OSCR

Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification.

Code ↔ Paper

3 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 3 matches
  1. [1] § Results and discussion › Preprocessing ↔ sovaharmony/postprocessingprep.py, lines 16–106 · score 0.93 · 1.5–6 Hz, 10.5–12.5 Hz, 12.5–18.5 Hz, 18.5–21 Hz, 21–30 Hz, 6–8.5 Hz
  2. [2] § Results and discussion › Preprocessing ↔ sovaharmony/metrics/pme.py, lines 567–629 · score 0.93 · 1.5–6 Hz, 10.5–12.5 Hz, 12.5–18.5 Hz, 18.5–21 Hz, 21–30 Hz, 6–8.5 Hz
  3. [3] § Results and discussion › Feature selection ↔ Manipulation/Funciones.py, lines 756–815 · score 0.67 · C8 Mbeta3 Theta, C3 Mbeta3, C5 Mbeta2, cross

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 authors' code

Python · 106 lines · 4.9 KB · no license · 1 match

  1. from sovaflow.utils import cfg_logger
  2. from sovaharmony.preprocessing import get_derivative_path
  3. from sovaharmony.preprocessing import write_json
  4. from bids import BIDSLayout
  5. import mne
  6. import os
  7. from sovaharmony.metrics.features import get_derivative
  8. from sovaharmony.spatial import get_spatial_filter
  9. import time
  10. import traceback
  11. from sovaflow.flow import crop_raw_data
  12. from sovaharmony.utils import _verify_epoch_continuous,_verify_epochs_axes
  13. import numpy as np
  14. from sovareject.tools import format_data
  15. OVERWRITE = False # Ojo con esta variable, es para obligar a sobreescribir los archivos
  16. # en general deberia estar en False
  17. def features(THE_DATASET):
  18. # Inputs not dataset dependent
  19. def_spatial_filter='54x10'
  20. bands ={'delta':(1.5,6),
  21. 'theta':(6,8.5),
  22. 'alpha-1':(8.5,10.5),
  23. 'alpha-2':(10.5,12.5),
  24. 'beta1':(12.5,18.5),
  25. 'beta2':(18.5,21),
  26. 'beta3':(21,30),
  27. 'gamma':(30,45)}
  28. if THE_DATASET.get('spatial_filter',def_spatial_filter):
  29. spatial_filter = get_spatial_filter(THE_DATASET.get('spatial_filter',def_spatial_filter))
  30. input_path = THE_DATASET.get('input_path',None)
  31. layout_dict = THE_DATASET.get('layout',None)
  32. e = 0
  33. archivosconerror = []
  34. # Static Params
  35. pipelabel = '['+THE_DATASET.get('run-label', '')+']'
  36. layout = BIDSLayout(input_path)
  37. bids_root = layout.root
  38. eegs = layout.get(**layout_dict)
  39. pipeline = 'sovaharmony'
  40. derivatives_root = os.path.join(layout.root,'derivatives',pipeline)
  41. log_path = os.path.join(derivatives_root,'code')
  42. os.makedirs(log_path, exist_ok=True)
  43. logger,currentdt = cfg_logger(log_path)
  44. desc_pipeline = "sovaharmony, a harmonization eeg pipeline using the bids standard"
  45. num_files = len(eegs)
  46. for i,eeg_file in enumerate(eegs):
  47. #process=str(i)+'/'+str(num_files)
  48. msg =f"File {i+1} of {num_files} ({(i+1)*100/num_files}%) : {eeg_file}"
  49. logger.info(msg)
  51. prep_path = get_derivative_path(layout,eeg_file,'prep','eeg','.fif',bids_root,derivatives_root)
  53. json_dict = {"Description":desc_pipeline,"RawSources":[eeg_file.replace(bids_root,'')],"Configuration":THE_DATASET}
  55. features_tuples=[
  56. ('power',{'bands':bands}),
  57. ('sl',{'bands':bands}),
  58. ('cohfreq',{'window':3,'bands':bands}),
  59. ('entropy',{'bands':bands,'D':3}),
  60. ('crossfreq',{'bands':bands}),
  61. ]
  62. times_strings = []
  63. for feature,kwargs in features_tuples:
  64. try:
  65. for sf in [None, spatial_filter]: # Channels and Components
  66. #for sf in [spatial_filter]: # Only components
  67. #for norm_ in [True,False]: # Only with huber and without huber
  68. if sf is not None:
  69. sf_label = f'ics[{spatial_filter["name"]}]'
  70. else:
  71. sf_label = 'sensors'
  72. feature_suffix = f'space-{sf_label}_prep_{feature}'
  73. feature_path = get_derivative_path(layout,eeg_file,pipelabel,feature_suffix,'.txt',bids_root,derivatives_root)
  74. os.makedirs(os.path.split(feature_path)[0], exist_ok=True)
  76. if OVERWRITE or not os.path.isfile(feature_path):
  77. signal1 = mne.io.read_raw(prep_path)
  78. start = time.perf_counter()
  79. signal2,_ = format_data(signal1.get_data(),signal1.info['sfreq'],5)#segmentacion por epocas paper de Ximena: 2s , pacho 5s
  80. signal = np.transpose(signal2,(2,0,1))
  81. _verify_epochs_axes(signal,signal2)
  82. signal = mne.EpochsArray(signal, signal1.info)
  83. val_dict = get_derivative(signal,feature=feature,kwargs=kwargs,spatial_filter=sf)
  84. final = time.perf_counter()
  85. tstring = f'TIME {feature_suffix}:::::::::::::::::::{final-start}'
  86. times_strings.append(tstring)
  87. logger.info(tstring)
  88. print(tstring)
  89. write_json(val_dict,feature_path)
  90. write_json(json_dict,feature_path.replace('.txt','.json'))
  91. else:
  92. msg = f'{feature_path}) already existed, skipping...'
  93. logger.info(msg)
  94. print(msg)
  95. except Exception as error:
  96. e+=1
  97. logger.exception(f'Error for {eeg_file}-{feature_path}')
  98. archivosconerror.append((eeg_file,feature_path))
  99. print(error)
  100. print(traceback.format_exc())
  101. logger.exception(error)
  102. logger.exception(traceback.format_exc())
  103. pass
  104. [print(x) for x in times_strings]
  105. [logger.info(x) for x in times_strings]
  106. return

