Early detection of cognitive decline with deep learning and graph-based modeling
Bibliographic record
Abstract
In today's world, increasing stress and depression significantly impact cognitive well-being, making early detection of cognitive impairment essential for timely intervention. This work introduces a Multimodal Fusion Cognitive Assessment Framework that leverages advanced deep learning and graph intelligence to enhance early identification accuracy. Traditional tools like the Montreal Cognitive Assessment (MOCA) are limited in adaptability, prompting the need for a more dynamic, data-driven approach. The framework is validated using datasets involving cognitive tests, voice samples, and physiological signals. It enables a scalable, personalized, and adaptive cognitive assessment system that improves early detection and supports targeted intervention strategies. By integrating deep learning and information fusion, this approach addresses the complexity of cognitive health in a modern context.•This paper introduces Multimodal Deep Learning Integration, incorporating MOCA scores, behavioral data, speech signals, and physiological parameters using GAT, TAT, and CNN-LSTM models to capture diverse cognitive indicators.•The proposed model achieves superior performance through Information Fusion via Heterogeneous GNNs, effectively merging cross-domain data to enable holistic cognitive state assessment via inter-modality learning.•This paper applies Reinforcement Learning (RL) to personalize user interactions based on real-time cognitive and stress cues, reducing cognitive overload and enhancing engagement.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".