Rationale: Implementation of electronic health records may improve the quality, accuracy, timeliness, and availability of documentation. Thus, our institution developed a system that integrated EEG ordering, scheduling, standardized reporting, and billing. Given the importance of user perceptions for successful implementation, we performed a quality improvement study to evaluate electroencephalographer satisfaction with the new EEG report system. Methods: We implemented an EEG report system that was integrated in an electronic health record. In this single-center quality improvement study, we surveyed electroencephalographers regarding overall acceptability, report standardization, workflow efficiency, documentation quality, and fellow education using a 0 to 5 scale (with 5 denoting best). Results: Eighteen electroencephalographers responded to the survey. The median score for recommending the overall system to a colleague was 5 (range 3–5), which indicated good overall satisfaction and acceptance of the system. The median scores for report standardization (4; 3–5) and workflow efficiency (4.5; 3–5) indicated that respondents perceived the system as useful and easy to use for documentation tasks. The median scores for quality of documentation (4.5; 1–5) and fellow education (4; 1–5) indicated that although most respondents believed the system provided good quality reports and helped with fellow education, a small number of respondents had substantially different views (ratings of 1). Conclusions: Overall electroencephalographer satisfaction with the new EEG report system was high, as were the scores for perceived usefulness (assessed as standardization, documentation quality, and education) and ease of use (assessed as workflow efficiency). Future study is needed to determine whether implementation yields useful data for clinical research and quality improvement studies or improves EEG report standardization.

Objective: Improvement in epilepsy care requires standardized methods to assess disease severity. We report the results of implementing common data elements (CDEs) to document epilepsy history data in the electronic medical record (EMR) after 12 months of clinical use in outpatient encounters. Methods: Data regarding seizure frequency were collected during routine clinical encounters using a CDE-based form within our EMR. We extracted CDE data from the EMR and developed measurements for seizure severity and seizure improvement scores. Seizure burden and improvement was evaluated by patient demographic and encounter variables for in-person and telemedicine encounters. Results: We assessed a total of 1696 encounters in 1038 individuals with childhood epilepsies between September 6, 2019 and September 11, 2020 contributed by 32 distinct providers. Childhood absence epilepsy (n = 121), Lennox-Gastaut syndrome (n = 86), and Dravet syndrome (n = 42) were the most common epilepsy syndromes.Overall, 43% (737/1696) of individuals had at least monthly seizures, 17% (296/1696) had a least daily seizures, and 18% (311/1696) were seizure-free for >12 months.Quantification of absolute seizure burden and changes in seizure burden over time differed between epilepsy syndromes, including high and persistent seizure burden in patients with Lennox-Gastaut syndrome. Individuals seen via telemedicine or in-person encounters had comparable seizure frequencies. Individuals identifying as Hispanic/Latino, particularly from postal codes with lower median household incomes, were more likely to have ongoing seizures that worsened over time.

No abstract

Background Accurate prediction of seizures can help direct resource-intense continuous EEG (CEEG) monitoring to high-risk neonates. We aimed to use data extracted from standardized EEG reports to generate seizure prediction models for vulnerable neonates. Methods In 2018, we implemented a novel CEEG reporting system in the electronic medical record (EMR) that incorporated standardized terminology. We developed seizure prediction models using logistic regression, decision tree, and random forest models for neonates and specifically, neonates with hypoxic-ischemic encephalopathy (HIE), using EEG features on day 1 to predict future seizures. Findings We evaluated 1117 neonates, including 150 neonates with HIE, with CEEG data reported using standardized templates. Implementation of a consistent EEG reporting system, which documents discrete and standardized EEG variables, resulted in >95% reporting of key EEG features. Several EEG features were highly correlated, and patients could be clustered based on specific features. However, no simple combination of features adequately predicted seizure risk. We therefore applied computational models to complement clinical identification of high-risk neonates. Random forest models incorporating background features performed with classification accuracies of up to 90% for all neonates and 97% for neonates with HIE, and recall (sensitivity) of up to 97% for all neonates and >99% for neonates with HIE. Interpretation Using data extracted from the standardized EEG report on the first day of CEEG, we predict the presence or absence of neonatal seizures on subsequent days with classification performances of >90%. This information, incorporated into routine care, can guide decisions about the necessity of continuing CEEG beyond the first day and thereby improve the allocation of limited CEEG resources. Additionally, this analysis illustrates the benefits of standardized clinical data collection which can drive learning health system approaches to personalized CEEG utilization.

No abstract