Machine Learning-Based Alzheimer’s Disease Stage Diagnosis Utilizing Blood Gene Expression and Clinical Data: A Comparative Investigation

Topic: Amyloid, tau and blood-test diagnosis

Utilizing clinical data, the highest ROC AUC scores attained were 0.989, 0.927, and 0.907 for the identification of the CN, MCI, and dementia stages, respectively. The highest F1 scores achieved were 0.971, 0.939, and 0.886. Employing gene expression data, we obtained ROC AUC scores of 0.763, 0.761, and 0.706 for the CN, MCI, and dementia stages, respectively, and F1 scores of 0.71, 0.77, and 0.53 for CN, MCI, and dementia, respectively. This represents the best outcome to date for AD stage diagnosis from ADNI blood gene expression profile data utilizing multiclassification techniques. The results indicated that our multiclassification model effectively manages the imbalanced data of a high-dimension, low-sample-size (HDLSS) nature to identify samples of the minority class. MAPK14, PLG, FZD2, FXYD6, and TEP1 are among the novel genes identified as being associated with AD risk.

Key findings

• Utilizing clinical data, the highest ROC AUC scores attained were 0.989, 0.927, and 0.907 for the identification of the CN, MCI, and dementia stages, respectively.
• The highest F1 scores achieved were 0.971, 0.939, and 0.886.
• Employing gene expression data, we obtained ROC AUC scores of 0.763, 0.761, and 0.706 for the CN, MCI, and dementia stages, respectively, and F1 scores of 0.71, 0.77, and 0.53 for CN, MCI, and dementia, respectively.
• This represents the best outcome to date for AD stage diagnosis from ADNI blood gene expression profile data utilizing multiclassification techniques.
• The results indicated that our multiclassification model effectively manages the imbalanced data of a high-dimension, low-sample-size (HDLSS) nature to identify samples of the minority class.

Why it matters

This study uses machine learning on blood gene expression and clinical data to identify Alzheimer's disease stages and flags several genes as associated with AD risk. It is a diagnostic and risk-association study only and does not test any treatment, cure or prevention.

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.3390/diagnostics15020211
• PubMed: 39857095
• Original source →
• Free full text: Diagnostics →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{sarma2025-39857095,
  author  = {Sarma, Manash and Chatterjee, Subarna},
  title   = {{Machine Learning-Based Alzheimer’s Disease Stage Diagnosis Utilizing Blood Gene Expression and Clinical Data: A Comparative Investigation}},
  journal = {Diagnostics},
  year    = {2025},
  doi     = {10.3390/diagnostics15020211},
  pmid    = {39857095},
  url     = {https://doi.org/10.3390/diagnostics15020211}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here.

• The genetics of Alzheimer disease Cold Spring Harbor perspectives in medicine · 2012-10-01 · usefulness score 51/100 · Genetics

Related studies in Digital health tools

• ‘Machine Learning’ multiclassification for stage diagnosis of Alzheimer’s disease utilizing augmented blood gene expression and feature fusion Discover Applied Sciences · 2025-06-12 · usefulness score 35/100
• Enhancing Alzheimer’s Diagnosis with Machine Learning on EEG: A Spectral Feature-Based Comparative Analysis Diagnostics · 2025-08-29 · usefulness score 43/100
• Development and validation of machine learning models with blood-based digital biomarkers for Alzheimer’s disease diagnosis: a multicohort diagnostic study EClinicalMedicine · 2025-03-01 · usefulness score 52/100
• Surrogate variables and the risk of overfitting in neuropsychiatric gene expression analyses bioRxiv · 2026-10-12 · usefulness score 16/100
• A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: Results from the European Medical Information Framework for Alzheimer disease biomarker discovery cohort Alzheimer's & dementia (New York, N. Y.) · 2019-12-18 · usefulness score 58/100
• Classifications of Neurodegenerative Disorders Using a Multiplex Blood Biomarkers-Based Machine Learning Model International journal of molecular sciences · 2020-09-21 · usefulness score 49/100

Also tagged “classification”

835 studies in the library carry the topic tag “classification”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 835 tagged studies.

• The role of brain MR and FDG-PET in the diagnosis of neurodegenerative disease European Radiology · 2025-09-03 · usefulness score 35/100 · Treatments
• Retinal fluorescence lifetime imaging ophthalmoscopy measures depend on the severity of Alzheimer's disease Acta ophthalmologica · 2014-12-07 · usefulness score 41/100 · Tau biomarkers
• Multidimensional MRI reveals cortical astrogliosis linked to dementia in Alzheimer’s disease Brain Communications · 2025-01-01 · usefulness score 43/100 · Getting a diagnosis

Similar studies

• Improving Alzheimer's disease diagnosis with machine learning techniques 2011 · Digital health tools
• Accurate Blood-Based Diagnostic Biosignatures for Alzheimer's Disease via Automated Machine Learning 2020 · Digital health tools
• Detection and Classification of Alzheimer’s Disease Using Deep and Machine Learning 2025 · Digital health tools
• Early diagnosis of Alzheimer's disease using machine learning: a multi-diagnostic, generalizable approach 2022 · Digital health tools
• Advances in Alzheimer’s disease diagnosis with machine learning and deep learning techniques: a comprehensive review 2026 · Digital health tools
• An explainable machine learning approach for Alzheimer's disease classification 2024 · Digital health tools

More on Digital health tools

• A review that covers this ground Multivariate classification of blood oxygen level-dependent FMRI data with diagnostic intention: a clinical perspective AJNR. American journal of neuroradiology · 2013-09-12 · usefulness score 51/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →