Multi-modal approaches to Alzheimer's disease diagnosis: Combining cognitive assessments with biomarkers and imaging
Bibliographic record
Abstract
BackgroundAlzheimer's disease (AD) is a progressive neurodegenerative disorder where early diagnosis is essential for effective care.ObjectiveThis paper is set to compare the diagnostic performance of cognitive tests (Mini-Mental State Examination and Montreal Cognitive Assessment), serum biomarkers, EEG, and MRI separately and in combination with PET-CT results in the early diagnosis of AD.MethodsThe cognitive assessment was made in 384 individuals. blood sampling (biomarker tests), EEG monitoring, MRI, and PET-CT scans. Sensitivity, specificity, positive predictive value, and negative predictive value were used to determine diagnostic performance. The additional rule of probability and the product rule of probability were used to determine combined diagnostic power. ROC curves were plotted to visualize the performance of any modality.ResultsAmong 384 participants, PET-CT confirmed AD in 192 cases (50%). Serum biomarkers showed the highest individual sensitivity (77.60%), followed by MRI (69.79%), EEG (66.67%), and cognitive tests (62.50%). All modalities had a specificity of 84.90%. When combined using the addition rule of probability, diagnostic sensitivity increased to 99.15% and specificity to 99.95%. ROC curve analysis showed serum biomarkers and MRI had the highest diagnostic accuracy. The multi-modal approach significantly improved early diagnostic performance compared to single modalities.ConclusionsSerum biomarkers and MRI showed the best individual performance, though accuracy was only moderate. Combining modalities with the addition rule improved sensitivity and specificity markedly, while the product rule yielded low sensitivity and moderate specificity. Multimodal strategies may enhance early detection of AD but require further validation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.016 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.009 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".