Home › Research › Mild cognitive impairment
Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers
Kesheng Wang, Donald Adjeroh, Wei Fang, Suzy Mascaro Walter, Danqing Xiao, Ubolrat Piamjariyakul, Chun Di Xu. International Journal of Molecular Sciences, 2025-03-08
Topic: Amyloid, tau and blood-test diagnosis
Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer’s disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor (KNN), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost)) and six variations of a deep neural network (DNN) model—the DL model in the H2O package. Least Absolute Shrinkage and Selection Operator (LASSO) selected 35 proteomic biomarkers from the pool. Based on grid search, the DNN model with an activation function of “Rectifier With Dropout” with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985. Several biomarkers were correlated with the APOE-ε4 genotype, polygenic hazard score (PHS), and three clinical cerebrospinal fluid biomarkers (Aβ42, tTau, and pTau). Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization. The results showed that the DL model may represent a promising tool in the prediction of MCI. These plasma proteomic biomarkers may help with early diagnosis, prognostic risk stratification, and early treatment interventions for individuals at risk for MCI.
Key findings
- Based on grid search, the DNN model with an activation function of “Rectifier With Dropout” with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985.
- Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization.
- The results showed that the DL model may represent a promising tool in the prediction of MCI.
Why it matters
This study compared deep learning and traditional machine learning models for predicting mild cognitive impairment using plasma proteomic biomarkers, with the deep learning model achieving the highest accuracy. This could improve early detection, but no treatment or cure is tested.
Study details
- Participants239
- Evidence strengthModerate
How this study scored 48/100
Published in a peer-reviewed journal. Scored zero for study design, effect reported and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (International Journal of Molecular Sciences) |
| Journal's citation record | 3 / 4 | International Journal of Molecular Sciences: journal h-index 426 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 3 / 5 | Rated “moderate” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 year(s) of the newest study here |
| Sample size | 2 / 4 | 239 participants |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 2 / 7 | Cited 7 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 2.3 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 3 / 6 | Cited 4.4× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 1 / 4 | Cited 7 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Chun Di Xu: h-index 30 (OpenAlex, whole career) |
| Institution's track record | 1 / 3 | University of South Carolina: institution h-index 712 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 5 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 40141072) |
| Free to read | 2 / 2 | Free to read |
| Total | 48 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.3390/ijms26062428
- PubMed: 40141072
- Original source →
- Free full text: International Journal of Molecular Sciences →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record names 7 authors; APA and Vancouver show the first six, BibTeX and the downloads carry all of them. Check the citation against the original before you use it.
APA 7th
Wang, K., Adjeroh, D., Fang, W., Walter, S. M., Xiao, D., Piamjariyakul, U., et al. (2025). Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms26062428
Vancouver
Wang K, Adjeroh D, Fang W, Walter SM, Xiao D, Piamjariyakul U, et al. Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers. International Journal of Molecular Sciences. 2025. doi:10.3390/ijms26062428. PMID: 40141072.
BibTeX
@article{wang2025-40141072,
author = {Wang, Kesheng and Adjeroh, Donald and Fang, Wei and Walter, Suzy Mascaro and Xiao, Danqing and Piamjariyakul, Ubolrat and Di Xu, Chun},
title = {{Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers}},
journal = {International Journal of Molecular Sciences},
year = {2025},
doi = {10.3390/ijms26062428},
pmid = {40141072},
url = {https://doi.org/10.3390/ijms26062428}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 19.