OSCR

Mild cognitive impairment cases affect the predictive power of Alzheimer's disease diagnostic models using routine clinical variables.

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 of them tie a paragraph to a whole file, not to given lines: a weak match, whose lines are not tinted
  1. [1] § Results › Feature selection does not improve the predictive performance of CatBoost for identifying MCI and AD patients ↔ .virtual_documents/code/Experiment_1.3.ipynb, the whole file · a weak match · score 0.56 · GDHOPE, PTMARRY, GDBORED, HMT16, HMT8, GDDROP
  2. [2] § Methods › Model evaluation and leakage control ↔ code/shap.R, lines 38–74 · score 0.54 · multi class models, SHAP, loop, predictive
  3. [3] § Methods › Statistical analyses and machine learning ↔ code/Experiment.2.Feature_Selection_Model.ipynb, lines 278–292 · score 0.54 · hierarchical cluster dendrogram, distance, proximity, PC2, PCA, models
  4. [4] § Methods › Statistical analyses and machine learning ↔ .virtual_documents/code/Experiment.1.Baseline_Model_for_3_classes.ipynb, lines 1–64 · score 0.52 · L2, boosting, depth, iterations, leaf, resampled
  5. [5] § Methods › Statistical analyses and machine learning ↔ .virtual_documents/code/Untitled.ipynb, lines 61–130 · score 0.51 · L2, boosting, depth, iterations, leaf, resampled
  6. [6] § Methods › Statistical analyses and machine learning ↔ .virtual_documents/code/Clustering_1.ipynb, lines 196–238 · score 0.51 · hierarchical cluster dendrogram, distance, PCA, healthy

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

Jupyter notebook · 72 lines · 2.1 KB · no license · 1 match

  1. import pandas as pd
  2. import numpy as np
  3. from sklearn.model_selection import train_test_split
  4. from sklearn import metrics
  5. from imblearn.over_sampling import SMOTE
  6. import optuna
  7. from optuna.samplers import TPESampler
  8. from sklearn.preprocessing import StandardScaler
  9. from sklearn.model_selection import StratifiedKFold
  10. from sklearn.metrics import classification_report, accuracy_score, confusion_matrix, multilabel_confusion_matrix, roc_curve, auc, precision_score,recall_score,make_scorer,roc_auc_score
  11. import matplotlib.pyplot as plt
  12. import shap
  13. from sklearn.preprocessing import PolynomialFeatures
  14. from catboost import CatBoostClassifier
  15. import funcs
  16. from scipy.stats import f_oneway, kruskal, pointbiserialr
  19. data = pd.read_csv("../objects/df_imputed_not_complete_874.csv", index_col=0)
  20. data.head()
  23. mci = pd.read_csv("../objects/MCI.csv", index_col=0)
  26. mci1 = mci[mci['cluster'] == 'MCI3']['RID'].to_list()
  29. data = data[~data['RID'].isin(mci1)]
  32. data['DIAGNOSIS'].value_counts()
  35. outcome = data['DIAGNOSIS']
  36. data.drop(['RID', 'DIAGNOSIS'], axis = 1, inplace=True)
  39. outcome_mapping = {"Control": 0,
  40. "MCI": 1,
  41. "AZ": 2}
  42. outcome = outcome.map(outcome_mapping)
  45. X, X_test, y, y_test = train_test_split(data, outcome, test_size=0.2, random_state=43)
  48. smote_over = SMOTE(random_state=44)
  49. X, y = smote_over.fit_resample(X, y)
  52. best_params_filter_based = {'iterations': 1800, 'learning_rate': 0.20649746303659136, 'l2_leaf_reg': 4.37841702433753, 'bagging_temperature': 1.6766419657563723, 'random_strength': 1.9555985333019168, 'depth': 7, 'min_data_in_leaf': 91, 'colsample_bylevel': 0.9759404466998405}
  55. feat = ["PTEDUCAT", "PTMARRY", "VSPULSE", "NXGAIT", "LIMMTOTAL", "LDELTOTAL", "MHPSYCH", "GDBORED", "GDDROP", "GDMEMORY", "GDHOPE", "GDBETTER", "HMT15", "HMT16", "HMT8", "apoe"]
  58. final_model = CatBoostClassifier(**best_params_filter_based, loss_function="MultiClass", verbose=False)
  61. X_corr = X[feat]
  62. X_test_corr = X_test[feat]
  65. final_model.fit(X_corr, y)
  68. predictions = final_model.predict(X_test_corr)
  69. predictions_proba = final_model.predict_proba(X_test_corr)
  72. funcs.metrics_merged(y_test, predictions, predictions_proba)

