A Comparison of Machine Learning Models for Classification of Parkinson's Disease During a Working Memory and Sustained Attention Task.
Overview
- Biomedical Engineering Department, University of North Dakota, Grand Forks, ND 58202, USA
- Department of Psychology, North Dakota State University, Fargo, ND 58102, USA; (S.A.B.); (J.S.J.)
- Department of Neurology, Sanford Health, Fargo, ND 58103, USA; (J.-S.L.); (J.K.)
- Department of Neurology, University of North Dakota School of Medicine and Health Science, Grand Forks, ND 58202, USA
- Department of Psychology, Minnesota State Community and Technical College, Moorhead, MN 56560, USA
Abstract
Highlights: What are the main findings? A task-aligned machine learning pipeline combining EEG and pupillometry features separated individuals with Parkinson’s disease from healthy controls during a working memory task, achieving accuracy that exceeded what standard behavioral performance measures alone could distinguish between the two groups. Seven physiological features, including markers of frontal alpha activity, oscillatory ratios, and pupillary response, emerged as most discriminative, concentrated in the most demanding parts of the task (higher memory loads, longer delays, and incorrect trials).
What are the implications of the main findings? Physiological signals recorded during cognitive tasks may capture Parkinson’s-related cognitive changes that are not reliably evident from behavioral performance alone, pointing to their potential value as more sensitive early markers of cognitive dysfunction. The task-aligned, interpretable design of this framework offers a reproducible platform for future biomarker discovery, laying groundwork for larger validation studies and, eventually, tools to support cognitive screening and monitoring in Parkinson’s disease.
Abstract: Background and Objectives: Individuals with Parkinson’s disease (PD) experience deficits in working memory (WM) and sustained attention (ATTN), but diagnosing and monitoring these deficits remains challenging. This study compares machine learning (ML) classification models trained on EEG and pupillometry data from WM and ATTN tasks to identify task-specific and shared cognitive biomarkers of PD. Methods: EEG and pupillometry were recorded from PD patients and healthy controls (HC) during a visual change detection WM task and a continuous performance ATTN task. A standardized toolbox extracted 108 features, reduced via PCA and recursive elimination (RE) and classified using an SVM-RBF within a nested, 5-fold cross-validated pipeline, with class balancing (SMOTE) and feature selection performed strictly within training folds to prevent leakage. Results: On internal test folds, WM achieved 71% accuracy (F1 = 0.701) and ATTN achieved 73% (F1 = 0.699); on an independent hold-out set, WM achieved 63% accuracy (F1 = 0.626) and ATTN achieved 70% (F1 = 0.623). ATTN showed higher accuracy and precision, WM showed higher recall, and univariate analyses independently supported several top-ranked features (e.g., theta/
Reproduced under the paper's license (CC BY), from the paper cited above.
Code
No file of the authors' code could be read here: it is described below, and read at its source.
mercedesterry/EEG-and-Pupillary-Feature-Extraction-Toolbox
Availability: 1 check, the latest on 27 September 2026: the link is dead
- 27 September 2026: the link is dead
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:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 0 scripts, each with its path and the digest of its content;
- no match between paragraphs and code yet;
- 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 Availability Statement
The de-identified EEG and pupillometry datasets generated and analyzed during the current study are available from the corresponding author upon reasonable request. Access to de-identified raw data from human participants can be available to Jeffrey S. Johnson or Samuel A. Birkholz upon reasonable request. The custom feature extraction toolbox and scripts used for model training and analysis are openly available on GitHub at [https://
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, 7 authors, 10 keywords, 1 funder, 42 references.
Cite
This paper
Terry, M. A., Birkholz, S. A., Johnson, J. S., Lou, J.-S., Huether, A. X. A., Keller, J., & Alvarez-Vazquez, E. (2026). A Comparison of Machine Learning Models for Classification of Parkinson's Disease During a Working Memory and Sustained Attention Task. Brain sciences, 16(8), 781. https://
BibTeX
@article{terry2026compar
author = {Terry, Mercedes A. and Birkholz, Samuel A. and Johnson, Jeffrey S. and Lou, Jau-Shin and Huether, Asenath X. A. and Keller, Jessica and Alvarez-Vazquez, Enrique},
title = {{A Comparison of Machine Learning Models for Classification of Parkinson's Disease During a Working Memory and Sustained Attention Task}},
journal = {Brain sciences},
year = {2026},
month = jul,
volume = {16},
number = {8},
pages = {781},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2076-3425},
doi = {10.3390/
url = {https://
pmid = {42651093},
pmcid = {PMC13510374}
}
RIS
TY - JOUR
AU - Terry, Mercedes A.
