Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms.

Code ↔ Paper

2 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 2 matches · all tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted

[1] § STAR★Methods › Method details › Machine learning ↔ linear-regression/demo.m, the whole file · a weak match · score 0.67 · linear regression, gradient descent, model parameters, predicts
[2] § STAR★Methods › Method details › Machine learning ↔ linear-regression/linear_regression_train.m, the whole file · a weak match · score 0.65 · linear regression, gradient descent, model parameters

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The paper is loaded by your browser, with JavaScript: read it at doi.org or on Europe PMC.

The authors' code

MATLAB · 103 lines · 3.2 KB · MIT · 1 match

% Clear variables and a screen.
clear; close all; clc;
% Loading training data from file ----------------------------------------------
fprintf('Loading the training data from file...\n\n');
% Loading training data from file.
data = load('house_prices.csv');
% Split data into features and results.
X = data(:, 1:2);
y = data(:, 3);
% Plotting training data -------------------------------------------------------
fprintf('Plotting the training data...\n\n');
% Split the figure on 2x2 sectors.
% Start drawing in first sector.
subplot(2, 2, 1);
scatter3(X(:, 1), X(:, 2), y, [], y(:), 'o');
title('Training Set');
xlabel('Size');
ylabel('Rooms');
zlabel('Price');
% Running linear regression ----------------------------------------------------
fprintf('Running linear regression...\n');
% Setup regularization parameter.
lambda = 0;
alpha = 0.1;
num_iterations = 50;
[theta mu sigma X_normalized J_history] = linear_regression_train(X, y, alpha, lambda, num_iterations);
fprintf('- Initial cost: %f\n', J_history(1));
fprintf('- Optimized cost: %f\n', J_history(end));
fprintf('- Theta (with normalization):\n');
fprintf('-- %f\n', theta);
fprintf('\n');
% Calculate model parameters using normal equation -----------------------------
fprintf('Calculate model parameters using normal equation...\n');
X_normal = [ones(size(X, 1), 1) X];
theta_normal = normal_equation(X_normal, y);
normal_cost = cost_function(X_normal, y, theta_normal, lambda);
fprintf('- Normal function cost: %f\n', normal_cost);
fprintf('- Theta (without normalization):\n');
fprintf('-- %f\n', theta_normal);
fprintf('\n');
% Plotting normalized training data --------------------------------------------
fprintf('Plotting normalized training data...\n\n');
% Start drawing in second sector.
subplot(2, 2, 2);
scatter3(X_normalized(:, 2), X_normalized(:, 3), y, [], y(:), 'o');
title('Normalized Training Set');
xlabel('Normalized Size');
ylabel('Normalized Rooms');
zlabel('Price');
% Draw gradient descent progress ------------------------------------------------
fprintf('Plot gradient descent progress...\n\n');
% Continue plotting to the right area.
subplot(2, 2, 3);
plot(1:num_iterations, J_history);
xlabel('Iteration');
ylabel('J(\theta)');
title('Gradient Descent Progress');
% Plotting hypothesis plane on top of training set -----------------------------
fprintf('Plotting hypothesis plane on top of training set...\n\n');
% Get apartment size and rooms boundaries.
apt_sizes = X_normalized(:, 2);
apt_rooms = X_normalized(:, 3);
apt_size_range = linspace(min(apt_sizes), max(apt_sizes), 10);
apt_rooms_range = linspace(min(apt_rooms), max(apt_rooms), 10);
% Calculate predictions for each possible combination of rooms number and appartment size.
apt_prices = zeros(length(apt_size_range), length(apt_rooms_range));
for apt_size_index = 1:length(apt_size_range)
for apt_room_index = 1:length(apt_rooms_range)
X = [1, apt_size_range(apt_size_index), apt_rooms_range(apt_room_index)];
apt_prices(apt_size_index, apt_room_index) = hypothesis(X, theta);
end
end
% Plot the plane on top of training data to see how it feets them.
subplot(2, 2, 2);
hold on;
mesh(apt_size_range, apt_rooms_range, apt_prices);
legend('Training Examples', 'Hypothesis Plane')
hold off;

demo.m at commit 34a3893, under MIT · at the source

Overview

Authors: Ran Ao^1,2, Ping Zhan^1,2, Guojing Wang^1,2, Hongyun Liu^1,2, Weidong Wang^1,2

