# Scope and Arbitration in Machine Learning Clinical EEG Classification

arXiv: https://arxiv.org/abs/2303.06386 · HTML: https://mlsanity.com/paper/2303.06386/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Uncovering the structure of clinical EEG signals with self-supervised learning](https://mlsanity.com/paper/2007.16104/) (2020)
- [Machine-Learning-Based Diagnostics of EEG Pathology](https://mlsanity.com/paper/2002.05115/) (2020)
- [ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification](https://mlsanity.com/paper/1802.00308/) (2018)
- [EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network](https://mlsanity.com/paper/2011.12107/) (2020)
- [Robust learning from corrupted EEG with dynamic spatial filtering](https://mlsanity.com/paper/2105.12916/) (2021)

## Abstract (arXiv)

A key task in clinical EEG interpretation is to classify a recording or session as normal or abnormal. In machine learning approaches to this task, recordings are typically divided into shorter windows for practical reasons, and these windows inherit the label of their parent recording. We hypothesised that window labels derived in this manner can be misleading for example, windows without evident abnormalities can be labelled `abnormal' disrupting the learning process and degrading performance. We explored two separable approaches to mitigate this problem: increasing the window length and introducing a second-stage model to arbitrate between the window-specific predictions within a recording. Evaluating these methods on the Temple University Hospital Abnormal EEG Corpus, we significantly improved state-of-the-art average accuracy from 89.8 percent to 93.3 percent. This result defies previous estimates of the upper limit for performance on this dataset and represents a major step towards clinical translation of machine learning approaches to this problem.