postprocessingprep.py at commit ba7bc95, no license · at the source

Overview

Authors: Verónica Henao Isaza1,2,3, David Aguillon2, Carlos Andrés Tobón-Quintero1, Francisco Lopera2, John Fredy Ochoa-Gómez2,3
ORCID iDs: Verónica Henao Isaza, David Aguillon, John Fredy Ochoa-Gómez
  1. Grupo Neuropsicología y Conducta (GRUNECO), Facultad de Medicina, Universidad de Antioquia (UdeA), Medellín, Colombia
  2. Grupo de Neurociencias de Antioquia (GNA), Facultad de Medicina, Universidad de Antioquia (UdeA), Medellín, Colombia
  3. Semillero de Neurociencias Computacionales (NeuroCo), Facultad de Medicina y Facultad de Ingeniería, Universidad de Antioquia (UdeA), Medellín, Colombia
Institutions: Universidad de Antioquia (Colombia)
Journal: PloS one, volume 21, issue 3, article e0343722
Dates: received 27 August 2025; accepted 10 February 2026; published online 11 March 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1371/journal.pone.0343722 · PMID 41811929 · PMCID PMC12978488 · OpenAlex W7130553955
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: EEG (modality), human (organism), Alzheimer's / dementia (population), clinical / translational (subfield)
Methods: Statistics, Smoothing, state filtering, decompositions, Machine learning, Connectivity, Preprocessing, Spectral & time-frequency, Complexity, Physiology & signal measures
MeSH: Alzheimer Disease*, Electroencephalography*, Aged, Biomarkers, Female, Humans, Male, Propensity Score, Signal Processing, Computer-Assisted (* major topic)
Topic: Dementia and Cognitive Impairment Research (Psychiatry and Mental health, Medicine), according to OpenAlex
Funding: Universidad de Antioquia
Citations: not cited yet (Europe PMC); 37 references in the paper

Abstract

Objective: Dementia, particularly Alzheimer’s disease (AD), constitutes a major global health concern, with AD accounting for approximately 70% of all cases. EEG-based biomarkers hold promise for early identification of individuals at risk; however, small and heterogeneous samples frequently limit generalizability.

