Cognitive Decline Profiles in Mild Cognitive Impairment: A Novel Convenient Multi‐Domain Screening Tool Perspective
Bibliographic record
Abstract
BACKGROUND: Mild cognitive impairment (MCI) is an intermediate stage between cognitively unimpaired (CU) and dementia, often considered a critical phase for early detection. Mini-Mental State Examination (MMSE) and Hippocampal volume (HV) are commonly used to evaluate cognitive impairment. However, the sensitivity of these methods for detecting early MCI remains relatively low. Montreal Cognitive Assessment (MoCA) is more sensitive than MMSE in detecting MCI but is also more time-consuming and complex, requiring greater examiner expertise. There is an unmet need for a screening tool quicker and more convenient than MoCA while being more sensitive than HV. The Virtual Reality Eye-tracking Cognitive Assessment (VECA) represents a novel approach that integrates virtual reality, eye-tracking technology, and machine learning to evaluate multiple cognitive domains efficiently. This study aims to explore cognitive decline patterns across MCI subgroups using VECA and compare its diagnostic performance to HV. METHODS: A total of 125 MCI patients and 190 CU individuals from the Shenzhen multi-modal Aging Research (STAR) cohort underwent neuropsychological assessments, VECA, and 3D-T1WI MRI. MCI patients were divided into four subgroups (Q1-MCI to Q4-MCI) based on their MoCA and MMSE scores. Statistical analyses were performed using SPSS 27.0. The performances were compared using the DeLong test in MedCalc. RESULTS: In the Q1-MCI subgroup, functions of abstraction, calculation, execution, memory, and recall consistently performed best. In the Q2-MCI and Q3-MCI subgroups, abstraction, calculation, execution, and memory functions consistently performed best. In the Q4-MCI subgroup, calculation, execution, and memory functions consistently performed best. No significant differences in attention function were observed among the four groups, with AUC values consistently demonstrating lower scores than other cognitive functions (p < 0.05). Besides, VECA (Total Score) demonstrated higher AUC values (0.746 for Q1-MCI subgroup, 0.845-0.964 for Q2-MCI to Q4-MCI subgroup) than HV in all subgroups (p < 0.05). CONCLUSION: VECA demonstrates strong potential as a rapid and efficient screening tool, requiring only 5 minutes to administer and consistently outperforming HV in differentiating MCI across all stages. VECA findings indicate that attention remains relatively preserved during MCI, while impairments in calculation, execution, and memory become progressively more pronounced in later stages.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".