Performance of Machine Learning Algorithms for Predicting Progression to Dementia in Memory Clinic Patients

Topic: Risk, prevention and care in population studies

Importance Machine learning algorithms could be used as the basis for clinical decision-making aids to enhance clinical practice. Objective To assess the ability of machine learning algorithms to predict dementia incidence within 2 years compared with existing models and determine the optimal analytic approach and number of variables required. Design, setting, and participants This prognostic study used data from a prospective cohort of 15 307 participants without dementia at baseline to perform a secondary analysis of factors that could be used to predict dementia incidence. Participants attended National Alzheimer Coordinating Center memory clinics across the United States between 2005 and 2015. Analyses were conducted from March to May 2021. Exposures 258 variables spanning domains of dementia-related clinical measures and risk factors. Main outcomes and measures The main outcome was incident all-cause dementia diagnosed within 2 years of baseline assessment. Results In a sample of 15 307 participants (mean [SD] age, 72.3 [9.8] years; 9129 [60%] women and 6178 [40%] men) without dementia at baseline, 1568 (10%) received a diagnosis of dementia within 2 years of their initial assessment. Compared with 2 existing models for dementia risk prediction (ie, Cardiovascular Risk Factors, Aging, and Incidence of Dementia Risk Score, and the Brief Dementia Screening Indicator), machine learning algorithms were superior in predicting incident all-cause dementia within 2 years. The gradient-boosted trees algorithm had a mean (SD) overall accuracy of 92% (1%), sensitivity of 0.45 (0.05), specificity of 0.97 (0.01), and area under the curve of 0.92 (0.01) using all 258 variables. Analysis of variable importance showed that only 6 variables were required for machine learning algorithms to achieve an accuracy of 91% and area under the curve of at least 0.89. Machine learning algorithms also identified up to 84% of participants who received an initial dementia diagnosis that was subsequently reversed to mild cognitive impairment or cognitively unimpaired, suggesting possible misdiagnosis. Conclusions and relevance These findings suggest that machine learning algorithms could accurately predict incident dementia within 2 years in patients receiving care at memory clinics using only 6 variables. These findings could be used to inform the development and validation of decision-making aids in memory clinics.

Key findings

• Objective To assess the ability of machine learning algorithms to predict dementia incidence within 2 years compared with existing models and determine the optimal analytic approach and number of variables required.
• Results In a sample of 15 307 participants (mean [SD] age, 72.3 [9.8] years; 9129 [60%] women and 6178 [40%] men) without dementia at baseline, 1568 (10%) received a diagnosis of dementia within 2 years of their initial assessment.
• Compared with 2 existing models for dementia risk prediction (ie, Cardiovascular Risk Factors, Aging, and Incidence of Dementia Risk Score, and the Brief Dementia Screening Indicator), machine learning algorithms were superior in predicting incident all-cause dementia within 2 years.
• The gradient-boosted trees algorithm had a mean (SD) overall accuracy of 92% (1%), sensitivity of 0.45 (0.05), specificity of 0.97 (0.01), and area under the curve of 0.92 (0.01) using all 258 variables.
• Analysis of variable importance showed that only 6 variables were required for machine learning algorithms to achieve an accuracy of 91% and area under the curve of at least 0.89.

Why it matters

In 15,307 participants without dementia at baseline, machine learning algorithms were assessed for predicting dementia incidence within 2 years and compared with two existing risk prediction models. The study concerns prediction and clinical decision-making aids, not treating, curing, or preventing Alzheimer's disease.

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

Study details

• Study designprospective cohort
• Participants307
• Evidence strengthModerate

Read the original

• DOI: 10.1001/jamanetworkopen.2021.36553
• PubMed: 34913981
• Original source →
• Free full text: JAMA Network Open →

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

@article{james2021-34913981,
  author  = {James, C. and Ranson, J. M. and Everson, R. and Llewellyn, D. J.},
  title   = {{Performance of Machine Learning Algorithms for Predicting Progression to Dementia in Memory Clinic Patients}},
  journal = {JAMA network open},
  year    = {2021},
  doi     = {10.1001/jamanetworkopen.2021.36553},
  pmid    = {34913981},
  url     = {https://doi.org/10.1001/jamanetworkopen.2021.36553}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 13.

