Related Experiment Video
Updated: Jun 15, 2026
Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
Published on: September 20, 2024
Natural language processing for identification of refractory status epilepticus in children
Fatemeh Mohammad Alizadeh Chafjiri1, Latania Reece1,2, Lillian Voke1
1Department of Neurology, Division of Epilepsy and Clinical Neurophysiology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Insights
Natural language processing (NLP) tools like DrT significantly improve the identification of pediatric refractory status epilepticus (rSE) cases in electronic health records (EHRs). This NLP-assisted approach enhances patient discovery compared to manual review alone.
Area of Science:
- Medical Informatics
- Computational Linguistics
- Pediatric Neurology
Background:
- Pediatric status epilepticus (SE) is a critical pediatric emergency with significant mortality and morbidity.
- Electronic health records (EHRs) offer a cost-effective method for analyzing care and outcomes, but manual review is labor-intensive.
- Identifying refractory status epilepticus (rSE) cases efficiently is crucial for timely intervention.
Purpose of the Study:
- To compare the efficacy of a natural language processing (NLP)-assisted screening method with traditional manual review for identifying pediatric rSE cases in EHRs.
- To evaluate the sensitivity and efficiency of the NLP tool Document Review Tool (DrT) in detecting rSE.
Main Methods:
- Utilized the NLP tool DrT to generate regular expressions and trained a bag-of-words NLP classifier on EHR data from 2017-2019.
- Tested the NLP algorithm on EHR data from February to December 2012.
- Compared the case identification results from NLP-assisted search followed by manual review against results from manual review alone.
Main Results:
- The NLP-assisted approach reviewed 400 notes, identifying 31 rSE cases, including 12 new cases missed by manual review.
- The NLP model achieved a sensitivity of 96.88% (31/32 cases), significantly higher than the 62.5% sensitivity (20/32 cases) from manual review alone.
- DrT successfully reduced the number of notes requiring manual review while increasing the detection rate of rSE.
Conclusions:
- The NLP tool DrT provides a highly sensitive method for identifying pediatric rSE cases within EHRs, outperforming manual review.
- NLP-assisted EHR review is a suitable and efficient application for identifying patients with a history of rSE.
- This approach facilitates near real-time implementation of monitoring and treatment strategies for rSE.
Objective:
Pediatric status epilepticus is one of the most frequent pediatric emergencies, with high mortality and morbidity. Utilizing electronic health records (EHRs) permits analysis of care approaches and disease outcomes at a lower cost than prospective research. However, reviewing EHR manually is time intensive. We aimed to compare refractory status epilepticus (rSE) cases identified by human EHR review with a natural language processing (NLP)-assisted rSE screen followed by a manual review.
Methods:
We used the NLP screening tool Document Review Tool (DrT) to generate regular expressions, trained a bag-of-words NLP classifier on EHRs from 2017 to 2019, and then tested our algorithm on data from February to December 2012. We compared results from manual review to NLP-assisted search followed by manual review.
Results:
Our algorithm identified 1528 notes in the test set. After removing notes pertaining to the same event by DrT, the user reviewed a total number of 400 notes to find patients with rSE. Within these 400 notes, we identified 31 rSE cases, including 12 new cases not found in manual review, and 19 of the 20 previously identified cases. The NLP-assisted model found 31 of 32 cases, with a sensitivity of 96.88% (95% CI = 82%-99.84%), whereas manual review identified 20 of 32 cases, with a sensitivity of 62.5% (95% CI = 43.75%-78.34%).
Significance:
DrT provided a highly sensitive model compared to human review and an increase in patient identification through EHRs. The use of DrT is a suitable application of NLP for identifying patients with a history of recent rSE, which ultimately contributes to the implementation of monitoring techniques and treatments in near real time.
More Related Videos
10:22Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
Published on: December 6, 2016
08:43Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System
Published on: July 21, 2015