Methods: An EEG-based sample enrichment framework was developed by integrating advanced signal processing, component-level feature extraction, data harmonization (neuroHarmonize), and Propensity Score Matching (PSM). EEG data from four independent cohorts were harmonized to reduce site-related variability while preserving covariates such as age and sex. Features including power, entropy, coherence, synchronization likelihood, and cross-frequency coupling were extracted from independent components. PSM was applied at 2:1, 5:1, and 10:1 ratios to expand and balance the control group (HC) relative to the Alzheimer’s risk group (ACr), composed of PSEN1-E280A mutation carriers without cognitive symptoms.

Results: Sample enrichment through PSM improved classification accuracy, with decision tree models yielding values between 0.91 and 0.96. Higher enrichment ratios enhanced model stability and generalizability, as shown by learning curves and confusion matrices. Feature selection was based on model performance and effect sizes (Cohen’s d).

Conclusions: The proposed framework addresses sample size and variability constraints in EEG-based AD risk classification.

Significance: Harmonization and statistical balancing provide a replicable strategy for multicenter EEG studies targeting early AD detection.

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 3 matches between paragraphs and lines of code.

GRUNECO/eeg_harmonization

License: none: the authors keep all their rights
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: ba7bc95f06f9219876bc0a9e0d61e57b2b443766, 5 September 2026
Languages: Python (72), Jupyter (3), Shell (2), R (1), MATLAB (1)
Size: 155 files, 79 scripts
Software Heritage: not archived
Found in: “Data Availability”
Holds: README, environment (requirements.txt, setup.cfg, setup.py), tests, 3 notebooks
Not found: license file, CITATION.cff, continuous integration, documentation
Tools: NumPy (51 files), pandas (42 files), Matplotlib (30 files), seaborn (18 files), SciPy (15 files), MNE-Python (14 files), PyBIDS (10 files), neuroHarmonize (9 files), Pingouin (5 files), Pillow (3 files), YASA (3 files), ggplot2 (2 files), MNE-BIDS (2 files), scikit-learn (2 files), specparam (formerly FOOOF) (2 files), neuroCombat (1 file), rpy2 (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
81 files
At the source: github.com/GRUNECO/eeg_harmonization

GRUNECO/Data_analysis_ML_Harmonization_Proyect

License: none: the authors keep all their rights
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: debf609b243a3a2c9ef9e5608b9a88c866cd24b2, 5 September 2026
Languages: Python (41), Jupyter (3)
Size: 200 files, 44 scripts
Software Heritage: not archived
Found in: “Data Availability”
Holds: README, 3 notebooks
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: pandas (42 files), NumPy (37 files), Matplotlib (31 files), seaborn (22 files), scikit-learn (13 files), SciPy (9 files), Pingouin (8 files), Keras (4 files), Pillow (4 files), MNE-Python (3 files)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
45 files
At the source: github.com/GRUNECO/Data_analysis_ML_Harmonization_Proyect

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:

  • 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 123 scripts, each with its path and the digest of its content;
  • 3 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

Datasets cited

Data Availability

“The publicly available datasets are: CHBMP: https://chbmp-open.loris.ca/ SRM: https://openneuro.org/datasets/ds003775/versions/1.2.1 UdeA1 and UdeA2: https://openneuro.org/datasets/ds007427 The analysis codes are publicly available at: https://github.com/GRUNECO/eeg_harmonization https://github.com/GRUNECO/Data_analysis_ML_Harmonization_Proyect”.

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, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 9 MeSH terms, 1 funder, 32 references.

Cite

This paper

Henao Isaza, V., Aguillon, D., Tobón-Quintero, C. A., Lopera, F., & Ochoa-Gómez, J. F. (2026). Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification. PloS one, 21(3), e0343722. https://doi.org/10.1371/journal.pone.0343722

BibTeX

@article{henaoisaza2026comprehensive,
author = {Henao Isaza, Verónica and Aguillon, David and Tobón-Quintero, Carlos Andrés and Lopera, Francisco and Ochoa-Gómez, John Fredy},
title = {{Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification}},
journal = {PloS one},
year = {2026},
month = mar,
volume = {21},
number = {3},
pages = {e0343722},
publisher = {PLOS},
issn = {1932-6203},
doi = {10.1371/journal.pone.0343722},
url = {https://doi.org/10.1371/journal.pone.0343722},
pmid = {41811929},
pmcid = {PMC12978488}
}

