OSCR

Neural Response to Familiar Names Predicts Outcome of Comatose ICU Patients: A Prospective Observational Cohort Study.

Code ↔ Paper

6 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 6 matches
  1. [1] § Methods › Outcome prediction model ↔ Python_script/train/LDA_model_run.py, lines 50–127 · score 0.75 · LDA model, predicted probability, oversampling, split, accuracy, training
  2. [2] § Methods › Outcome prediction model ↔ Python_script/train/LDA_model_run.py, lines 50–127 · score 0.67 · predicted probabilities, ROC, curves, accuracy, AUC, training
  3. [3] § Methods › Outcome prediction model ↔ Python_script/train/LDA_model_run.py, lines 1–48 · score 0.57 · GCS score, LDA, Hz, age, months, model
  4. [4] § Methods › EEG recording and processing ↔ Matlab_script/singleSubPreprocessing.m, lines 51–54 · score 0.56 · bad channels, spherical, EEGLAB, preprocessing
  5. [5] § Results › Neural responses to names and acoustic control ↔ Matlab_script/Fig2_violin_plot.m, lines 1–56 · score 0.56 · FDR corrected, acoustic control, EEG response, IQR, coma, bootstrap
  6. [6] § Results › Predicting patient outcomes using EEG name responses ↔ Python_script/train/LDA_model_run.py, lines 1–48 · score 0.56 · clinical model, GCS score, Glasgow, training, age, classification

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 · 129 lines · 6.2 KB · no license · 4 matches

