Feasibility of Automatic Extraction of Electronic Health Data to Evaluate a Status Epilepticus Clinical Protocol

Area of Science:

• Pediatric Neurology
• Clinical Informatics
• Health Data Science

Background:

• Status epilepticus is a frequent pediatric neurologic emergency.
• Standardized care protocols are crucial for managing pediatric status epilepticus.
• Electronic health records (EHRs) offer potential for evaluating protocol adherence.

Purpose of the Study:

• To assess the feasibility of automated data extraction from EHRs for pediatric status epilepticus.
• To demonstrate a timeline visualization of the initial 24 hours of care for these patients.
• To explore the utility of EHR data for protocol adherence evaluation.

Main Methods:

• Review of clinical data from a small cohort (n=7) of children with status epilepticus.
• Qualitative assessment of automated data extraction from structured EHR fields.
• Manual abstraction for specific data types, such as electroencephalography (EEG).
• Development of a timeline-style visualization of patient care.

Main Results:

• Most clinical data were readily available in structured EHR fields.
• Automated extraction was feasible but required manual abstraction for certain critical data, including EEG.
• A clear timeline visualization of patient care was successfully generated.

Conclusions:

• Automated creation of patient care timelines from EHR data is feasible for pediatric status epilepticus.
• Supplementing automated extraction with manual data abstraction enhances visualization accuracy.
• This timeline visualization can serve as a foundation for future protocol adherence studies.