OSCR

Serum elemental profile-based machine learning models for Alzheimer's disease identification and cognitive score prediction.

Code ↔ Paper

10 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 10 matches · 2 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § METHODS › Machine learning and regression analysis ↔ exp2/test.py, lines 52–66 · score 1.00 · hidden layer, neural network, DecisionTreeClassifier, GaussianNB, GradientBoostingClassifier, KNeighborsClassifier
  2. [2] § METHODS › Machine learning and regression analysis ↔ exp2/train.py, lines 61–71 · score 0.99 · hidden layer, neural network, DecisionTreeClassifier, GaussianNB, GradientBoostingClassifier, KNeighborsClassifier
  3. [3] § METHODS › Machine learning and regression analysis ↔ exp3/train.py, lines 25–53 · score 0.91 · LinearRegression, RandomForestRegressor, decision tree regression, StandardScaler, dump, RF
  4. [4] § METHODS › Machine learning and regression analysis ↔ exp3/test.py, the whole file · a weak match · score 0.83 · DataFrame, get_dummies, Excel, encoded, Bi, Mo
  5. [5] § METHODS › Machine learning and regression analysis ↔ exp1/test.py, lines 56–82 · score 0.72 · positive class, predicted probabilities, F1 score, AUC, joblib, precision
  6. [6] § METHODS › Machine learning and regression analysis ↔ exp3/test.py, the whole file · a weak match · score 0.70 · StandardScaler, linear regression, decision tree, RF, joblib, fitting
  7. [7] § METHODS › Machine learning and regression analysis ↔ exp3/train.py, lines 25–53 · score 0.63 · random_state, test_size, train_test_split, Regression, MoCA, predict
  8. [8] § METHODS › Machine learning and regression analysis ↔ exp3/train.py, lines 1–22 · score 0.62 · Excel, Bi, Mo, Sr, Cd, Cr
  9. [9] § RESULTS › Machine learning models for AD classification ↔ exp1/test.py, lines 56–82 · score 0.59 · positive class, Confusion matrices, F1 score, AUC, precision, recall
  10. [10] § RESULTS › Characteristics of the study population ↔ exp3/train.py, lines 1–22 · score 0.51 · Bi, Mo, Sr, Cd, Cr, Mg

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 · 53 lines · 2.1 KB · no license · 4 matches

  1. import pandas as pd
  2. import matplotlib.pyplot as plt
  3. from sklearn.model_selection import train_test_split
  4. from sklearn.linear_model import LinearRegression
  5. from sklearn.tree import DecisionTreeRegressor
  6. from sklearn.ensemble import RandomForestRegressor
  7. from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
  8. from sklearn.preprocessing import StandardScaler
  9. import os
  10. import joblib
  12. file_path = '../data.xlsx'
  13. data = pd.read_excel(file_path)
  15. sample_names = data['样品名称']
  17. selected_columns = ['性别', '年龄', 'Mg (ppm)', 'Ca (ppm)', 'Cr (ppb)', 'Mn (ppb)', 'Fe (ppm)',
  18. 'Co (ppb)', 'Ni (ppb)', 'Cu (ppm)', 'Zn (ppm)', 'As (ppb)', 'Se (ppb)', 'Sr (ppb)',
  19. 'Mo (ppb)', 'Cd (ppb)', 'Sn (ppb)', 'Sb (ppb)', 'I (ppb)', 'Hg (ppb)',
  20. 'Pb (ppb)', 'Bi (ppb)', 'Cu/Zn']
  21. features = data[selected_columns]
  22. labels = data['MOCA']
  23. #labels = data['MMSE']
  25. gender_column = pd.get_dummies(features['性别'], prefix='Gender', drop_first=True)
  26. features = pd.concat([features, gender_column], axis=1)
  27. features.drop('性别', axis=1, inplace=True)
  29. X_train, X_test, y_train, y_test, sample_names_train, sample_names_test = train_test_split(features, labels, sample_names, test_size=0.2, random_state=42)
  31. scaler = StandardScaler()
  32. X_train_scaled = scaler.fit_transform(X_train)
  33. X_test_scaled = scaler.transform(X_test)
  35. linear_model = LinearRegression()
  36. linear_model.fit(X_train_scaled, y_train)
  37. y_pred_linear = linear_model.predict(X_test_scaled)
  38. y_pred_linear = y_pred_linear.round().astype(int)
  40. tree_model = DecisionTreeRegressor()
  41. tree_model.fit(X_train_scaled, y_train)
  42. y_pred_tree = tree_model.predict(X_test_scaled)
  43. y_pred_tree = y_pred_tree.round().astype(int)
  45. rf_model = RandomForestRegressor()
  46. rf_model.fit(X_train_scaled, y_train)
  47. y_pred_rf = rf_model.predict(X_test_scaled)
  48. y_pred_rf = y_pred_rf.round().astype(int)
  51. joblib.dump(linear_model, 'D:\mywork/blood_AD\exp2\MOCA_models/linear_model.pkl')
  52. joblib.dump(tree_model, 'D:\mywork/blood_AD\exp2\MOCA_models/tree_model.pkl')
  53. joblib.dump(rf_model, 'D:\mywork/blood_AD\exp2\MOCA_models/rf_model.pkl')

train.py at commit 71bbe33, no license · at the source

Overview

Authors: Haotian Liu1,2,3, Xinnan Liu2,3, Yashuang Chen1, Meng Pan1, Ying Fu2,3, Chao Ma2,3, Wei Ge1
ORCID iDs: Haotian Liu, Wei Ge
  1. Department of Immunology, State Key Laboratory of Complex, Severe, and Rare Diseases, Institute of Basic Medical Sciences & School of Basic Medicine, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
  2. Department of Human Anatomy, Histology and Embryology, Neuroscience Center, Institute of Basic Medical Sciences & School of Basic Medicine, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
  3. National Human Brain Bank for Development and Function, Beijing, China
Institutions: Chinese Academy of Medical Sciences & Peking Union Medical College (China); Institute of Basic Medical Sciences of the Chinese Academy of Medical Sciences
Journal: Neuroprotection (Chichester, England), article 10.1002/nep3.70054
Dates: received 5 December 2025; accepted 2 July 2026; published online 5 August 2026; in print August 2026
Type: Research article · Language: English
License: CC BY-NC
Identifiers: DOI 10.1002/nep3.70054 · PMID 42564343 · PMCID PMC13443228 · OpenAlex W7197029934
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: human (organism), Alzheimer's / dementia (population), clinical / translational (subfield)
Methods: Statistics, Machine learning, Connectivity
Keywords: Alzheimer disease, cognitive impairment, machine learning, serum elemental profiling
Topic: Dementia and Cognitive Impairment Research (Psychiatry and Mental health, Medicine), according to OpenAlex
Funding: National Natural Science Foundation of China (2021ZD0201100, STI2030, 82471222, 82501462); China Postdoctoral Science Foundation (2025M781354); Peking Union Medical College Hospital; Peking Union Medical College; Fundamental Research Funds for the Central Universities
Citations: not cited yet (Europe PMC); 23 references in the paper

Abstract

Background: Current diagnostic approaches for Alzheimer's disease (AD) largely rely on cerebrospinal fluid biomarkers and neuroimaging, which may be invasive, costly, and not readily accessible in routine clinical settings. We investigated whether serum elemental profiling combined with machine learning could provide complementary information for AD identification and exploratory cognitive score prediction.

Methods: This retrospective cross‐sectional study included 874 participants enrolled between 2017 and 2023 from the Brain Aging National Cohort–Peking Union Medical College cohort, comprising 427 cognitively normal controls (NCs) and 447 patients with clinically defined AD. Serum concentrations of 20 elements were quantified by inductively coupled plasma mass spectrometry. Associations between serum element concentrations and AD status were evaluated using age‐ and sex‐adjusted logistic regression models with false discovery rate (FDR) correction. Associations with Mini‐Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) scores were assessed using linear regression models with FDR correction. Machine learning classification models were developed for AD identification, whereas regression models were developed for exploratory MMSE and MoCA score prediction. Model performance was evaluated in an internal hold‐out test set.

