrane Library and MEDLINE/PubMed. The searches were performed by combining descriptors, applying terms of the Medical Subject Headings (MeSH) of Descriptors of Health Sciences and descriptors contractions. PRISMA protocol was used as a guide and the terms used were the clinical outcomes ("Schizophrenia" OR "Auditory Hallucinations" OR "Auditory Verbal Hallucinations" OR "Psychosis") searched together ("AND") with interventions ("transcranial Direct Current Stimulation" OR "tDCS" OR "Brain Polarization"). RESULTS: Six randomized controlled trials that evaluated the effects of tDCS on the severity of auditory hallucinations in schizophrenic patients were selected. Analysis of the clinical results of these studies pointed toward incongruence in the information with regard to the therapeutic use of tDCS with a view to reducing the severity of auditory hallucinations in schizophrenia. Only three studies revealed a therapeutic benefit, manifested by reductions in severity and frequency of auditory verbal hallucinations in schizophrenic patients. CONCLUSION: Although tDCS has shown promising results in reducing the severity of auditory hallucinations in schizophrenic patients, this technique cannot yet be used as a therapeutic alternative due to lack of studies with large sample sizes that portray the positive effects that have been described.

Patient-reported financial barriers to adherence to treatment in neurology.

OBJECTIVE: Many effective medical therapies are available for treating neurological diseases, but these therapies tend to be expensive and adherence is critical to their effectiveness. We used patient-reported data to examine the frequency and determinants of financial barriers to medication adherence among individuals treated for neurological disorders. PATIENTS AND METHODS: Patients completed cross-sectional surveys on iPads as part of routine outpatient care in a neurology clinic. Survey responses from a 3-month period were collected and merged with administrative sources of demographic and clinical information (eg, insurance type). We explored the association between patient characteristics and patient-reported failure to refill prescription medication due to cost in the previous 12 months, termed here as "nonadherence". RESULTS: The population studied comprised 6075 adults who were presented between July and September 2015 for outpatient neurology appointments. The mean age of participants was 56 (standard deviation: 18) years, and 1613 (54%) were females. The patients who participated in the surveys (2992, 49%) were comparable to nonparticipants with respect to gender and ethnicity but more often identified English as their preferred language (94% vs 6%, p<0.01). Among respondents, 9.8% (n=265) reported nonadherence that varied by condition. These patients were more frequently Hispanic (16.7% vs 9.8% white, p=0.01), living alone (13.9% vs 8.9% cohabitating, p<0.01), and preferred a language other than English (15.3% vs 9.4%, p=0.02). CONCLUSION: Overall, the magnitude of financial barriers to medication adherence appears to vary across neurological conditions and demographic characteristics.