AU - Birkholz, Samuel A.
AU - Johnson, Jeffrey S.
AU - Lou, Jau-Shin
AU - Huether, Asenath X. A.
AU - Keller, Jessica
AU - Alvarez-Vazquez, Enrique
TI - A Comparison of Machine Learning Models for Classification of Parkinson's Disease During a Working Memory and Sustained Attention Task
T2 - Brain sciences
J2 - Brain Sci
PY - 2026
DA - 2026/
VL - 16
IS - 8
SP - 781
SN - 2076-3425
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.3390/
"type": "article-journal",
"title": "A Comparison of Machine Learning Models for Classification of Parkinson's Disease During a Working Memory and Sustained Attention Task",
"container-title": "Brain sciences",
"author": [
{
"family": "Terry",
"given": "Mercedes A."
},
{
"family": "Birkholz",
"given": "Samuel A."
},
{
"family": "Johnson",
"given": "Jeffrey S."
},
{
"family": "Lou",
"given": "Jau-Shin"
},
{
"family": "Huether",
"given": "Asenath X. A."
},
{
"family": "Keller",
"given": "Jessica"
},
{
"family": "Alvarez-Vazquez",
"given": "Enrique"
}
],
"container-title-short":
"volume": "16",
"issue": "8",
"page": "781",
"DOI": "10.3390/
"PMID": "42651093",
"PMCID": "PMC13510374",
"ISSN": "2076-3425",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
24
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1007/s11571-026-10526-z
- A task-aligned multimodal machine learning framework for studying working memory dysfunction in Parkinson's disease.Journal: Cognitive neurodynamicsIn common: Parkinson's, EEG, cognitive, 9 references
- [2] doi:10.1002/brb3.71563
- A Hybrid Random Forest-SARSA Framework for Resting-State EEG-Based Parkinson's Disease Detection With Temporal Decision Refinement.Journal: Brain and behaviorIn common: Parkinson's, EEG, 3 references
- [3] doi:10.1177/20552076261467837
- Generalization over accuracy: A cross-dataset, explainable, and federated learning framework for Parkinson's disease detection.Journal: Digital healthIn common: Parkinson's, 2 references
- [4] doi:10.1038/s41467-025-63444-9
- Synaptic vesicle endocytosis deficits underlie cognitive dysfunction in mouse models of GBA-linked Parkinson's disease and dementia with Lewy bodies.Journal: Nature communicationsIn common: Parkinson's, 2 references
- [5] doi:10.1038/s41531-024-00630-4 [code]
- Neurocognitive correlates of semantic memory navigation in Parkinson's disease.Journal: NPJ Parkinson's diseaseIn common: Parkinson's, 2 references
- [6] doi:10.3390/biomedicines11030683
- Association of Cognitive Deficit with Glutamate and Insulin Signaling in a Rat Model of Parkinson's Disease.Journal: BiomedicinesIn common: Parkinson's, 2 references
- [7] doi:10.1093/braincomms/fcae306 [code]
- Changes in electrophysiological aperiodic activity during cognitive control in Parkinson's disease.Journal: Brain communicationsIn common: Parkinson's, EEG, cognitive, 1 reference
- [8] doi:10.1002/ana.27288 [code]
- Blood α-Synuclein Separates Parkinson's Disease from Dementia with Lewy Bodies.Journal: Annals of neurologyIn common: Parkinson's, 2 references
- [9] doi:10.1038/s41598-024-52276-0
- Integrative analysis of gene expression profiles of substantia nigra identifies potential diagnosis biomarkers in Parkinson's disease.Journal: Scientific reportsIn common: Parkinson's, 2 references
- [10] doi:10.1038/s41598-025-13558-3
- Longitudinal dynamics of clinical and neurophysiological changes in parkinson's disease over four and a half years.Journal: Scientific reportsIn common: Parkinson's, other, 1 reference
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.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 0 scripts, and 0 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:d20618d5e2663ac5…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.3390/brainsci16080781)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.3390/brainsci16080781.svg
:target: https://openscicode.org/badge/doi/10.3390/brainsci16080781
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.3390/brainsci16080781"><img src="https://openscicode.org/badge/doi/10.3390/brainsci16080781.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge 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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