  1. import pandas as pd
  2. import numpy as np
  3. import os
  4. from sklearn.metrics import confusion_matrix, accuracy_score, roc_auc_score, roc_curve
  5. from sklearn.model_selection import GridSearchCV, LeaveOneOut
  6. from imblearn.pipeline import Pipeline
  7. from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
  8. from sklearn.preprocessing import StandardScaler
  9. import itertools
  10. from datetime import datetime
  11. from sklearn.model_selection import train_test_split
  12. from imblearn.over_sampling import RandomOverSampler
  13. from tqdm import tqdm
  15. base_dir = os.path.dirname(os.path.abspath(__file__))
  16. print(base_dir)
  18. data_path = os.path.join(base_dir, '..', '..', 'data', 'data.csv')
  19. result_path = os.path.join(base_dir, '..', 'result')
  21. """
  22. Classification Targets
  23. GOSE_1M_C3: Glasgow Outcome Scale Extended (GOSE) score at 1-month follow-up, with a binary threshold set at 2/3 to categorize outcomes.
  24. """
  26. classification_cols = [
  27. 'GOSE_1M_C2', 'GOSE_3M_C2', 'GOSE_6M_C2',
  28. 'GOSE_1M_C3', 'GOSE_3M_C3', 'GOSE_6M_C3',
  29. 'GOSE_1M_C4', 'GOSE_3M_C4', 'GOSE_6M_C4']
  31. """
  32. Feature names: Each list of feature names corresponds to different input sets used for model training.
  33. Clinical Model: Age, Etiology, GCS_score
  34. EEG Name Model: P1N1_name_1.3Hz, P1N1_diff_1.3Hz, P1N1_name_2.7Hz, P1N1_diff_2.7Hz, P1N1_name_4Hz, P1N1_diff_4Hz
  35. Clinical + EEG Name Model: combine all the features mentioned above
  36. """
  38. feature_names = [
  39. # ['Age', 'Etiology', 'GCS_score'],
  40. # ['P1N1_name_1.3Hz', 'P1N1_diff_1.3Hz', 'P1N1_name_2.7Hz', 'P1N1_diff_2.7Hz', 'P1N1_name_4Hz', 'P1N1_diff_4Hz'],
  41. ['Age', 'Etiology', 'GCS_score', 'P1N1_name_1.3Hz', 'P1N1_diff_1.3Hz', 'P1N1_name_2.7Hz', 'P1N1_diff_2.7Hz', 'P1N1_name_4Hz', 'P1N1_diff_4Hz'],
  43. ]
  44. method = 'LDA'
  45. num_runs = 1000 # Repetition time
  46. rs = 40 # Reproducible
  47. combinations = list(itertools.product(classification_cols, feature_names))
  48. data = pd.read_csv(data_path).reset_index()
  50. # model training and test
  51. for classification_col, feature_name in combinations:
  52. print('Start:', datetime.now(), classification_col, feature_name)
  53. feature = data[feature_name]
  54. target = data[classification_col]
  55. indices = np.arange(len(feature))
  56. stratify_var = data['Etiology'].astype(str) + "_" + target.astype(str)
  57. feature_train, feature_test, target_train, target_test, index_train, index_test = train_test_split(feature, target, indices, test_size=0.4, stratify=stratify_var, random_state=40)
  58. cv = LeaveOneOut()
  60. # Define the classifier and its grid of searching parameters
  61. classifier_c = LDA
  62. param_grid = {
  63. 'classifier__solver': ['lsqr'],
  64. 'classifier__shrinkage': ['auto', 10e-4, 10e-3, 10e-2, 10e-1],
  65. }
  66. classifier = classifier_c()
  67. preprocessor = StandardScaler()
  69. pred_prob_train_all = []
  70. pred_prob_test_all = []
  71. for i_run in tqdm(range(num_runs)):
  72. # Create the pipeline with preprocessing, oversampling, and classifier
  73. pipeline = Pipeline([
  74. ('scaler', preprocessor),
  75. ('oversample', RandomOverSampler(sampling_strategy='auto', random_state=rs + i_run)),
  76. ('classifier', classifier)])
  78. # Perform Grid Search to find the best hyperparameters for the model
  79. grid_search = GridSearchCV(estimator=pipeline, param_grid=param_grid, scoring='accuracy', cv=cv, n_jobs=-1, verbose=0)
  80. grid_search.fit(feature_train, target_train)
  82. best_model = grid_search.best_estimator_
  83. i_pred_prob_train = best_model.predict_proba(feature_train)[:, 1]
  84. i_pred_prob_test = best_model.predict_proba(feature_test)[:, 1]
  85. pred_prob_train_all.append(i_pred_prob_train)
  86. pred_prob_test_all.append(i_pred_prob_test)
  88. pred_prob_train = np.mean(pred_prob_train_all, axis=0)
  89. pred_prob_test = np.mean(pred_prob_test_all, axis=0)
  90. fpr, tpr, thresholds = roc_curve(target_train, pred_prob_train)
  92. optimal_threshold_index = np.argmax(tpr - fpr)
  93. optimal_threshold = thresholds[optimal_threshold_index]
  95. pred_train = (pred_prob_train >= optimal_threshold).astype(int)
  96. pred_test = (pred_prob_test >= optimal_threshold).astype(int)
  98. # Calculate training performance
  99. roc_auc_train = roc_auc_score(target_train, pred_prob_train)
  100. accuracy_train = accuracy_score(target_train, pred_train)
  101. tn_train, fp_train, fn_train, tp_train = confusion_matrix(target_train, pred_train).ravel()
  102. sensitivity_train = (tp_train / (tp_train + fn_train))
  103. specificity_train = (tn_train / (tn_train + fp_train))
  105. # Calculate test performance
  106. roc_auc_test = roc_auc_score(target_test, pred_prob_test)
  107. accuracy_test = accuracy_score(target_test, pred_test)
  108. tn_test, fp_test, fn_test, tp_test = confusion_matrix(target_test, pred_test).ravel()
  109. sensitivity_test = (tp_test / (tp_test + fn_test))
  110. specificity_test = (tn_test / (tn_test + fp_test))
  112. print('Train: AUC', roc_auc_train, 'Accuracy', accuracy_train, 'sensitivity', sensitivity_train, 'specificity', specificity_train, 'thre', optimal_threshold)
  113. print('Test: AUC', roc_auc_test, 'Accuracy', accuracy_test, 'sensitivity', sensitivity_test, 'specificity', specificity_test, 'thre', optimal_threshold)
  115. run_name = '+'.join(feature_name)
  116. experiment = f'{method}_{run_name}_{classification_col}'
  117. result_save_path = os.path.join(result_path, experiment)
  118. os.makedirs(result_save_path, exist_ok=True)
  119. np.savez(
  120. os.path.join(result_save_path, 'result'), feature_name=feature_name,
  121. target_train=target_train, pred_train=pred_train, pred_prob_train=pred_prob_train, index_train=index_train,
  122. target_test=target_test, pred_test=pred_test, pred_prob_test=pred_prob_test, index_test=index_test,
  123. optimal_threshold=optimal_threshold,
  124. tn_train=tn_train, fp_train=fp_train, fn_train=fn_train, tp_train=tp_train, roc_auc_train=roc_auc_train, accuracy_train=accuracy_train, sensitivity_train=sensitivity_train, specificity_train=specificity_train,
  125. tn_test=tn_test, fp_test=fp_test, fn_test=fn_test, tp_test=tp_test, roc_auc_test=roc_auc_test, accuracy_test=accuracy_test, sensitivity_test=sensitivity_test, specificity_test=specificity_test,
  126. pred_prob_train_all=pred_prob_train_all, pred_prob_test_all=pred_prob_test_all
  127. )