Institutions: Chinese PLA General Hospital (China); Ministry of Industry and Information Technology (China)

Journal: iScience, volume 29, issue 7, article 116408

Dates: received 3 January 2026; accepted 29 May 2026; published online 22 June 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.1016/j.isci.2026.116408 · PMID 42382995 · PMCID PMC13316274 · OpenAlex W7165574404

Open access: gold, a free copy (OpenAlex)

Status: code verified

Categories: EEG (modality), human (organism), epilepsy (population), methods / tools (subfield)

Methods: Preprocessing, Connectivity, Statistics, Smoothing, state filtering, decompositions, Machine learning, Complexity, Spectral & time-frequency, Physiology & signal measures

Keywords: Neuroscience, Sensory neuroscience, Techniques in neuroscience, Machine learning

Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex

Funding: National Key Research and Development Program of China (2022YFC2405603)

Citations: not cited yet (Europe PMC); 48 references in the paper

Abstract

Interictal epileptiform discharges (IEDs) are essential for epilepsy diagnosis, yet visual electroencephalogram (EEG) analysis remains subjective and laborious. To address this, we developed Epilepsy-IEDs, an automated machine learning model for IED detection. Trained on 141 scalp EEG recordings (2,597 IEDs and 4,633 non-IEDs), the model was evaluated using four algorithms, with a separate daytime analysis to control for sleep effects. The Extreme Gradient Boosting (XGBoost)-based model achieved the highest performance, with sensitivities of 84.6% (area under the curve [AUC] = 0.966) and 87.1% (AUC = 0.973) on the full and daytime datasets, respectively, and demonstrated robust generalization on held-out epilepsy patients (AUC = 0.878–0.890), with a specificity of 71.54% on a non-epilepsy cohort. A simplified 10-feature variant maintained strong performance (AUC = 0.959). The Epilepsy-IEDs model provides an accurate, interpretable tool for IED detection, with a streamlined version suitable for integration into clinical EEG workflows.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 2 matches between paragraphs and lines of code.

ylooliu/Epilepsy-IEDs

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: 2ae2350ecbd3e2706e012a297e06c6c5024ef321, 23 April 2026

Size: 7 files

Software Heritage: not archived

Found in: “Data and code availability”

Holds: README

Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

1 file

README.md, Text, 14 lines

At the source: github.com/ylooliu/Epilepsy-IEDs

Zenodo 20404907

License: CC-BY-4.0

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Size: 1 file

Software Heritage: not checked

Found in: “Data and code availability”

Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation

Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)

27 September 2026: the link answers (HTTP 200)

1 file

README.md, Text, 14 lines

At the source: doi.org/10.5281/zenodo.20404907

trekhleb/machine-learning-octave

License: MIT

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: 34a3893d67e7c1deeeb34ac21e7cff391aa9f35d, 22 November 2025

Languages: MATLAB (48)

Size: 201 files, 48 scripts

Software Heritage: archived

Found in: the text, “Key resources table”

Holds: README, license file

Not found: CITATION.cff, environment file, tests, continuous integration, documentation

Tools: Optimization Toolbox (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

