Benchmarking machine learning models for late-onset alzheimer's disease prediction from genomic data

Topic: Amyloid, tau and blood-test diagnosis

Background Late-Onset Alzheimer's Disease (LOAD) is a leading form of dementia. There is no effective cure for LOAD, leaving the treatment efforts to depend on preventive cognitive therapies, which stand to benefit from the timely estimation of the risk of developing the disease. Fortunately, a growing number of Machine Learning methods that are well positioned to address this challenge are becoming available. Results We conducted systematic comparisons of representative Machine Learning models for predicting LOAD from genetic variation data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our experimental results demonstrate that the classification performance of the best models tested yielded ∼72% of area under the ROC curve. Conclusions Machine learning models are promising alternatives for estimating the genetic risk of LOAD. Systematic machine learning model selection also provides the opportunity to identify new genetic markers potentially associated with the disease.

Key findings

• Results We conducted systematic comparisons of representative Machine Learning models for predicting LOAD from genetic variation data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort.
• Our experimental results demonstrate that the classification performance of the best models tested yielded ∼72% of area under the ROC curve.
• Systematic machine learning model selection also provides the opportunity to identify new genetic markers potentially associated with the disease.

Why it matters

Machine learning models using genetic data predicted late-onset Alzheimer's disease with about 72% area under the ROC curve, which is not high enough to be a stand-alone diagnostic test. This work may help identify new genetic markers linked to the disease, but it does not provide a treatment, cure or prevention.

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

Study details

• Evidence strengthModerate

Read the original

• DOI: 10.1186/s12859-019-3158-x
• PubMed: 31842725
• Original source →
• Free full text: BMC Bioinformatics →

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

@article{develascooriol2019-31842725,
  author  = {De Velasco Oriol, J. and Vallejo, E. E. and Estrada, K. and Taméz Peña, J. G. and {Disease Neuroimaging Initiative TA}},
  title   = {{Benchmarking machine learning models for late-onset alzheimer's disease prediction from genomic data}},
  journal = {BMC bioinformatics},
  year    = {2019},
  doi     = {10.1186/s12859-019-3158-x},
  pmid    = {31842725},
  url     = {https://doi.org/10.1186/s12859-019-3158-x}
}

Studies this one cites

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

• Genome-wide analysis of genetic loci associated with Alzheimer disease JAMA · 2010-05-01 · usefulness score 78/100 · Genetics
• Meta-analysis of 74,046 individuals identifies 11 new susceptibility loci for Alzheimer's disease Nature Genetics · 2013-10-27 · usefulness score 66/100 · Risk genes beyond APOE
• Predicting Alzheimer's disease progression using multi-modal deep learning approach Scientific reports · 2019-02-13 · usefulness score 66/100 · Mild cognitive impairment
• APP, PSEN1, and PSEN2 mutations in early-onset Alzheimer disease: A genetic screening study of familial and sporadic cases PLoS medicine · 2017-03-28 · usefulness score 64/100 · Risk genes beyond APOE
• The antibody aducanumab reduces Aβ plaques in Alzheimer’s disease Nature · 2016-08-30 · usefulness score 60/100 · Treatments
• Alzheimer's disease Lancet (London, England) · 2011-03-01 · usefulness score 59/100 · Getting a diagnosis
• The Role of APOE and TREM2 in Alzheimer's Disease-Current Understanding and Perspectives International journal of molecular sciences · 2018-12-26 · usefulness score 47/100 · Genetics

Later studies that cite this one

1 study in the alzhub library lists this one in its references.

• Prediction of mild cognitive impairment using blood multi-omics data Frontiers in Genetics · 2025-05-26 · usefulness score 36/100 · Mild cognitive impairment

Related studies in Digital health tools

• Real‐world prediction of early‐onset dementia by health record data: A multi‐center machine learning study Alzheimer s & Dementia · 2025-11-01 · usefulness score 36/100
• Machine learning models to predict onset of dementia: A label learning approach Alzheimer's & dementia (New York, N. Y.) · 2019-12-10 · usefulness score 53/100
• Early-Stage Alzheimer's Disease Prediction Using Machine Learning Models Frontiers in public health · 2022-03-03 · usefulness score 53/100
• A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction Scientific reports · 2020-11-23 · usefulness score 67/100
• Machine learning prediction of incidence of Alzheimer's disease using large-scale administrative health data NPJ digital medicine · 2020-03-26 · usefulness score 59/100
• Machine Learning Prediction of Agitation in Dementia Patients Using Sleep and Physiological Data Applied Sciences · 2025-09-10 · usefulness score 33/100

Also in Digital health tools

178 studies in the library are filed under Digital health tools with no topic tag they share with another; these are this study's neighbours in a fixed tour of them. The Digital health tools hub.

• Referential communication in Alzheimer's type dementia Cortex; a journal devoted to the study of the nervous system and behavior · 2005-08-01 · usefulness score 43/100 · Digital health tools
• Gait speed in Parkinson disease correlates with cholinergic degeneration Neurology · 2013-09-27 · usefulness score 59/100 · Digital health tools
• Advances in Alzheimer’s disease diagnosis with machine learning and deep learning techniques: a comprehensive review Artificial Intelligence Review · 2026-02-04 · usefulness score 41/100 · Digital health tools

Similar studies

• Prediction Of Alzheimer Patients with Machine Learning Algorithms 2025 · Genetics
• Exploiting machine learning models to identify novel Alzheimer's disease biomarkers and potential targets 2023 · Digital health tools
• Late-onset Alzheimer Disease 2019 · Genetics
• Improving Alzheimer's disease diagnosis with machine learning techniques 2011 · Digital health tools
• A review on omics-based biomarkers discovery for Alzheimer's disease from the bioinformatics perspectives: Statistical approach vs machine learning approach 2021 · Digital health tools
• Machine learning for comprehensive forecasting of Alzheimer's Disease progression 2019 · Mild cognitive impairment

More on Digital health tools

• A review that covers this ground Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data Frontiers in aging neuroscience · 2019-08-20 · usefulness score 72/100
• 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 →