Results: Age did not differ significantly between NC and AD participants (66.4 ± 9.9 vs. 67.1 ± 9.0 years; t(872) = −1.13, p = 0.260), whereas the proportion of women was higher in the AD group than in the NC group (255/447 [57.0%] vs. 211/427 [49.4%]; χ 2(1) = 5.11, p = 0.024). MMSE scores were significantly lower in patients with AD than in NC participants (AD: n = 277, median [interquartile range (IQR)] = 24 [19–27]; NC: n = 427, median [IQR] = 30 [30–30]; Mann–Whitney U = 3043.5, p < 0.001), as were MoCA scores (AD: n = 240, median [IQR] = 18.00 [14.00–20.25]; NC: n = 427, median [IQR] = 30 [30.00–30.00]; Mann–Whitney U = 13.5, p < 0.001). After adjustment for age and sex, higher serum lead (Pb) and tin (Sn) levels were associated with increased odds of AD (Pb: odds ratio [OR] = 4.95, 95% confidence interval [CI]: 3.42–7.37; Sn: OR = 1.45, 95% CI: 1.20–1.78), whereas higher serum antimony, nickel, manganese, cobalt, selenium, and calcium levels were associated with lower odds of AD (OR range: 0.50–0.81; all FDR‐adjusted p‐values < 0.05). Among the eight classification models evaluated in the internal hold‐out test set, the random forest model showed the highest apparent performance for distinguishing AD from NC, achieving an accuracy of 88% and an area under the receiver operating (AUC) (acharacteristic curv of 0.94. Among the three regression models evaluated, the random forest regression showed the highest apparent performance for cognitive score prediction, yielding the strongest correlations between predicted and observed scores for both MMSE (r = 0.48, p < 0.001) and MoCA (r = 0.62, p < 0.001).

Conclusion: Serum elemental profiles combined with machine learning may provide a minimally invasive and accessible complementary approach for AD identification and cognitive assessment.

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

Repository

Its files are read in the Code ↔ Paper reader above, with 10 matches between paragraphs and lines of code.

weige347/AD-classifier

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 71bbe33affa42bcc8f9ff66e57cc72fadda47faf, 16 January 2024
Languages: Python (6)
Size: 31 files, 6 scripts
Software Heritage: not archived
Found in: “DATA AVAILABILITY STATEMENT”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: pandas (6 files), scikit-learn (6 files), Matplotlib (5 files), NumPy (4 files), seaborn (4 files)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
7 files
At the source: github.com/weige347/AD-classifier

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;
  • 6 scripts, each with its path and the digest of its content;
  • 10 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 data and code for developing machine learning models are available on GitHub (https://github.com/weige347/AD-classifier). The data and code used for developing the machine learning models are available in a public repository and can be accessed at GitHub: https://github.com/weige347/AD-classifier. Individual‐level clinical data are not publicly available owing to ethical and privacy restrictions.

Reproduced under the paper's license (CC BY-NC), 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 3, 28 September 2026

  • Funding: added National Natural Science Foundation of China: 2021ZD0201100, STI2030, 82471222, 82501462; China Postdoctoral Science Foundation: 2025M781354; Peking Union Medical College Hospital; Peking Union Medical College; Fundamental Research Funds for the Central Universities

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, pages, dates, 7 authors, 4 keywords, 23 references.

Cite

This paper

Liu, H., Liu, X., Chen, Y., Pan, M., Fu, Y., Ma, C., & Ge, W. (2026). Serum elemental profile-based machine learning models for Alzheimer's disease identification and cognitive score prediction. Neuroprotection (Chichester, England), 10.1002/nep3.70054. https://doi.org/10.1002/nep3.70054

BibTeX

@article{liu2026serum,
author = {Liu, Haotian and Liu, Xinnan and Chen, Yashuang and Pan, Meng and Fu, Ying and Ma, Chao and Ge, Wei},
title = {{Serum elemental profile-based machine learning models for Alzheimer's disease identification and cognitive score prediction}},
journal = {Neuroprotection (Chichester, England)},
year = {2026},
month = aug,
pages = {10.1002/nep3.70054},
publisher = {Wiley},
issn = {2770-7296},
doi = {10.1002/nep3.70054},
url = {https://doi.org/10.1002/nep3.70054},
pmid = {42564343},
pmcid = {PMC13443228}
}