• Rate of progression of mild cognitive impairment to dementia--meta-analysis of 41 robust inception cohort studies Acta psychiatrica Scandinavica · 2008-02-18 · usefulness score 71/100 · How common it is
• Diagnosis and management of dementia with Lewy bodies: third report of the DLB Consortium Neurology · 2005-10-19 · usefulness score 64/100 · Getting a diagnosis
• Progression of mild cognitive impairment to dementia in clinic- vs community-based cohorts Archives of neurology · 2009-09-01 · usefulness score 64/100 · Mild cognitive impairment
• Frontotemporal lobar degeneration: a consensus on clinical diagnostic criteria Neurology · 1998-12-01 · usefulness score 62/100 · Lewy body dementia
• Risk score for the prediction of dementia risk in 20 years among middle aged people: a longitudinal, population-based study The Lancet. Neurology · 2006-09-01 · usefulness score 62/100 · Prevention and risk
• The Alzheimer's Disease Centers' Uniform Data Set (UDS): the neuropsychologic test battery Alzheimer disease and associated disorders · 2009-04-01 · usefulness score 62/100 · Disparities
• Vascular dementia: diagnostic criteria for research studies. Report of the NINDS-AIREN International Workshop Neurology · 1993-02-01 · usefulness score 61/100 · Getting a diagnosis
• 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 · Digital health tools
• Clinical diagnosis of Alzheimer's disease: report of the NINCDS-ADRDA Work Group under the auspices of Department of Health and Human Services Task Force on Alzheimer's Disease Neurology · 1984-07-01 · usefulness score 58/100 · Getting a diagnosis
• Development and validation of a brief dementia screening indicator for primary care Alzheimer's & dementia : the journal of the Alzheimer's Association · 2014-02-01 · usefulness score 57/100 · Long-term cohort studies
• Validation of the NPI-Q, a brief clinical form of the Neuropsychiatric Inventory The Journal of neuropsychiatry and clinical neurosciences · 2000-01-01 · usefulness score 56/100 · Caregiving
• The Determinants of Quality of Life of Nursing Home Residents with Young-Onset Dementia and the Differences between Dementia Subtypes Dementia and Geriatric Cognitive Disorders · 2017-01-01 · usefulness score 56/100 · Caregiving

Later studies that cite this one

10 studies in the alzhub library list this one in their references. Showing the 8 highest-scoring.

• Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions Journal of medical systems · 2023-02-01 · usefulness score 62/100 · Digital health tools
• Development and validation of a novel predictive model for dementia risk in middle-aged and elderly depression individuals: a large and longitudinal machine learning cohort study Alzheimer s Research & Therapy · 2025-05-13 · usefulness score 60/100 · How common it is
• Artificial intelligence for dementia-Applied models and digital health Alzheimer's & dementia : the journal of the Alzheimer's Association · 2023-07-26 · usefulness score 56/100 · Digital health tools
• Parallel changes in cognition, neuropsychiatric symptoms, and amyloid in cognitively unimpaired older adults and those with mild cognitive impairment Alzheimer s & Dementia · 2025-02-01 · usefulness score 55/100 · Mild cognitive impairment
• Enhanced diagnostic interpretation of the MoCA using machine learning Frontiers in Neuroscience · 2026-02-20 · usefulness score 46/100 · Digital health tools
• Estimation of Machine Learning–Based Models to Predict Dementia Risk in Patients With Atherosclerotic Cardiovascular Diseases: UK Biobank Study JMIR Aging · 2025-01-20 · usefulness score 46/100 · Digital health tools
• Leveraging explainable artificial intelligence with ensemble of deep learning model for dementia prediction to enhance clinical decision support systems Scientific Reports · 2025-05-13 · usefulness score 44/100 · Digital health tools
• Enhancing the validity of CAIDE dementia risk scores with resting heart rate and machine learning: An analysis from the National Alzheimer's Coordinating Center across all races/ethnicities Alzheimer s & Dementia · 2025-08-01 · usefulness score 43/100 · Disparities

Related studies in Digital health tools

• Diagnostic performance of actigraphy in Alzheimer’s disease using a machine learning classifier – a cross-sectional memory clinic study Alzheimer s Research & Therapy · 2025-05-21 · usefulness score 51/100
• Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review Medical image analysis · 2020-10-06 · usefulness score 70/100
• Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review Alzheimer's research & therapy · 2021-09-28 · usefulness score 65/100
• Predicting the progression of MCI and Alzheimer’s disease on structural brain integrity and other features with machine learning GeroScience · 2025-04-26 · usefulness score 51/100
• Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases Acta Orthopaedica · 2025-07-07 · usefulness score 59/100
• Prediction of Postoperative Delirium in Geriatric Hip Fracture Patients: A Clinical Prediction Model Using Machine Learning Algorithms Geriatric orthopaedic surgery & rehabilitation · 2021-12-13 · usefulness score 52/100

Also tagged “prevalence”

1,224 studies in the library carry the topic tag “prevalence”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,224 tagged studies.

• Antipsychotic prescribing patterns in a Medicare Advantage population of older individuals with dementia Journal of Mental Health · 2016-11-12 · usefulness score 40/100 · Health systems and care delivery
• Undetected dementia in community-dwelling older people: the Canadian Study of Health and Aging Journal of the American Geriatrics Society · 2000-11-01 · usefulness score 46/100 · Clinical safety
• Stroke, disability, and dementia: results of a population survey Stroke · 1997-03-01 · usefulness score 55/100 · Disparities

Similar studies

• A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction 2020 · Digital health tools
• Using Machine Learning to Predict Dementia from Neuropsychiatric Symptom and Neuroimaging Data 2020 · Digital health tools
• Predicting Cognitive Impairment and Dementia: A Machine Learning Approach 2020 · Digital health tools
• Neuroimaging and Machine Learning for Dementia Diagnosis: Recent Advancements and Future Prospects 2019 · Digital health tools
• Machine learning for comprehensive forecasting of Alzheimer's Disease progression 2019 · Mild cognitive impairment
• Machine learning models to predict onset of dementia: A label learning approach 2019 · Digital health tools

More on Digital health tools

• A review that covers this ground Machine Learning Algorithms and Statistical Approaches for Alzheimer's Disease Analysis Based on Resting-State EEG Recordings: A Systematic Review International journal of neural systems · 2021-02-16 · usefulness score 55/100
• 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 →