LDA_model_run.py, no license · at the source

Overview

Authors: Min Wu1,2, Yujia Di3, Sheng Kuang4, Jun Hu1, Jie Zhang5, Kang Wang1, Jingchen Zhang6, Chunyou Chen7, Jiajia Zhou1, Tong Li6, Benyan Luo1,8, Nai Ding3,8,9
ORCID iDs: Benyan Luo, Nai Ding
  1. Department of Neurology, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
  2. Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
  3. Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China
  4. The D-Lab, Department of Precision Medicine, GROW – Research Institute of Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
  5. Centre for Rehabilitation Medicine, Rehabilitation and Sports Medicine Research Institute of Zhejiang Province, Department of Rehabilitation Medicine, Zhejiang Provincial People’s Hospital, Hangzhou Medical College, Hangzhou, China
  6. Department of Critical Care Medicine, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
  7. Department of Neurology, the First People’s Hospital of Wenling, Wenling, China
  8. State Key Lab of Brain-Machine Intelligence, MOE Frontier Science Center for Brain Science and Brain–Machine Integration, Zhejiang University, Hangzhou, China
  9. Innovation Center for Smart Medical Technologies & Devices, Binjiang Institute of Zhejiang University, Hangzhou, China
Institutions: University of Oxford (United Kingdom); Wellcome Centre for Integrative Neuroimaging (United Kingdom); First Affiliated Hospital Zhejiang University (China); Zhejiang University (China); Maastricht University (Netherlands); Zhejiang Provincial People's Hospital (China); Hangzhou Medical College (China); The First People's Hospital of Wenling (China)
Journal: Nature communications, volume 17, issue 1, article 7161
Dates: received 4 February 2026; accepted 20 May 2026; published online 4 June 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41467-026-73878-4 · PMID 42236468 · PMCID PMC13396180 · OpenAlex W7163448874
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: EEG (modality), human (organism), other condition (population), clinical / translational (subfield)
Methods: Spectral & time-frequency, Connectivity, Statistics, Smoothing, state filtering, decompositions, Machine learning, Preprocessing, Physiology & signal measures
Keywords: Prognostic markers, Disorders of consciousness, Electroencephalography - EEG, Machine learning
MeSH: Brain Injuries*, Coma*, Adult, Aged, Electroencephalography, Female, Glasgow Coma Scale, Glasgow Outcome Scale, Humans, Intensive Care Units, Machine Learning, Male, Middle Aged, Prognosis, Prospective Studies (* major topic)
Topic: Neurobiology of Language and Bilingualism (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: Natural Science Foundation of Zhejiang Province (LQN26H090007)
Citations: not cited yet (Europe PMC); 61 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 6 matches between paragraphs and lines of code.

OSF nr9aq

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Languages: MATLAB (13), Python (1)
Size: 23 files, 14 scripts
Software Heritage: not checked
Found in: “Code availability”
Holds: environment (Python_script/requirements.txt)
Not found: README, license file, CITATION.cff, tests, continuous integration, documentation
Tools: Statistics and Machine Learning Toolbox (3 files), EEGLAB (1 file), ERPLAB (1 file), fdr_bh (Benjamini-Hochberg FDR) (1 file), ICLabel (1 file), imbalanced-learn (1 file), Curve Fitting Toolbox (1 file), NumPy (1 file), pandas (1 file), scikit-learn (1 file), Violinplot-Matlab (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)
  • 27 September 2026: the link answers (HTTP 200)
14 files
At the source: osf.io/nr9aq/

Code availability statement

The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-73878-4.

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;
  • 14 scripts, each with its path and the digest of its content;
  • 6 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 availability statement

The paper has a data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

  • no repository, dataset or request procedure was recognized in it

Read it in the paper: doi.org/10.1038/s41467-026-73878-4.

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, 12 authors, 4 keywords, 15 MeSH terms, 1 funder, 60 references.

Cite

This paper

Wu, M., Di, Y., Kuang, S., Hu, J., Zhang, J., Wang, K., Zhang, J., Chen, C., Zhou, J., Li, T., Luo, B., & Ding, N. (2026). Neural Response to Familiar Names Predicts Outcome of Comatose ICU Patients: A Prospective Observational Cohort Study. Nature communications, 17(1), 7161. https://doi.org/10.1038/s41467-026-73878-4

BibTeX

@article{wu2026neural,
author = {Wu, Min and Di, Yujia and Kuang, Sheng and Hu, Jun and Zhang, Jie and Wang, Kang and Zhang, Jingchen and Chen, Chunyou and Zhou, Jiajia and Li, Tong and Luo, Benyan and Ding, Nai},
title = {{Neural Response to Familiar Names Predicts Outcome of Comatose ICU Patients: A Prospective Observational Cohort Study}},
journal = {Nature communications},
year = {2026},
month = jun,
volume = {17},
number = {1},
pages = {7161},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/s41467-026-73878-4},
url = {https://doi.org/10.1038/s41467-026-73878-4},
pmid = {42236468},
pmcid = {PMC13396180}
}