Experiment_1.3.ipynb at commit d009f98, no license · at the source

Overview

Authors: Caitlin A. Finney1,2, Artur Shvetcov1,2
ORCID iDs: Caitlin A. Finney, Artur Shvetcov
  1. Neurodegeneration and Disease Modelling Lab, Westmead Institute for Medical Research, The University of Sydney,Westmead, NSW Australia
  2. School of Medical Sciences, Faculty of Medicine and Health, The University of Sydney,Sydney, NSW Australia
Institutions: The University of Sydney (Australia)
Journal: npj aging, volume 12, issue 1, article 87
Dates: received 20 December 2025; accepted 12 April 2026; published online 21 April 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41514-026-00390-w · PMID 42014714 · PMCID PMC13284375 · OpenAlex W4407204496
Open access: hybrid, a free copy (OpenAlex)
Preprint: doi:10.1101/2025.02.04.25321694
Status: code verified
Categories: human (organism), Alzheimer's / dementia (population), clinical / translational (subfield)
Methods: Connectivity, Smoothing, state filtering, decompositions, Machine learning, Statistics
Keywords: Diseases, Health care, Medical research, Neurology, Neuroscience
Topic: Dementia and Cognitive Impairment Research (Psychiatry and Mental health, Medicine), according to OpenAlex
Funding: Cooley's Anemia Foundation; Alzheimer's Disease Neuroimaging Initiative
Citations: cited by 1 paper (Europe PMC); 84 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.

Art83/adni_mci

License: none: the authors keep all their rights
State: the link answers, verified on 29 September 2026
Evidence: files inventoried
Commit: d009f98c3801aa038e8e5183f238b8686f58aac4, 5 February 2025
Languages: Jupyter (12), Python (2), R (2)
Size: 54 files, 16 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README, 7 notebooks
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (14 files), pandas (14 files), scikit-learn (14 files), Matplotlib (12 files), imbalanced-learn (10 files), SciPy (7 files), seaborn (5 files), ggplot2 (2 files), SHAP (2 files), tidyverse (2 files)
Availability: 1 check, the latest on 29 September 2026: the link answers
  • 29 September 2026: the link answers
17 files
At the source: github.com/Art83/adni_mci

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/s41514-026-00390-w.

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;
  • 16 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/s41514-026-00390-w.

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, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 5 keywords, 2 funders, 79 references.

Cite

This paper

Finney, C. A., & Shvetcov, A. (2026). Mild cognitive impairment cases affect the predictive power of Alzheimer's disease diagnostic models using routine clinical variables. npj aging, 12(1), 87. https://doi.org/10.1038/s41514-026-00390-w

BibTeX

@article{finney2026mild,
author = {Finney, Caitlin A. and Shvetcov, Artur},
title = {{Mild cognitive impairment cases affect the predictive power of Alzheimer's disease diagnostic models using routine clinical variables}},
journal = {npj aging},
year = {2026},
month = apr,
volume = {12},
number = {1},
pages = {87},
publisher = {Nature Publishing Group},
issn = {2731-6068},
doi = {10.1038/s41514-026-00390-w},
url = {https://doi.org/10.1038/s41514-026-00390-w},
pmid = {42014714},
pmcid = {PMC13284375}
}

