WIMOAD: Weighted Integration of Multi-Omics Data with Meta Learning for Alzheimer’s Disease Diagnosis
Open accessAbstract
INTRODUCTION: Alzheimer’s disease (AD), the most prevalent subtype of dementia, is characterized by a gradual decline in brain cognitive function. Early detection is critical for initiating timely interventions that may delay the severe progression of the disease. Recent advances in next-generation sequencing (NGS) offer promising, non-invasive, and cost-effective strategies for AD screening. However, most current approaches rely on single-omics data, which may fail to capture the complex biological heterogeneity among individuals. METHODS: We introduce WIMOAD, a stacking ensemble and weighted multi-omics integration for AD diagnosis. It leverages paired gene expression and methylation data from ADNI and presents a meta learning framework for multi-cognitive stage classification during AD progression. RESULTS AND DISCUSSION: WIMOAD outperforms existing integration methods in AD diagnosis, effectively capturing complex multi-omics patterns linked to clinical outcomes. Its interpretability also facilitates the detection of novel biomarkers across different omics layers.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Classical machine learning algorithms such as random forests and support vector machines have demonstrated strong performance on curated datasets, providing interpretable feature rankings that aid in biomarker discovery.
“Classical machine learning algorithms such as random forests and support vector machines have demonstrated strong performance on curated datasets, providing interpretable feature rankings that aid in biomarker discovery227.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [227]
The Results sections (page unavailable) report that SVM was among the most competitive base classifiers and that SHAP rankings from both SVM and random forest helped identify AD-related genes. They do not establish similarly strong predictive performance for random forest; the interpretable rankings came from an added SHAP explainer, not from the classifiers alone. The evidence is specific to the paper’s Alzheimer’s multi-omics data rather than curated datasets generally. (LLM, conf=0.86)
Experimental — accuracy not yet measuredThe WIMOAD framework integrates paired gene expression and DNA methylation profiles using stacked meta-learners, achieving an accuracy of 0.89 and AUC of 0.92 in cross-validation within the ADNI cohort.
“The WIMOAD framework integrates paired gene expression and DNA methylation profiles using stacked meta-learners, achieving an accuracy of 0.89 and AUC of 0.92 in cross-validation within the ADNI cohort.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [227]
The Methods (Overview of WIMOAD Framework; Evaluation of the Model Performance) describe paired gene-expression and methylation inputs, stacked meta-learners, and leave-one-out cross-validation. The Results (WIMOAD remarkably outperformed state-of-the-art predictors for AD diagnosis) report an average AUC of 0.67 across nine binary classification tasks, not the claimed 0.92; our copy also does not report the claimed accuracy of 0.89. (LLM, conf=0.90)
Experimental — accuracy not yet measuredThe WIMOAD model applies ensemble learning to integrate gene expression and DNA methylation data, aligning molecular profiles with cortical thickness maps from MRI, and identifies early versus slow progression phenotypes within the ADNI cohort.
“Models like WIMOAD apply ensemble learning to integrate gene expression and DNA methylation data, aligning the resulting molecular profiles with cortical thickness maps derived from MRI, thereby identifying early versus slow progression phenotypes within the ADNI cohort227.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [227]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
NIA‐AA Research Framework: Toward a biological definition of Alzheimer's disease
Jack, C. R., Bennett, D. A., Blennow, K., Carrillo, M. C., Dunn, B., Haeberlein, S. B., Holtzman, D. M., Jagust, W., Jessen, F., Karlawish, J., et al. (2018) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2018.02.018 · Cited by 10,537 · see citing works
A data-driven approach to preprocessing Illumina 450K methylation array data
Pidsley, R., Y Wong, C. C., Volta, M., Lunnon, K., Mill, J., & Schalkwyk, L. C. (2013) · BMC Genomics · doi:10.1186/1471-2164-14-293 · Cited by 1,143 · see citing works
Multimodal deep learning for biomedical data fusion: a review
