# Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning

arXiv: https://arxiv.org/abs/2211.05207 · HTML: https://mlsanity.com/paper/2211.05207/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 9 Nov 2022.

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

- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery](https://mlsanity.com/paper/2011.14340/) (2020)
- [IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography](https://mlsanity.com/paper/2103.12308/) (2021)
- [Explaining Deep Classification of Time-Series Data with Learned Prototypes](https://mlsanity.com/paper/1904.08935/) (2019)
- [Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signals](https://mlsanity.com/paper/2012.11933/) (2020)
- [Effects of Epileptiform Activity on Discharge Outcome in Critically Ill Patients](https://mlsanity.com/paper/2203.04920/) (2022)

## Built on by (most cited first, 10 of 10)

- [Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time](https://mlsanity.com/paper/2503.01087/) (2025)
- ["What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts](https://mlsanity.com/paper/2403.05652/) (2024)
- [ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning](https://mlsanity.com/paper/2504.08713/) (2025)
- [An Automated Classifier of Harmful Brain Activities for Clinical Usage Based on a Vision-Inspired Pre-trained Framework](https://mlsanity.com/paper/2507.08874/) (2025)
- [Comparative Analysis of Deep Learning Approaches for Harmful Brain Activity Detection Using EEG](https://mlsanity.com/paper/2412.07878/) (2024)
- [FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammography](https://mlsanity.com/paper/2406.06386/) (2024)
- [This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN](https://mlsanity.com/paper/2510.20846/) (2025)
- [SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses](https://mlsanity.com/paper/2504.20405/) (2025)
- [Automatic detection of abnormal clinical EEG: comparison of a finetuned foundation model with two deep learning models](https://mlsanity.com/paper/2505.21507/) (2025)
- [Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs](https://mlsanity.com/paper/2508.01521/) (2025)

## Abstract (arXiv)

In intensive care units (ICUs), critically ill patients are monitored with electroencephalograms (EEGs) to prevent serious brain injury. The number of patients who can be monitored is constrained by the availability of trained physicians to read EEGs, and EEG interpretation can be subjective and prone to inter-observer variability. Automated deep learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, black box deep learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of trust and adoption by clinicians. To address these challenges, we propose a novel interpretable deep learning model that not only predicts the presence of harmful brainwave patterns but also provides high-quality case-based explanations of its decisions. Our model performs better than the corresponding black box model, despite being constrained to be interpretable. The learned 2D embedded space provides the first global overview of the structure of ictal-interictal-injury continuum brainwave patterns. The ability to understand how our model arrived at its decisions will not only help clinicians to diagnose and treat harmful brain activities more accurately but also increase their trust and adoption of machine learning models in clinical practice; this could be an integral component of the ICU neurologists' standard workflow.