Classification of Alzheimer's Disease with and without Imagery using Gradient Boosted Machines and ResNet-50

Topic: Amyloid, tau and blood-test diagnosis

Background Alzheimer's is a disease for which there is no cure. Diagnosing Alzheimer's disease (AD) early facilitates family planning and cost control. The purpose of this study is to predict the presence of AD using socio-demographic, clinical, and magnetic resonance imaging (MRI) data. Early detection of AD enables family planning and may reduce costs by delaying long-term care. Accurate, non-imagery methods also reduce patient costs. The Open Access Series of Imaging Studies (OASIS-1) cross-sectional MRI data were analyzed. A gradient boosted machine (GBM) predicted the presence of AD as a function of gender, age, education, socioeconomic status (SES), and a mini-mental state exam (MMSE). A residual network with 50 layers (ResNet-50) predicted the clinical dementia rating (CDR) presence and severity from MRI's (multi-class classification). The GBM achieved a mean 91.3% prediction accuracy (10-fold stratified cross validation) for dichotomous CDR using socio-demographic and MMSE variables. MMSE was the most important feature. ResNet-50 using image generation techniques based on an 80% training set resulted in 98.99% three class prediction accuracy on 4139 images (20% validation set) at Epoch 133 and nearly perfect multi-class predication accuracy on the training set (99.34%). Machine learning methods classify AD with high accuracy. GBM models may help provide initial detection based on non-imagery analysis, while ResNet-50 network models might help identify AD patients automatically prior to provider review.

Key findings

• A residual network with 50 layers (ResNet-50) predicted the clinical dementia rating (CDR) presence and severity from MRI's (multi-class classification).
• The GBM achieved a mean 91.3% prediction accuracy (10-fold stratified cross validation) for dichotomous CDR using socio-demographic and MMSE variables.
• ResNet-50 using image generation techniques based on an 80% training set resulted in 98.99% three class prediction accuracy on 4139 images (20% validation set) at Epoch 133 and nearly perfect multi-class predication accuracy on the training set (99.34%).
• Machine learning methods classify AD with high accuracy.
• GBM models may help provide initial detection based on non-imagery analysis, while ResNet-50 network models might help identify AD patients automatically prior to provider review.

Why it matters

Machine learning methods classified Alzheimer's disease with high accuracy using socio-demographic, clinical and MRI data, with the MMSE being the most important feature. This is about improving detection and diagnosis, not about treating, curing or preventing the disease.

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

Study details

• Study designcross-sectional
• Effect size91.3%; 98.99%; 99.34%
• Evidence strengthLow

Read the original

• DOI: 10.3390/brainsci9090212
• PubMed: 31443556
• Original source →
• Free full text: Brain Sciences →

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

@article{fulton2019-31443556,
  author  = {Fulton, L. V. and Dolezel, D. and Harrop, J. and Yan, Y. and Fulton, C. P.},
  title   = {{Classification of Alzheimer's Disease with and without Imagery using Gradient Boosted Machines and ResNet-50}},
  journal = {Brain sciences},
  year    = {2019},
  doi     = {10.3390/brainsci9090212},
  pmid    = {31443556},
  url     = {https://doi.org/10.3390/brainsci9090212}
}

Studies this one cites

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

• The Clinical Dementia Rating (CDR) Neurology · 1993-11-01 · usefulness score 59/100 · Cognitive tests and assessment

Later studies that cite this one

2 studies in the alzhub library list this one in their references.

• A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease Brain sciences · 2020-02-05 · usefulness score 49/100 · Brain scans and imaging
• Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review JAMIA open · 2021-07-01 · usefulness score 44/100 · Digital health tools

Related studies in Digital health tools

• Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests BMC research notes · 2011-08-17 · usefulness score 47/100
• Predicting the insurgence of human genetic diseases associated to single point protein mutations with support vector machines and evolutionary information Bioinformatics (Oxford, England) · 2006-08-07 · usefulness score 36/100
• 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
• Classification of Alzheimer's disease and frontotemporal dementia using routine clinical and cognitive measures across multicentric underrepresented samples: A cross sectional observational study Lancet regional health. Americas · 2022-11-03 · usefulness score 62/100
• Dementia etiology classification using NULISA plasma biomarkers and machine learning Alzheimer s & Dementia · 2026-06-01 · usefulness score 62/100
• Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images Frontiers in neuroinformatics · 2018-06-19 · usefulness score 53/100

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.

• Injury markers predict time to dementia in subjects with MCI and amyloid pathology Neurology · 2012-09-26 · usefulness score 67/100 · Genetics
• Amyloid positron emission tomography candidates may focus more on benefits than risks of results disclosure Alzheimer's & dementia (Amsterdam, Netherlands) · 2018-05-30 · usefulness score 65/100 · Biomarkers
• Cerebral Amyloid Angiopathy Pathology and Its Association With Amyloid-β PET Signal Neurology · 2021-09-09 · usefulness score 45/100 · Biomarkers

Similar studies

• Detection and Classification of Alzheimer’s Disease Using Deep and Machine Learning 2025 · Digital health tools
• An explainable machine learning approach for Alzheimer's disease classification 2024 · Digital health tools
• Application of Convolutional Neural Network Based on ResNet18 for Alzheimer Disease Classification 2025 · Brain scans and imaging
• A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer's Disease Stages Using Resting-State fMRI and Residual Neural Networks 2019 · Long-term cohort studies
• Classifying and diagnosing Alzheimer’s disease with deep learning using 6735 brain MRI images 2025 · Brain scans and imaging
• Performance evaluation of Alzheimer’s disease detection in brain MRI images using the Alzheimer-net classifier 2025 · Brain scans and imaging

More on Digital health tools

• A review that covers this ground Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging Frontiers in neuroscience · 2018-08-06 · usefulness score 41/100
• 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 →