Stahlschmidt, S. R., Ulfenborg, B., & Synnergren, J. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab569 · Cited by 766 · see citing works
Nativio, R., Lan, Y., Donahue, G., Sidoli, S., Berson, A., Srinivasan, A. R., Shcherbakova, O., Amlie-Wolf, A., Nie, J., Cui, X., et al. (2020) · Nature Genetics · doi:10.1038/s41588-020-0696-0 · Cited by 380 · see citing works
Role of the β‐amyloid protein in Alzheimer's disease
Sisodia, S. S., & Price, D. L. (1995) · The FASEB Journal · doi:10.1096/fasebj.9.5.7896005 · Cited by 262 · see citing works
Epigenomic dissection of Alzheimer’s disease pinpoints causal variants and reveals epigenome erosion
Xiong, X., James, B. T., Boix, C. A., Park, Y. P., Galani, K., Victor, M. B., Sun, N., Hou, L., Ho, L.-L., Mantero, J., et al. (2023) · Cell · doi:10.1016/j.cell.2023.08.040 · Cited by 205 · see citing works
Genetic Heterogeneity in Alzheimer Disease and Implications for Treatment Strategies
Dominantly Inherited Alzheimer Network, Ringman, J. M., Goate, A., Masters, C. L., Cairns, N. J., Danek, A., Graff-Radford, N., Ghetti, B., & Morris, J. C. (2014) · Current Neurology and Neuroscience Reports · doi:10.1007/s11910-014-0499-8 · Cited by 96 · see citing works
Deep belief network-based approach for detecting Alzheimer's disease using the multi-omics data
Mahendran, N., & Vincent P M, D. R. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.02.021 · Cited by 31 · see citing works
Flagged first, then by citations
Research works printed but not linked: 50
- 10.1016/j.arr.2016.01.002 · DOI
- 10.2147/DNND.S228939 · DOI · Paper page
- 10.1212/WNL.0000000000002923 · DOI · Paper page
- 10.1016/j.bspc.2024.106023 · DOI
- 10.1007/s11227-023-05655-9 · DOI
- 10.1007/s42979-024-02743-2 · DOI
- 10.1016/j.neuron.2013.12.003 · DOI · Paper page
- 10.1056/NEJMoa1202753 · DOI · Paper page
- 10.7326/0003-4819-109-4-298 · DOI
- 10.1212/WNL.0000000000009058 · DOI
- 10.1016/j.pneurobio.2019.101662 · DOI
- 10.1016/j.cca.2024.117842 · DOI
- 10.1038/tp.2012.45 · DOI
- 10.1038/s41576-018-0004-3 · DOI · Paper page
- 10.1016/j.bbi.2014.11.002 · DOI
- 10.1016/j.mad.2020.111319 · DOI
- 10.3389/fnins.2024.1277187 · DOI
- 10.7717/peerj.6543 · DOI
- 10.1111/acel.14044 · DOI
- 10.1038/s41598-024-56837-1 · DOI
- 10.1093/brain/awz384 · DOI
- 10.1038/s41598-023-30892-6 · DOI · Paper page
- 10.1007/s40484-016-0063-4 · DOI
- 10.1093/bioinformatics/btp543 · DOI · Paper page
- 10.1214/12-AOAS597 · DOI
- 10.1111/biom.13108 · DOI
- 10.1093/bib/bbad073 · DOI · Paper page
- 10.1016/j.bspc.2023.105669 · DOI
- 10.1016/j.bbi.2011.01.017 · DOI
- 10.1097/NEN.0b013e3181af2e46 · DOI
- 10.3233/JAD-2006-9406 · DOI
- 10.1038/s41390-022-02181-x · DOI
- 10.1109/TCBB.2016.2527657 · DOI
- 10.1021/acs.jproteome.6b00686 · DOI
- 10.1007/BF00994018 · DOI · Paper page
- 10.1109/ICDAR.1995.598994 · DOI
- 10.1007/978-0-387-30164-8_576 · DOI
- 10.1007/978-94-007-0753-5_1689 · DOI
- 2009, Multilayer perceptron and neural networks, WSEAS Trans Cir and Sys, 8, 579
- 10.1016/0925-2312(91)90023-5 · DOI
- 10.1007/978-3-540-39964-3_62 · DOI
- 10.19026/rjaset.7.299 · DOI
- 10.1023/A:1021709817809 · DOI
- 10.1016/j.patcog.2015.03.009 · DOI · Paper page
- 10.1038/s41551-018-0304-0 · DOI · Paper page
- 10.1016/j.compbiomed.2023.107303 · DOI
- 10.1002/sim.9953 · DOI
- 10.3389/fnagi.2023.1277731 · DOI
- 10.3390/ijms241814225 · DOI
- 10.1046/j.1471-4159.2003.01948.x · DOI
Cited by
Sorted by citations
Ren, F., Wei, J., Chen, Q., Hu, M., Yu, L., Mi, J., Zhou, X., Qin, D., Wu, J., & Wu, A. (2025) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2025.07.030 · Cited by 97 · see citing works
- Authors
- Xiao, H., Wang, J., & Wan, S.
- Affiliations
- University of Nebraska Medical Center (US)
- Corresponding author
- Wang, Jieqiong
- Wan, Shibiao
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2024-09-27
- PMC
- PMC11463407
- OpenAlex
- W4402918680
- Cited by
- 6
- References
- 8
- Citations by year
- 2026: 1 · 2025: 5
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion, cc-by-nc-nd)
- Funders
- National Institutes of Health (1r03od038391-01)
- National Cancer Institute (P30CA036727)
- National Institute of General Medical Sciences (P20GM103427, P20GM130447)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Alzheimer's disease research and treatments
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- Alzheimer's disease diagnosis, multi-omics integration, stacking ensemble, meta-learning, gene expression, DNA methylation, early detection, biomarkers, ADNI
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
