A Machine Learning-Based Framework for differential screening of Neurodegenerative Dementias using routine clinical data

Topic: Brain imaging, connectivity and assessment

Background The increasing prevalence of neurocognitive disorders (NCDs), including Alzheimer’s disease (AD), vascular dementia (VaD), dementia with Lewy bodies (DLB), primary progressive aphasia (PPA), and behavioral variant frontotemporal dementia (bvFTD), highlights the need for accessible tools to support early diagnosis. Machine learning (ML) may enhance diagnostic accuracy by leveraging routinely collected clinical information. We evaluated an ML pipeline based exclusively on first-visit neurological assessments to support differential diagnosis of major NCDs. Methods We retrospectively analysed clinical data from 932 patients. A CatBoost multiclass classifier was trained using 43 routinely available variables, including demographic characteristics, neurological signs, and symptom chronology. Bayesian optimization (Optuna) was used to maximize the macro-averaged F1-score while addressing class imbalance. Model interpretability was assessed through SHAP (SHapley Additive exPlanations), enabling patient-level and global feature attribution. Performance was evaluated on a held-out test set using accuracy, precision, recall, and F1-score. Results The model achieved 73.8% overall accuracy, with a macro F1-score of 0.646 and a weighted F1-score of 0.743. Diagnostic performance was highest for AD (F1 = 0.821), followed by DLB (0.704), bvFTD (0.681), PPA (0.667), and VaD (0.357). SHAP analysis identified first symptom, age at diagnosis, and language symptom chronology as the most influential predictors, closely reflecting established clinical diagnostic criteria. Conclusions Symptom chronology emerged as a robust diagnostic discriminator, underscoring the clinical value of temporal disease trajectories. The prototype Streamlit interface demonstrated practical clinical deployment by providing probabilistic predictions with transparent explanations. These findings support clinically driven, biomarker-free ML models as scalable first-line decision-support tools, particularly in resource-limited settings, while emphasizing the need for prospective multicenter external validation before clinical implementation.

Key findings

• Results The model achieved 73.8% overall accuracy, with a macro F1-score of 0.646 and a weighted F1-score of 0.743.
• The prototype Streamlit interface demonstrated practical clinical deployment by providing probabilistic predictions with transparent explanations.
• These findings support clinically driven, biomarker-free ML models as scalable first-line decision-support tools, particularly in resource-limited settings, while emphasizing the need for prospective multicenter external validation before clinical implementation.

New to this subject? Start with our plain-English guide: Getting a diagnosis →

Study details

• Participants932
• Effect size73.8%
• Evidence strengthLow

Read the original

• DOI: 10.21203/rs.3.rs-10815316/v1
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

@article{vilella2026-6ddf0c22,
  author  = {Vilella, D. and Tafuri, B. and Urso, D. and Rollo, E. and Giannoni-Luza, S. and Gigli, G. and Tartaglione, B. and Logroscino, G.},
  title   = {{A Machine Learning-Based Framework for differential screening of Neurodegenerative Dementias using routine clinical data}},
  journal = {Research Square},
  year    = {2026},
  doi     = {10.21203/rs.3.rs-10815316/v1},
  url     = {https://doi.org/10.21203/rs.3.rs-10815316/v1}
}

Related studies in Getting a diagnosis

• Explainable Machine Learning-Based Classification of Clinical Dementia Ratings Using a Tablet-Based Cognitive Assessment International Journal of Computational Intelligence Systems · 2025-11-17 · usefulness score 35/100
• Mayo Normative Studies: Regression-based normative data for remote self-administration of the Stricker Learning Span, Symbols Test, and Mayo Test Drive Screening Battery Composite and validation in individuals with mild cognitive impairment and dementia The Clinical Neuropsychologist · 2025-03-11 · usefulness score 50/100
• Machine Learning–Based Cognitive Assessment With The Autonomous Cognitive Examination: Randomized Controlled Trial Journal of Medical Internet Research · 2025-07-30 · usefulness score 47/100
• Investigating dementia patterns by machine learning and graph-based marker analysis for multiclass dementia diagnosis Discover Computing · 2026-05-18 · usefulness score 35/100
• Neuropsychological tests and machine learning: identifying predictors of MCI and dementia progression Aging Clinical and Experimental Research · 2025-03-12 · usefulness score 40/100
• Multi-model deep learning for dementia detection: addressing data and model limitations Frontiers in Neuroscience · 2025-11-25 · usefulness score 35/100

Similar studies

• Predictive Models for Cognitive Decline Assessment 2026 · Long-term cohort studies
• How Reliable and Explainable Are Machine Learning Models for Dementia Detection? A Leakage-Aware Evaluation 2026 · Cognitive tests and assessment
• Boosting power for clinical trials using classifiers based on multiple biomarkers 2010 · Digital health tools
• Machine Learning and Novel Biomarkers for the Diagnosis of Alzheimer's Disease 2021 · Digital health tools
• Artificial Intelligence for Alzheimer’s Disease Detection Across Neuroimaging and Speech: A Reproducible Cross-Modal Secondary Analysis 2026 · Digital health tools
• Multivariate data analysis and machine learning in Alzheimer's disease with a focus on structural magnetic resonance imaging 2014 · Digital health tools

More on Getting a diagnosis

• A review that covers this ground Clinical Neurology and Epidemiology of the Major Neurodegenerative Diseases Cold Spring Harbor perspectives in biology · 2018-04-02 · usefulness score 51/100
• Newest in this subject The Contribution of Routinely Collected Clinical Data to Dementia Identification in Primary Care: A Cross-Sectional Study Research Square · 2026-10-28 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Beyond “Denial”: Understanding and Responding to Help-Refusal in Dementia Preprints.org · 2026-10-26 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Getting a diagnosis →