Machine learning models for dementia screening to classify brain amyloid positivity on positron emission tomography using blood markers and demographic characteristics: a retrospective observational study

Topic: Amyloid, tau and blood-test diagnosis

Data from 262 records (260 unique participants) were analyzed. The mean (standard deviation [SD]) participant age was 73.8 (7.8) years. Using L2-regularized logistic regression, the mean receiver operating characteristic (ROC) area under the curve (AUC) (SD) in Model 0 (basic demographic characteristics) was 0.67 (0.01). Classification performance was similar in Model 1 (basic demographic characteristics and Mini Mental State Examination [MMSE] subscores) and Model 2 (demographic characteristics and blood test results) with a cross-validated mean ROC AUC (SD) of 0.70 (0.01) for both. Model 3 (demographic characteristics, blood test results, MMSE subscores) and Model 4 (Model 3 and ApoE4 phenotype) showed improved performance with a mean ROC AUC (SD) of 0.73 (0.01) and 0.76 (0.01), respectively. In models using blood test results, thyroid-stimulating hormone and mean corpuscular volume tended to be the largest contributors to classification. Classification performances were similar using the SVM and Elastic Net algorithms. The machine learning models used in this study were useful for classifying PET Aβ-positivity using data from routine physician visits. TRIAL REGISTRATION: UMIN Clinical Trials Registry (UMIN000051776, registered on 31/08/2023).

Key findings

• Data from 262 records (260 unique participants) were analyzed.
• The mean (standard deviation [SD]) participant age was 73.8 (7.8) years.
• Using L2-regularized logistic regression, the mean receiver operating characteristic (ROC) area under the curve (AUC) (SD) in Model 0 (basic demographic characteristics) was 0.67 (0.01).
• Classification performance was similar in Model 1 (basic demographic characteristics and Mini Mental State Examination [MMSE] subscores) and Model 2 (demographic characteristics and blood test results) with a cross-validated mean ROC AUC (SD) of 0.70 (0.01) for both.
• Model 3 (demographic characteristics, blood test results, MMSE subscores) and Model 4 (Model 3 and ApoE4 phenotype) showed improved performance with a mean ROC AUC (SD) of 0.73 (0.01) and 0.76 (0.01), respectively.

Why it matters

Machine learning models using routine visit data such as demographics, blood tests, MMSE subscores, and ApoE4 status were useful for classifying whether a person was amyloid-positive on PET scans. This is about improving screening and classification, not about treating, curing, or preventing Alzheimer's disease.

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

Study details

• Participants15
• Evidence strengthLow

Read the original

• DOI: 10.1186/s13195-024-01650-1
• PubMed: 39838434
• Original source →
• Free full text: Alzheimer s Research & Therapy →

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

@article{kimura2025-39838434,
  author  = {Kimura, Noriyuki and Sasaki, Kotaro and Masuda, Teruaki and Ataka, Takuya and Matsumoto, Mariko and Kitamura, Mika and Nakamura, Yosuke and Matsubara, Etsuro},
  title   = {{Machine learning models for dementia screening to classify brain amyloid positivity on positron emission tomography using blood markers and demographic characteristics: a retrospective observational study}},
  journal = {Alzheimer s Research \& Therapy},
  year    = {2025},
  doi     = {10.1186/s13195-024-01650-1},
  pmid    = {39838434},
  url     = {https://doi.org/10.1186/s13195-024-01650-1}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 22.