RIS

TY - JOUR
AU - Henao Isaza, Verónica
AU - Aguillon, David
AU - Tobón-Quintero, Carlos Andrés
AU - Lopera, Francisco
AU - Ochoa-Gómez, John Fredy
TI - Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification
T2 - PloS one
J2 - PLoS One
PY - 2026
DA - 2026/03/11
VL - 21
IS - 3
SP - e0343722
SN - 1932-6203
PB - PLOS
DO - 10.1371/journal.pone.0343722
UR - https://doi.org/10.1371/journal.pone.0343722
LA - en
ER -

CSL-JSON

{
"id": "10.1371/journal.pone.0343722",
"type": "article-journal",
"title": "Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification",
"container-title": "PloS one",
"author": [
{
"family": "Henao Isaza",
"given": "Verónica"
},
{
"family": "Aguillon",
"given": "David"
},
{
"family": "Tobón-Quintero",
"given": "Carlos Andrés"
},
{
"family": "Lopera",
"given": "Francisco"
},
{
"family": "Ochoa-Gómez",
"given": "John Fredy"
}
],
"container-title-short": "PLoS One",
"volume": "21",
"issue": "3",
"page": "e0343722",
"DOI": "10.1371/journal.pone.0343722",
"PMID": "41811929",
"PMCID": "PMC12978488",
"ISSN": "1932-6203",
"publisher": "PLOS",
"URL": "https://doi.org/10.1371/journal.pone.0343722",
"language": "en",
"issued": {
"date-parts": [
[
2026,
3,
11
]
]
}
}

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:10.7554/elife.100605 [code]
Age-related changes in ‘cortical’ 1/f dynamics are linked to cardiac activity
Journal: n/a
In common: YASA, MNE-BIDS, specparam (formerly FOOOF), 9 other tools
[2] doi:10.34133/csbj.0042 [code]
Using Steady-State Visual Evoked Potentials to Characterize Wide-Ranging Retinopathy Linked to <i>CRB1</i>: Implications for Clinical Trials.
Journal: Computational and structural biotechnology journal
In common: MNE-BIDS, Pingouin, MNE-Python, 9 other tools, EEG, clinical / translational
[3] doi:10.1038/s42003-026-10205-z [code]
Source-space EEG alpha activity reveals brain age gaps due to neurodegeneration and disparity.
Journal: Communications biology
In common: statsmodels, seaborn, scikit-learn, 4 other tools, Alzheimer's / dementia, EEG, 1 reference, author David Aguillon
[4] doi:10.1038/s41597-026-07377-y [code]
An open-access multi-site fMRI dataset for investigating conscious visual perception.
Journal: Scientific data
In common: MNE-BIDS, Pingouin, MNE-Python, 8 other tools, 1 reference
[5] doi:10.1097/j.pain.0000000000004044 [code]
No effect of rhythmic visual stimulation on experimental pain perception.
Journal: Pain
In common: MNE-BIDS, specparam (formerly FOOOF), Pingouin, 7 other tools, EEG
[6] doi:10.1038/s41597-026-07350-9 [code]
An open multi-center MEG-EEG dataset for studying conscious visual perception.
Journal: Scientific data
In common: MNE-BIDS, Pingouin, MNE-Python, 8 other tools, EEG
[7] doi:10.1162/imag.a.1269 [code]
From early to contemporary normative modeling: Mapping individual differences in neurophysiological signals.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: specparam (formerly FOOOF), Pingouin, MNE-Python, 7 other tools, EEG, 1 reference
[8] doi:10.1007/s00234-026-04103-8 [code]
Enhanced detection of subtle cortical abnormalities in focal epilepsy using 7 T MRI surface-based models and graph neural networks.
Journal: Neuroradiology
In common: neuroCombat, PyBIDS, Pillow, 7 other tools, EEG
[9] doi:10.1093/cercor/bhag113 [code]
Long-term reliability and stability of parameterized resting state EEG: evidence from a five-year follow-up.
Journal: Cerebral cortex (New York, N.Y. : 1991)
In common: MNE-BIDS, specparam (formerly FOOOF), MNE-Python, 7 other tools, EEG
[10] doi:10.1093/nc/niag029 [code]
A data-driven approach to identifying and evaluating connectivity-based neural correlates of conscious visual perception.
Journal: Neuroscience of consciousness
In common: MNE-BIDS, Pingouin, MNE-Python, 8 other tools

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.