50 files

anomaly-detection/demo.m, MATLAB, 39 lines
anomaly-detection/estimate_gaussian.m, MATLAB, 7 lines
anomaly-detection/multivariate_gaussian.m, MATLAB, 16 lines
anomaly-detection/select_threshold.m, MATLAB, 38 lines
anomaly-detection/visualize_fit.m, MATLAB, 16 lines
k-means/compute_centroids.m, MATLAB, 16 lines
k-means/demo.m, MATLAB, 72 lines
k-means/find_closest_centroids.m, MATLAB, 26 lines
k-means/init_centroids.m, MATLAB, 8 lines
k-means/k_means_train.m, MATLAB, 17 lines
linear-regression/cost_function.m, MATLAB, 30 lines
linear-regression/demo.m, MATLAB, 103 lines, 1 match
linear-regression/feature_normalize.m, MATLAB, 22 lines
linear-regression/gradient_descent.m, MATLAB, 34 lines
linear-regression/gradient_step.m, MATLAB, 36 lines
linear-regression/hypothesis.m, MATLAB, 16 lines
linear-regression/linear_regression_train.m, MATLAB, 26 lines, 1 match
linear-regression/normal_equation.m, MATLAB, 5 lines
logistic-regression/add_polynomial_features.m, MATLAB, 13 lines
logistic-regression/cost_function.m, MATLAB, 22 lines
logistic-regression/demo.m, MATLAB, 121 lines
logistic-regression/display_data.m, MATLAB, 54 lines
logistic-regression/fmincg.m, MATLAB, 175 lines
logistic-regression/gradient_callback.m, MATLAB, 15 lines
logistic-regression/gradient_descent.m, MATLAB, 14 lines
logistic-regression/gradient_step.m, MATLAB, 26 lines
logistic-regression/hypothesis.m, MATLAB, 16 lines
logistic-regression/logistic_regression_train.m, MATLAB, 27 lines
logistic-regression/one_vs_all.m, MATLAB, 34 lines
logistic-regression/one_vs_all_predict.m, MATLAB, 20 lines
logistic-regression/sigmoid.m, MATLAB, 4 lines
neural-network/debug_initialize_weights.m, MATLAB, 14 lines
neural-network/debug_nn_gradients.m, MATLAB, 49 lines
neural-network/debug_numerical_gradient.m, MATLAB, 24 lines
neural-network/demo.m, MATLAB, 65 lines
neural-network/display_data.m, MATLAB, 54 lines
neural-network/fmincg.m, MATLAB, 175 lines
neural-network/neural_network_predict.m, MATLAB, 12 lines
neural-network/neural_network_train.m, MATLAB, 20 lines
neural-network/nn_backpropagation.m, MATLAB, 88 lines
neural-network/nn_cost_function.m, MATLAB, 39 lines
neural-network/nn_feedforward_propagation.m, MATLAB, 24 lines
neural-network/nn_gradient_step.m, MATLAB, 12 lines
neural-network/nn_params_init.m, MATLAB, 18 lines
neural-network/nn_params_roll.m, MATLAB, 23 lines
neural-network/sigmoid.m, MATLAB, 4 lines
neural-network/sigmoid_gradient.m, MATLAB, 6 lines
neural-network/unroll.m, MATLAB, 10 lines
LICENSE, License, 21 lines
README.md, Text, 104 lines

At the source: github.com/trekhleb/machine-learning-octave

ajaiantilal/randomforest-matlab

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: 11344de678dd9595d7bcff2a6ab6055c01e1fbd6, 19 April 2016

Languages: MATLAB (17), C++ (14), C (2), C/C++ (2)

Size: 66 files, 35 scripts

Software Heritage: archived

Found in: the text, “Key resources table”

Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

35 files

RF_Class_C/classRF_predict.m, MATLAB, 92 lines
RF_Class_C/classRF_predict_matlab.m, MATLAB, 105 lines
RF_Class_C/classRF_train.m, MATLAB, 467 lines
RF_Class_C/compile_linux.m, MATLAB, 23 lines
RF_Class_C/compile_windows.m, MATLAB, 24 lines
RF_Class_C/rfImpute.m, MATLAB, 83 lines
RF_Class_C/src/classRF.cpp, C++, 903 lines
RF_Class_C/src/classTree.cpp, C++, 255 lines
RF_Class_C/src/cokus.cpp, C++, 196 lines
RF_Class_C/src/cokus_test.cpp, C++, 42 lines
RF_Class_C/src/mex_ClassificationRF_predict.cpp, C++, 188 lines
RF_Class_C/src/mex_ClassificationRF_train.cpp, C++, 296 lines
RF_Class_C/src/qsort.c, C, 155 lines
RF_Class_C/src/rf.h, C/C++, 117 lines
RF_Class_C/src/rfutils.cpp, C++, 308 lines
RF_Class_C/src/twonorm_C_wrapper.cpp, C++, 316 lines
RF_Class_C/test_ClassRF_extensively.m, MATLAB, 29 lines
RF_Class_C/tutorial_ClassRF.m, MATLAB, 313 lines
RF_Class_C/tutorial_ClusterRF.m, MATLAB, 42 lines
RF_Class_C/tutorial_Proximity_training_test.m, MATLAB, 79 lines
RF_Reg_C/compile_linux.m, MATLAB, 24 lines
RF_Reg_C/compile_windows.m, MATLAB, 24 lines
RF_Reg_C/regRF_predict.m, MATLAB, 59 lines
RF_Reg_C/regRF_train.m, MATLAB, 345 lines
RF_Reg_C/rfImpute.m, MATLAB, 93 lines
RF_Reg_C/src/cokus.cpp, C++, 196 lines
RF_Reg_C/src/cokus_test.cpp, C++, 42 lines
RF_Reg_C/src/diabetes_C_wrapper.cpp, C++, 382 lines
RF_Reg_C/src/mex_regressionRF_predict.cpp, C++, 151 lines
RF_Reg_C/src/mex_regressionRF_train.cpp, C++, 356 lines
RF_Reg_C/src/qsort.c, C, 155 lines
RF_Reg_C/src/reg_RF.cpp, C++, 1,092 lines
RF_Reg_C/src/reg_RF.h, C/C++, 19 lines
RF_Reg_C/test_RegRF_extensively.m, MATLAB, 48 lines
RF_Reg_C/tutorial_RegRF.m, MATLAB, 300 lines