• Prevalence of cerebral amyloid pathology in persons without dementia: a meta-analysis JAMA · 2015-05-01 · usefulness score 84/100 · Genetics
• Associations of Plasma Phospho-Tau217 Levels With Tau Positron Emission Tomography in Early Alzheimer Disease JAMA neurology · 2021-02-01 · usefulness score 75/100 · Biomarkers
• Head-to-Head Comparison of 8 Plasma Amyloid-β 42/40 Assays in Alzheimer Disease JAMA neurology · 2021-11-01 · usefulness score 72/100 · How common it is
• Toward defining the preclinical stages of Alzheimer's disease: recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease Alzheimer's & dementia : the journal of the Alzheimer's Association · 2011-04-21 · usefulness score 70/100 · Getting a diagnosis
• Dementia prevention, intervention, and care: 2020 report of the Lancet Commission The Lancet · 2020-07-30 · usefulness score 67/100 · Prevention and risk
• Dementia prevention, intervention, and care The Lancet · 2017-07-20 · usefulness score 65/100 · Prevention and risk
• Alzheimer's disease Lancet (London, England) · 2021-03-02 · usefulness score 65/100 · Prevention and risk
• NIA-AA Research Framework: Toward a biological definition of Alzheimer's disease Alzheimer's & dementia : the journal of the Alzheimer's Association · 2018-04-01 · usefulness score 64/100 · Getting a diagnosis
• Plasma Amyloid as Prescreener for the Earliest Alzheimer Pathological Changes Annals of neurology · 2018-10-04 · usefulness score 64/100 · Mild cognitive impairment
• Associations of blood cell indices and anemia with risk of incident dementia: A prospective cohort study of 313,448 participants Alzheimer's & dementia : the journal of the Alzheimer's Association · 2023-04-26 · usefulness score 64/100 · Long-term cohort studies
• Imaging brain amyloid in Alzheimer's disease with Pittsburgh Compound‐B Annals of Neurology · 2004-01-21 · usefulness score 63/100 · Brain scans and imaging
• High-precision plasma β-amyloid 42/40 predicts current and future brain amyloidosis Neurology · 2019-08-01 · usefulness score 62/100 · Biomarkers

Later studies that cite this one

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

• Prediction of continuous amyloid positron emission tomography with fluid measures of phosphorylated tau and β-amyloid EMBO Molecular Medicine · 2025-12-01 · usefulness score 46/100 · Biomarkers

Related studies in Digital health tools

• Fluorodeoxyglucose F18 positron emission tomography in progressive apraxia of speech and primary progressive aphasia variants Archives of neurology · 2010-05-01 · usefulness score 46/100
• A Novel Ensemble-Based Machine Learning Algorithm to Predict the Conversion From Mild Cognitive Impairment to Alzheimer's Disease Using Socio-Demographic Characteristics, Clinical Information, and Neuropsychological Measures Frontiers in neurology · 2019-07-16 · usefulness score 51/100
• Machine learning model for predicting Amyloid-β positivity and cognitive status using early-phase 18F-Florbetaben PET and clinical features Scientific Reports · 2025-07-01 · usefulness score 50/100
• 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
• The Brain Chart of Aging: Machine-learning analytics reveals links between brain aging, white matter disease, amyloid burden, and cognition in the iSTAGING consortium of 10,216 harmonized MR scans Alzheimer's & dementia : the journal of the Alzheimer's Association · 2020-09-13 · usefulness score 55/100
• Developing a machine learning model for detecting depression, anxiety, and apathy in older adults with mild cognitive impairment using speech and facial expressions: A cross-sectional observational study International journal of nursing studies · 2023-07-07 · usefulness score 52/100

Similar studies

• Machine learning algorithms and traditional statistical models for detection of dementia: a population-based study 2025 · Digital health tools
• Predicting Prodromal Alzheimer's Disease in Subjects with Mild Cognitive Impairment Using Machine Learning Classification of Multimodal Multicenter Diffusion-Tensor and Magnetic Resonance Imaging Data 2015 · Digital health tools
• Identifying incipient dementia individuals using machine learning and amyloid imaging 2017 · Digital health tools
• Neuroimaging and Machine Learning for Dementia Diagnosis: Recent Advancements and Future Prospects 2019 · Digital health tools
• Amyloid PET/MRI in the differential diagnosis of dementia 2014 · Biomarkers
• Machine learning–enhanced screening funnel for clinical trials in Alzheimer's disease 2025 · Digital health tools

More on Digital health tools

• A review that covers this ground Exploiting machine learning models to identify novel Alzheimer's disease biomarkers and potential targets Scientific reports · 2023-03-27 · 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 →