This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Dennis, Donnelly, Jon, Barnett, Alina Jade, Semenova, Lesia, Jing, Jin, Hadar, Peter, Karakis, Ioannis, Selioutski, Olga, Zhao, Kehan, Westover, M. Brandon, Rudin, Cynthia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911229022306304
author Tang, Dennis
Donnelly, Jon
Barnett, Alina Jade
Semenova, Lesia
Jing, Jin
Hadar, Peter
Karakis, Ioannis
Selioutski, Olga
Zhao, Kehan
Westover, M. Brandon
Rudin, Cynthia
author_facet Tang, Dennis
Donnelly, Jon
Barnett, Alina Jade
Semenova, Lesia
Jing, Jin
Hadar, Peter
Karakis, Ioannis
Selioutski, Olga
Zhao, Kehan
Westover, M. Brandon
Rudin, Cynthia
contents The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IEDs difficult, leading many practitioners to turn to machine learning for help. While existing machine learning algorithms can achieve strong accuracy on this task, most models are uninterpretable and cannot justify their conclusions. Absent the ability to understand model reasoning, doctors cannot leverage their expertise to identify incorrect model predictions and intervene accordingly. To improve the human-model interaction, we introduce ProtoEEG-kNN, an inherently interpretable model that follows a simple case-based reasoning process. ProtoEEG-kNN reasons by comparing an EEG to similar EEGs from the training set and visually demonstrates its reasoning both in terms of IED morphology (shape) and spatial distribution (location). We show that ProtoEEG-kNN can achieve state-of-the-art accuracy in IED detection while providing explanations that experts prefer over existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20846
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN
Tang, Dennis
Donnelly, Jon
Barnett, Alina Jade
Semenova, Lesia
Jing, Jin
Hadar, Peter
Karakis, Ioannis
Selioutski, Olga
Zhao, Kehan
Westover, M. Brandon
Rudin, Cynthia
Neurons and Cognition
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IEDs difficult, leading many practitioners to turn to machine learning for help. While existing machine learning algorithms can achieve strong accuracy on this task, most models are uninterpretable and cannot justify their conclusions. Absent the ability to understand model reasoning, doctors cannot leverage their expertise to identify incorrect model predictions and intervene accordingly. To improve the human-model interaction, we introduce ProtoEEG-kNN, an inherently interpretable model that follows a simple case-based reasoning process. ProtoEEG-kNN reasons by comparing an EEG to similar EEGs from the training set and visually demonstrates its reasoning both in terms of IED morphology (shape) and spatial distribution (location). We show that ProtoEEG-kNN can achieve state-of-the-art accuracy in IED detection while providing explanations that experts prefer over existing approaches.
title This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN
topic Neurons and Cognition
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2510.20846