Quantifying Clinical Outcome Measures in Patients with Epilepsy Using the Electronic Health Record

Kevin Xie, Brian Litt, Dan Roth, Colin A. Ellis


Abstract
A wealth of important clinical information lies untouched in the Electronic Health Record, often in the form of unstructured textual documents. For patients with Epilepsy, such information includes outcome measures like Seizure Frequency and Dates of Last Seizure, key parameters that guide all therapy for these patients. Transformer models have been able to extract such outcome measures from unstructured clinical note text as sentences with human-like accuracy; however, these sentences are not yet usable in a quantitative analysis for large-scale studies. In this study, we developed a pipeline to quantify these outcome measures. We used text summarization models to convert unstructured sentences into specific formats, and then employed rules-based quantifiers to calculate seizure frequencies and dates of last seizure. We demonstrated that our pipeline of models does not excessively propagate errors and we analyzed its mistakes. We anticipate that our methods can be generalized outside of epilepsy to other disorders to drive large-scale clinical research.
Anthology ID:
2022.bionlp-1.36
Volume:
Proceedings of the 21st Workshop on Biomedical Language Processing
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
BioNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
369–375
Language:
URL:
https://aclanthology.org/2022.bionlp-1.36
DOI:
10.18653/v1/2022.bionlp-1.36
Bibkey:
Cite (ACL):
Kevin Xie, Brian Litt, Dan Roth, and Colin A. Ellis. 2022. Quantifying Clinical Outcome Measures in Patients with Epilepsy Using the Electronic Health Record. In Proceedings of the 21st Workshop on Biomedical Language Processing, pages 369–375, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Quantifying Clinical Outcome Measures in Patients with Epilepsy Using the Electronic Health Record (Xie et al., BioNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.bionlp-1.36.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.bionlp-1.36.mp4