SCORE-IT: A Machine Learning-based Tool for Automatic Standardization of EEG Reports

TL;DR

This paper introduces SCORE-IT, a machine learning tool that automatically extracts standardized metadata from unstructured EEG reports, improving data consistency for large-scale neurological research.

Contribution

It presents a novel ML-based system that extracts key EEG report components aligned with the SCORE standard from natural language reports.

Findings

Achieved F1 scores of 0.92, 0.82, and 0.97 on key extraction tasks.

Demonstrated effectiveness on the TUH EEG corpus.

Facilitates large-scale EEG data analysis.

Abstract

Machine learning (ML)-based analysis of electroencephalograms (EEGs) is playing an important role in advancing neurological care. However, the difficulties in automatically extracting useful metadata from clinical records hinder the development of large-scale EEG-based ML models. EEG reports, which are the primary sources of metadata for EEG studies, suffer from lack of standardization. Here we propose a machine learning-based system that automatically extracts components from the SCORE specification from unstructured, natural-language EEG reports. Specifically, our system identifies (1) the type of seizure that was observed in the recording, per physician impression; (2) whether the session recording was normal or abnormal according to physician impression; (3) whether the patient was diagnosed with epilepsy or not. We performed an evaluation of our system using the publicly available TUH EEG corpus and report F1 scores of 0.92, 0.82, and 0.97 for the respective tasks.