MMSE-Based Dementia Prediction: Deep vs. Traditional Models

Topic: Risk, prevention and care in population studies

Early and accurate diagnosis of dementia is essential to improving patient outcomes and reducing societal burden. The Mini-Mental State Examination (MMSE) is widely used to assess cognitive function, yet traditional statistical and machine learning approaches often face limitations in capturing nonlinear interactions and subtle decline patterns. This study developed a novel deep learning-based dementia prediction model using MMSE data collected from domestic clinical settings and compared its performance with traditional machine learning models. A notable strength of this work lies in its use of item-level MMSE features combined with explainable AI (SHAP analysis), enabling both high predictive accuracy and clinical interpretability-an advancement over prior approaches that primarily relied on total scores or linear modeling. Data from 164 participants, classified into cognitively normal, mild cognitive impairment (MCI), and dementia groups, were analyzed. Individual MMSE items and total scores were used as input features, and the dataset was divided into training and validation sets (8:2 split). A fully connected neural network with regularization techniques was constructed and evaluated alongside Random Forest and support vector machine (SVM) classifiers. Model performance was assessed using accuracy, F1-score, confusion matrices, and receiver operating characteristic (ROC) curves. The deep learning model achieved the highest performance (accuracy 0.90, F1-score 0.90), surpassing Random Forest (0.86) and SVM (0.82). SHAP analysis identified Q11 (immediate memory), Q12 (calculation), and Q17 (drawing shapes) as the most influential variables, aligning with clinical diagnostic practices. These findings suggest that deep learning not only enhances predictive accuracy but also offers interpretable insights aligned with clinical reasoning, underscoring its potential utility as a reliable tool for early dementia diagnosis. However, the study is limited by the use of data from a single clinical site with a relatively small sample size, which may restrict generalizability. Future research should validate the model using larger, multi-institutional, and multimodal datasets to strengthen clinical applicability and robustness.

Key findings

• These findings suggest that deep learning not only enhances predictive accuracy but also offers interpretable insights aligned with clinical reasoning, underscoring its potential utility as a reliable tool for early dementia diagnosis.

Why it matters

This study built a deep learning model using individual MMSE items to predict dementia and compared it with traditional machine learning models. It is a diagnostic prediction tool and does not address treating, curing or preventing Alzheimer's disease.

Study details

• Participants164
• Evidence strengthLow

Read the original

• DOI: 10.3390/life15101544
• PubMed: 41157217
• Original source →
• Free full text: Life →

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

@article{jung2025-41157217,
  author  = {Jung, Yuyeon and Park, Yeji and Jo, Jae-Hyun and Jeong, Jin-Hyoung},
  title   = {{MMSE-Based Dementia Prediction: Deep vs. Traditional Models}},
  journal = {Life},
  year    = {2025},
  doi     = {10.3390/life15101544},
  pmid    = {41157217},
  url     = {https://doi.org/10.3390/life15101544}
}

Studies this one cites

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

• 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
• Clinical prediction models using artificial intelligence approaches in dementia Aging Clinical and Experimental Research · 2025-07-25 · usefulness score 59/100 · Digital health tools
• “Mini-mental state” Journal of Psychiatric Research · 1975-11-01 · usefulness score 55/100 · Cognitive tests and assessment
• Cognitive performance classification of older patients using machine learning and electronic medical records Scientific Reports · 2025-02-24 · usefulness score 49/100 · Digital health tools

Related studies in Cognitive tests and assessment

• Streamlining eligibility assessment for Alzheimer's disease-modifying therapies: Prediction of MMSE scores using the digital clock and recall Frontiers in Digital Health · 2026-07-09 · usefulness score 43/100
• Deep Convolutional Neural Networks and Transfer Learning for Measuring Cognitive Impairment Using Eye-Tracking in a Distributed Tablet-Based Environment IEEE transactions on bio-medical engineering · 2020-12-21 · usefulness score 48/100
• Comparing Traditional and Technology-Based Methods for Executive Function and Attention Training in Moderate Alzheimer's Dementia Psicothema · 2025-01-01 · usefulness score 58/100
• Introduction to Large Language Models (LLMs) for dementia care and research Frontiers in dementia · 2024-05-14 · usefulness score 45/100
• Relationships between hourly cognitive variability and risk of Alzheimer's disease revealed with mixed-effects location scale models Neuropsychology · 2023-04-20 · usefulness score 41/100
• How Reliable and Explainable Are Machine Learning Models for Dementia Detection? A Leakage-Aware Evaluation Research Square · 2026-09-09 · usefulness score 16/100

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.

• Exploring cognitive and neuroimaging profiles of dementia subtypes of individuals with dementia in the Democratic Republic of Congo Frontiers in Aging Neuroscience · 2025-02-12 · usefulness score 44/100 · Getting a diagnosis
• P3‐509: FEASIBILITY OF A DEMENTIA VILLAGE IN SINGAPORE Alzheimer s & Dementia · 2018-07-01 · usefulness score 24/100 · Risk factors
• Trends in antipsychotic use in dementia 1999-2007 Archives of general psychiatry · 2011-02-01 · usefulness score 54/100 · Disparities

Similar studies

• Predicting Cognitive Impairment and Dementia: A Machine Learning Approach 2020 · Digital health tools
• Current Developments in Dementia Risk Prediction Modelling: An Updated Systematic Review 2015 · Prevention and risk
• Leveraging explainable artificial intelligence with ensemble of deep learning model for dementia prediction to enhance clinical decision support systems 2025 · Digital health tools
• Predicting dementia with routine care EMR data 2020 · Digital health tools
• A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data 2019 · Prevention and risk
• Prediction of dementia risk in low-income and middle-income countries (the 10/66 Study): an independent external validation of existing models 2020 · Long-term cohort studies

More on Cognitive tests and assessment

• A review that covers this ground Development of Neurodegenerative Disease Diagnosis and Monitoring from Traditional to Digital Biomarkers Biosensors · 2025-02-11 · usefulness score 43/100
• Newest in this subject A digital programme to prevent falls and improve wellbeing in people living with dementia in the community: Quantitative results from the KOKU-LITE feasibility study medRxiv · 2026-10-29 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Factors Influencing the Implementation of Computerized Cognitive Training in Chinese Community-Dwelling Elderly: A Qualitative Study Research Square · 2026-10-28 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Cognitive tests and assessment →