RIS

TY - JOUR
AU - Wu, Min
AU - Di, Yujia
AU - Kuang, Sheng
AU - Hu, Jun
AU - Zhang, Jie
AU - Wang, Kang
AU - Zhang, Jingchen
AU - Chen, Chunyou
AU - Zhou, Jiajia
AU - Li, Tong
AU - Luo, Benyan
AU - Ding, Nai
TI - Neural Response to Familiar Names Predicts Outcome of Comatose ICU Patients: A Prospective Observational Cohort Study
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/06/04
VL - 17
IS - 1
SP - 7161
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/s41467-026-73878-4
UR - https://doi.org/10.1038/s41467-026-73878-4
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41467-026-73878-4",
"type": "article-journal",
"title": "Neural Response to Familiar Names Predicts Outcome of Comatose ICU Patients: A Prospective Observational Cohort Study",
"container-title": "Nature communications",
"author": [
{
"family": "Wu",
"given": "Min"
},
{
"family": "Di",
"given": "Yujia"
},
{
"family": "Kuang",
"given": "Sheng"
},
{
"family": "Hu",
"given": "Jun"
},
{
"family": "Zhang",
"given": "Jie"
},
{
"family": "Wang",
"given": "Kang"
},
{
"family": "Zhang",
"given": "Jingchen"
},
{
"family": "Chen",
"given": "Chunyou"
},
{
"family": "Zhou",
"given": "Jiajia"
},
{
"family": "Li",
"given": "Tong"
},
{
"family": "Luo",
"given": "Benyan"
},
{
"family": "Ding",
"given": "Nai"
}
],
"container-title-short": "Nat Commun",
"volume": "17",
"issue": "1",
"page": "7161",
"DOI": "10.1038/s41467-026-73878-4",
"PMID": "42236468",
"PMCID": "PMC13396180",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41467-026-73878-4",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
4
]
]
}
}

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:10.1162/imag.a.1229 [code]
40 Hz audiovisual stimulation improves sustained attention and related brain oscillations.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: ERPLAB, Violinplot-Matlab, fdr_bh (Benjamini-Hochberg FDR), 5 other tools, EEG
[2] doi:10.1186/s12967-026-08108-y [code]
An explainable multimodal machine learning model for diagnosing disorders of consciousness: evidence from a large multicenter Chinese cohort.
Journal: Journal of translational medicine
In common: ICLabel, pandas, NumPy, EEG, other condition, 1 reference, author Benyan Luo
[3] doi:10.1038/s41598-026-47785-z [code]
Modulations of the P3b effect as a function of bilingual language experience.
Journal: Scientific reports
In common: ERPLAB, ICLabel, EEGLAB, 1 other tool, EEG, 2 references
[4] doi:10.1038/s41598-026-56070-y [code]
SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG.
Journal: Scientific reports
In common: ICLabel, EEGLAB, Statistics and Machine Learning Toolbox, 3 other tools, EEG, 2 references
[5] doi:10.1111/cogs.70220 [code]
Shared Neural Computations for Syntactic and Morphological Structures: Evidence From Mandarin Chinese.
Journal: Cognitive science
In common: ERPLAB, fdr_bh (Benjamini-Hochberg FDR), EEGLAB, 1 other tool, EEG, 1 reference
[6] doi:10.1038/s41593-026-02357-2 [code]
Experience reorganizes content-specific memory traces in macaques.
Journal: Nature neuroscience
In common: fdr_bh (Benjamini-Hochberg FDR), Curve Fitting Toolbox, EEGLAB, 4 other tools
[7] doi:10.1523/eneuro.0069-26.2026 [code]
Electrophysiological Indices of Hierarchical Speech Processing Differentially Reflect the Comprehension of Speech in Noise.
Journal: eNeuro
In common: ICLabel, EEGLAB, Statistics and Machine Learning Toolbox, EEG, 3 references
[8] doi:10.1371/journal.pone.0353990 [code]
Positive mood enhances accessibility of unrelated concepts in the first language but not in the foreign language.
Journal: PloS one
In common: ERPLAB, ICLabel, EEGLAB, EEG, 2 references
[9] doi:10.1016/j.isci.2026.115375 [code]
Bursts of regional cortical inhibition during smartphone use.
Journal: iScience
In common: ICLabel, EEGLAB, Statistics and Machine Learning Toolbox, 3 other tools, 2 references
[10] doi:10.7554/elife.107088 [code]
Development of auditory and spontaneous movement responses to music over the first postnatal year.
Journal: eLife
In common: ICLabel, EEGLAB, Statistics and Machine Learning Toolbox, 3 other tools, EEG, 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.

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.