RIS

TY - JOUR
AU - Liu, Haotian
AU - Liu, Xinnan
AU - Chen, Yashuang
AU - Pan, Meng
AU - Fu, Ying
AU - Ma, Chao
AU - Ge, Wei
TI - Serum elemental profile-based machine learning models for Alzheimer's disease identification and cognitive score prediction
T2 - Neuroprotection (Chichester, England)
J2 - Neuroprotection
PY - 2026
DA - 2026/08/05
SP - 10.1002/nep3.70054
SN - 2770-7296
PB - Wiley
DO - 10.1002/nep3.70054
UR - https://doi.org/10.1002/nep3.70054
LA - en
ER -

CSL-JSON

{
"id": "10.1002/nep3.70054",
"type": "article-journal",
"title": "Serum elemental profile-based machine learning models for Alzheimer's disease identification and cognitive score prediction",
"container-title": "Neuroprotection (Chichester, England)",
"author": [
{
"family": "Liu",
"given": "Haotian"
},
{
"family": "Liu",
"given": "Xinnan"
},
{
"family": "Chen",
"given": "Yashuang"
},
{
"family": "Pan",
"given": "Meng"
},
{
"family": "Fu",
"given": "Ying"
},
{
"family": "Ma",
"given": "Chao"
},
{
"family": "Ge",
"given": "Wei"
}
],
"container-title-short": "Neuroprotection",
"page": "10.1002/nep3.70054",
"DOI": "10.1002/nep3.70054",
"PMID": "42564343",
"PMCID": "PMC13443228",
"ISSN": "2770-7296",
"publisher": "Wiley",
"URL": "https://doi.org/10.1002/nep3.70054",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
5
]
]
}
}

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:10.64898/2026.05.06.26352540 [code]
Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning
Journal: medRxiv (preprint)
In common: seaborn, scikit-learn, pandas, 2 other tools, Alzheimer's / dementia, clinical / translational, 1 reference
[2] doi:10.1016/j.tjpad.2026.100646 [code]
Quantifying generalization error in machine learning prediction of cognitive decline.
Journal: The journal of prevention of Alzheimer's disease
In common: seaborn, scikit-learn, pandas, 2 other tools, Alzheimer's / dementia, 1 reference
[3] doi:10.1038/s41514-026-00391-9 [code]
Region-specific transcriptional signatures of brain aging in the absence of neuropathology at the single-cell level.
Journal: npj aging
In common: seaborn, scikit-learn, pandas, 2 other tools, 1 reference
[4] doi:10.3389/fninf.2026.1799307
FUSION-AD: interpretable AI framework for risk assessment and subgroup discovery in Alzheimer's disease.
Journal: Frontiers in neuroinformatics
In common: Alzheimer's / dementia, 2 references
[5] doi:10.1002/hbm.70508 [code]
Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET.
Journal: Human brain mapping
In common: NumPy, Alzheimer's / dementia, 1 reference
[6] doi:10.1002/alz.71711 [code]
Exploring longitudinal relationships among Alzheimer's disease biomarkers.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: Alzheimer's / dementia, clinical / translational, 1 reference
[7] doi:10.1007/s10103-026-04962-w
Comparative efficacy and safety of photobiomodulation, transcranial direct current stimulation, and repetitive transcranial magnetic stimulation in Alzheimer's disease: a network meta-analysis of randomized controlled trials.
Journal: Lasers in medical science
In common: Alzheimer's / dementia, clinical / translational, 1 reference
[8] doi:10.3389/fnagi.2026.1862742
A brief checklist of modifiable dementia risk factors (RF12): associations with cognitive and affective measures in an Italian cohort.
Journal: Frontiers in aging neuroscience
In common: Alzheimer's / dementia, clinical / translational, 1 reference
[9] doi:10.1002/dad2.70484
AST/ALT, &lt;i&gt;APOE&lt;/i&gt; ε4, and Alzheimer's disease progression: A longitudinal cohort study.
Journal: Alzheimer's & dementia (Amsterdam, Netherlands)
In common: Alzheimer's / dementia, clinical / translational, 1 reference
[10] doi:10.11817/j.issn.1672-7347.2026.260137 [code]
Life&lt;b&gt;'&lt;/b&gt;s Essential 10 and brain health: A prospective cohort study.
Journal: Zhong nan da xue xue bao. Yi xue ban = Journal of Central South University. Medical sciences
In common: Alzheimer's / dementia, clinical / translational, 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.