Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 74 of the 74 references it cites were found in a registry or an index.

Cognitive performance classification of older patients using machine learning and electronic medical records

Open access
Richter-Laskowska, Monika, Sobotnicka, Ewelina, Bednorz, Adam · 2025 · Scientific Reports

Published version of a preprint

Abstract

Dementia rates are projected to increase significantly by 2050, posing considerable challenges for healthcare systems worldwide. Developing efficient diagnostic tools is critical, and machine learning (ML) algorithms have shown potential for improving the accuracy of cognitive impairment classification. This study aims to address challenges in current systems by leveraging readily available electronic medical record (EMR) data to simplify and enhance the classification of cognitive impairment. The analysis includes 283 older adults, categorized into three groups: 144 individuals with mild cognitive impairment (MCI), 38 with dementia, and 101 healthy controls. Various ML techniques are evaluated to classify cognitive performance levels based on input features such as sociodemographic variables, lab results, comorbidities, Body Mass Index (BMI), and functional scales. Key predictors for distinguishing healthy controls from individuals with MCI are identified. These are history of myocardial infarction, vitamin D3 levels, the Instrumental Activities of Daily Living (IADL) scale, age, and sodium levels. The nonlinear Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel achieve the best performance for MCI classification, with an accuracy of 69%, an AUC of 0.75, and a Matthews Correlation Coefficient (MCC) of 0.43. For distinguishing healthy controls from those with dementia, the most influential factors include the IADL scale, the Activities of Daily Living (ADL) scale, education, vitamin D3 levels, and age. Here, the Random Forest algorithm demonstrates superior performance, achieving 84% accuracy, an AUC of 0.96, and an MCC of 0.71. These two models consistently outperform other ML techniques, such as K-Nearest Neighbors, Multi-Layer Perceptron, linear SVM, Naive Bayes, Quadratic Discriminant Analysis, Linear Discriminant Analysis, AdaBoost, and Gaussian Process Classifiers. The findings suggest that EMR data can be an effective resource for the initial classification of cognitive impairments. Integrating these ML-driven approaches into primary care settings may facilitate the early identification of older patients who could benefit from further cognitive assessments.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-025-90460-y