At the source: github.com/ajaiantilal/randomforest-matlab

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

4 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
83 scripts, each with its path and the digest of its content;
2 matches between paragraphs of the paper and lines of the code (method lexical-v1);
neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data and code availability

• All data presented within this study are available in key resources table. • All original code has been deposited at GitHub (https://github.com/ylooliu/Epilepsy-IEDs) and Zenodo (https://doi.org/10.5281/zenodo.20404907) and is publicly available as of the date of publication (see key resources table). • Any additional information required to reanalyze the data reported in this work paper is available from the lead contact upon request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 4 keywords, 1 funder, 47 references.

Cite

This paper

Ao, R., Zhan, P., Wang, G., Liu, H., & Wang, W. (2026). Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms. iScience, 29(7), 116408. https://doi.org/10.1016/j.isci.2026.116408

BibTeX

@article{ao2026epilepsy, author = {Ao, Ran and Zhan, Ping and Wang, Guojing and Liu, Hongyun and Wang, Weidong}, title = {{Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms}}, journal = {iScience}, year = {2026}, month = jun, volume = {29}, number = {7}, pages = {116408}, publisher = {Elsevier}, issn = {2589-0042}, doi = {10.1016/j.isci.2026.116408}, url = {https://doi.org/10.1016/j.isci.2026.116408}, pmid = {42382995}, pmcid = {PMC13316274} }

RIS

TY - JOUR AU - Ao, Ran AU - Zhan, Ping AU - Wang, Guojing AU - Liu, Hongyun AU - Wang, Weidong TI - Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms T2 - iScience J2 - iScience PY - 2026 DA - 2026/06/22 VL - 29 IS - 7 SP - 116408 SN - 2589-0042 PB - Elsevier DO - 10.1016/j.isci.2026.116408 UR - https://doi.org/10.1016/j.isci.2026.116408 LA - en ER -

CSL-JSON

{ "id": "10.1016/j.isci.2026.116408", "type": "article-journal", "title": "Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms", "container-title": "iScience", "author": [ { "family": "Ao", "given": "Ran" }, { "family": "Zhan", "given": "Ping" }, { "family": "Wang", "given": "Guojing" }, { "family": "Liu", "given": "Hongyun" }, { "family": "Wang", "given": "Weidong" } ], "container-title-short": "iScience", "volume": "29", "issue": "7", "page": "116408", "DOI": "10.1016/j.isci.2026.116408", "PMID": "42382995", "PMCID": "PMC13316274", "ISSN": "2589-0042", "publisher": "Elsevier", "URL": "https://doi.org/10.1016/j.isci.2026.116408", "language": "en", "issued": { "date-parts": [ [ 2026, 6, 22 ] ] } }

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.

Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms.

Code ↔ Paper

Paper

The authors' code

Overview

Abstract

Repositories

ylooliu/Epilepsy-IEDs

Zenodo 20404907

trekhleb/machine-learning-octave

ajaiantilal/randomforest-matlab

Tracing map

Data

Data and code availability

Versions

Version 1, 27 September 2026: the first record

Cite

This paper

Similar papers

Contribute

Claim this paper

Correct its record

Validate its tracing map

Add the badge to its README

Request its removal

Discussion, reproductions, activity