Classifying mild cognitive impairment from normal cognition: fMRI complexity matches tau PET performance
Bibliographic record
Abstract
INTRODUCTION: Cognitive decline in Alzheimer's disease (AD) is closely linked to tau pathology, which leads to loss of synaptic connections and ultimately neurons. While tau positron emission tomography (PET) carries radiation risks, is costly, and often unavailable in clinical settings, brain entropy mapping via resting-state functional magnetic resonance imaging (fMRI) has emerged as a marker of impaired brain function related to tauopathy. METHODS: Using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Estudio de la Enfermedad de Alzheimer en Jalisciences (EEAJ), we investigate the classification performance of fMRI entropy with tau PET in distinguishing cognitively normal (CN) from cognitively impaired (mild cognitive impairment/AD) individuals. Convolutional neural networks, initially trained and evaluated via 5-fold cross-validation on ADNI data, were subsequently tested on an independent external cohort (EEAJ) using an ensemble approach. RESULTS: The fMRI entropy classifier matched the tau PET model in accuracy and outperformed it in F1 score (0.64 vs. 0.61) and area under the curve (AUC; 0.73 vs. 0.67). On the independent external validation dataset (EEAJ), fMRI sample entropy showed a comparable F1 score (0.88) to tau PET (0.88) and achieved a notably higher AUC (0.94 vs. 0.92). DISCUSSION: Our findings suggest that fMRI entropy could be a non-invasive imaging marker alternative to tau PET for detecting AD-related cognitive impairment. Highlights: Functional magnetic resonance imaging (fMRI) complexity matches tau positron emission tomography (PET) in classifying cognitive impairment.Sample entropy and multiscale entropy were used for fMRI-based Alzheimer's disease (AD) classification.3D convolutional neural networks models achieve up to 84% accuracy using fMRI complexity measures.The dorsal attention network was identified as critical for distinguishing mild cognitive impairment/AD.fMRI complexity offers a non-invasive alternative to tau positron emission tomography imaging.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".