Cites

74 of 74 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 The most important features impacting classification tasks among the following patients groups: (a) Control vs. MCI, (b) Control vs. Dementia, (c) Control vs. MCI and D combined, where control refers to subjects not exhibiting any cognitive impairment symptoms, MCI stands for Mild cognitive impairment and D denotes the patients diagnosed with dementia. The vertical line indicates the feature scoring returned by the result of F-test.
Fig. 1 The most important features impacting classification tasks among the following patients groups: (a) Control vs. MCI, (b) Control vs. Dementia, (c) Control vs. MCI and D combined, where control refers to subjects not exhibiting any cognitive impairment symptoms, MCI stands for Mild cognitive impairment and D denotes the patients diagnosed with dementia. The vertical line indicates the feature scoring returned by the result of F-test.CC BY-NC-ND · PubMed Central
Fig. 2 Decision boundary surfaces for the non–linear SVM classificator with the RBF kernel across three classification scenarios: (a) C vs. MCI, (b) C vs. D, (c) C vs. (MCI+D), based on two most discriminative features. D3 represents the level of vitamin D3 and ’Heart Attack’ indicates whether a patient has a history of myocardial infarction (2) or not (1) IADL and ADL refer for measures of Instrumental Activities of Daily Living and Activities of Daily Living, respectively.
Fig. 2 Decision boundary surfaces for the non–linear SVM classificator with the RBF kernel across three classification scenarios: (a) C vs. MCI, (b) C vs. D, (c) C vs. (MCI+D), based on two most discriminative features. D3 represents the level of vitamin D3 and ’Heart Attack’ indicates whether a patient has a history of myocardial infarction (2) or not (1) IADL and ADL refer for measures of Instrumental Activities of Daily Living and Activities of Daily Living, respectively.CC BY-NC-ND · PubMed Central
Fig. 3 The general scheme used during ML classification involves several steps. Initially, patients are assigned to one of three categories: C (control), MCI (mild cognitive impairment), D (dementia). Then the discrimination is performed either between patients labeled as C and MCI, C and D or C and MCI+D, based on their medical records. Next, missing values in the data are handled with the KNN imputation algorithm. Subsequently, the most significant features are derived from the dataset using the univariate statistical test. To address data imbalance, the SMOTE technique is applied. Such prepared data is then fed into a ML classifier. To optimize the results, the best hyperparameters of the model are selected using Grid Search combined with k-fold Cross Validation.
Fig. 3 The general scheme used during ML classification involves several steps. Initially, patients are assigned to one of three categories: C (control), MCI (mild cognitive impairment), D (dementia). Then the discrimination is performed either between patients labeled as C and MCI, C and D or C and MCI+D, based on their medical records. Next, missing values in the data are handled with the KNN imputation algorithm. Subsequently, the most significant features are derived from the dataset using the univariate statistical test. To address data imbalance, the SMOTE technique is applied. Such prepared data is then fed into a ML classifier. To optimize the results, the best hyperparameters of the model are selected using Grid Search combined with k-fold Cross Validation.CC BY-NC-ND · PubMed Central
Fig. 4 The scheme of the SVM algorithm in a 2–dimensional space. The blue stars and red dots represent samples corresponding to two categories. The solid line illustrates the optimal hyperplane separating two data classes, while the dashed lines show hyperplanes passing through the support vectors.
Fig. 4 The scheme of the SVM algorithm in a 2–dimensional space. The blue stars and red dots represent samples corresponding to two categories. The solid line illustrates the optimal hyperplane separating two data classes, while the dashed lines show hyperplanes passing through the support vectors.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Show all 73 references

Research works printed but not linked: 3

  1. Prince, M., Albanese, E., Guerchet, M. & Prina, M. World Alzheimer Report 2014. Dementia and Risk Reduction: An analysis of protective and modifiable risk factors. Ph.D. thesis, schoolAlzheimer’s Disease International (2014).
  2. Gauthier, S., Rosa-Neto, P., Morais, J. A. & Webster, C. World Alzheimer report 2021: Journey through the diagnosis of dementia. Alzheimer’s Dis. Int. 2022, 30 (2021).
  3. Fernández-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems?. J. Mach. Learn. Res. 15, 3133–3181 (2014).

Cited by

See all 16

Metadata

Authors
Richter-Laskowska, M., Sobotnicka, E., & Bednorz, A.
Affiliations
  • Lukasiewicz Research Network - Krakow Institute of Technology (PL)
  • Humanitas University in Sosnowiec (PL)
Corresponding author
  • Richter-Laskowska, Monika
  • Bednorz, Adam
Venue
Scientific Reports
Published
2025-02-24
Volume
15
Issue
1
Pages
6564-6564
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4407884340
Cited by
16
References
73
Citations by year
2026: 9 · 2025: 7
FWCI
10.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
cognitive impairment classification, mild cognitive impairment, dementia, older adults, electronic health records, support vector machine, random forest, vitamin D3, instrumental activities of daily living, activities of daily living, comorbidities, early diagnosis of dementia, primary care
MeSH terms
Machine Learning, Activities of Daily Living, Aged, Aged, 80 and over, Algorithms, Cognition, Dementia, Female, Humans, Male, Case-Control Studies, Electronic Health Records, Support Vector Machine, Cognitive Dysfunction

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Cognitive performance classification of older patients using machine learning and electronic medical records. https://app.cochat.ai/papers/10.1038/s41598-025-90460-y
The paper
Richter-Laskowska, M., Sobotnicka, E., & Bednorz, A. (2025). Cognitive performance classification of older patients using machine learning and electronic medical records. Scientific Reports. https://doi.org/10.1038/s41598-025-90460-y

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.