RIS

TY - JOUR
AU - Finney, Caitlin A.
AU - Shvetcov, Artur
TI - Mild cognitive impairment cases affect the predictive power of Alzheimer's disease diagnostic models using routine clinical variables
T2 - npj aging
J2 - NPJ Aging
PY - 2026
DA - 2026/04/21
VL - 12
IS - 1
SP - 87
SN - 2731-6068
PB - Nature Publishing Group
DO - 10.1038/s41514-026-00390-w
UR - https://doi.org/10.1038/s41514-026-00390-w
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41514-026-00390-w",
"type": "article-journal",
"title": "Mild cognitive impairment cases affect the predictive power of Alzheimer's disease diagnostic models using routine clinical variables",
"container-title": "npj aging",
"author": [
{
"family": "Finney",
"given": "Caitlin A."
},
{
"family": "Shvetcov",
"given": "Artur"
}
],
"container-title-short": "NPJ Aging",
"volume": "12",
"issue": "1",
"page": "87",
"DOI": "10.1038/s41514-026-00390-w",
"PMID": "42014714",
"PMCID": "PMC13284375",
"ISSN": "2731-6068",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41514-026-00390-w",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
21
]
]
}
}

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:10.1016/j.isci.2026.115329 [code]
Brain metastases converge on shared geometric architecture and transcriptomic landscape yet remain distinct from gliomas.
Journal: iScience
In common: imbalanced-learn, SHAP, ggplot2, 7 other tools, clinical / translational
[2] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: imbalanced-learn, SHAP, ggplot2, 7 other tools
[3] doi:10.1016/j.nicl.2026.104012 [code]
Structural-functional multilayer brain network properties and outcome of combined repetitive transcranial magnetic stimulation and psychotherapy for obsessive-compulsive disorder.
Journal: NeuroImage. Clinical
In common: imbalanced-learn, SHAP, ggplot2, 7 other tools
[4] doi:10.1073/pnas.2516601123 [code]
Unveiling the glymphatic system's role in brain aging: A comprehensive biomarker and modifiable intervention target.
Journal: Proceedings of the National Academy of Sciences of the United States of America
In common: SHAP, ggplot2, seaborn, 6 other tools, clinical / translational, 1 reference
[5] doi:10.1186/s13059-026-04125-8 [code]
MLMarker: a machine learning framework for tissue inference and biomarker discovery.
Journal: Genome biology
In common: imbalanced-learn, SHAP, seaborn, 6 other tools
[6] doi:10.1038/s43856-026-01606-6 [code]
Validation of remote multimodal AI screening for Parkinson disease across diverse settings.
Journal: Communications medicine
In common: imbalanced-learn, SHAP, seaborn, 5 other tools, clinical / translational
[7] doi:10.1038/s41598-026-47047-y [code]
Imaging-genetics-based dementia risk prediction using deep survival neural networks in the Rotterdam Study.
Journal: Scientific reports
In common: SHAP, seaborn, scikit-learn, 4 other tools, Alzheimer's / dementia, clinical / translational, 1 reference
[8] doi:10.1038/s41467-026-76837-1 [code]
Drug screen and machine learning predict neuroprotective agents in a preclinical human model of childhood dementia.
Journal: Nature communications
In common: SHAP, ggplot2, seaborn, 6 other tools, Alzheimer's / dementia
[9] doi:10.3390/s26175327 [code]
Subject Identity Confounds qEEG Emotion Recognition on DEAP and DREAMER.
Journal: Sensors (Basel, Switzerland)
In common: imbalanced-learn, SHAP, seaborn, 5 other tools
[10] doi:10.1038/s41598-026-56688-y [code]
On the value of radiomics in addition to clinical measures in emotional conflict fMRI for predicting sertraline response in major depressive disorder.
Journal: Scientific reports
In common: imbalanced-learn, SHAP, seaborn, 5 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.