Association between integrated cognitive assessment (ICA) and measures of brain structure in mild cognitive impairment and mild Alzheimer’s disease
Bibliographic record
Abstract
Abstract Background Integrated Cognitive Assessment (ICA) is an artificial intelligence‐assisted test for cognitive assessment in mild cognitive impairment (MCI) and Alzheimer’s Disease (AD) (Khaligh‐Razavi et al., 2019). ICA is shown to be accurate in detection of subtle cognitive impairments in MCI/ AD, and have demonstrated a strong association with the level of neural damage, as measured by NfL. However, the link between ICA and measurements of brain atrophy has not been studied yet. Here, we investigated the link between participant’s performance in ICA test and their cortical volume and thickness; we were further interested to see whether the impairment detected by ICA precedes that of brain atrophy. Method High‐resolution (1mm3) MRI scans were acquired from 45 participants (age= 64.63±7.46): 15 MCI patients, 10 mild AD, and 20 healthy controls (HC). All the participants took ICA. Structural images of the brain were then reconstructed using FreeSurfer software for volumetric and cortical thickness measurements. Result ICA shows significant correlations with cortical thickness in various brain regions, such as part of the lingual and parahippocampal cortex (r= 0.7, p<10‐11), lateral occipital (r= 0.48, p<10‐6), inferior temporal (r= 0.43, p<10‐5) and fusiform (r=0.4, p<10‐4) in the left hemisphere. Within the right hemisphere, ICA has a significant correlation with precuneus (r= 0.45, p<10‐5) and lateral occipital (r=0.5, p<10‐7). ICA has a large effect size (Cohen’s d= 0.95, p<0.001) in differentiating HC from MCI and HC from mild AD (Cohen’s d= 1.98, p<0.0001). Cortical thickness and left hippocampal volume could differentiate HC from mild AD (Cohen’s d= 0.88, p<0.05; and d= 0.8, p<0.05 respectively), but not HC from MCI. Conclusion We found a significant association between participants’ ICA score and the thickness of the cortex in some of the key brain areas, including parahippocampal, that are anatomically identified among the early areas affected by tau‐pathology (Braak and Braak, 1991). Furthermore, participant’s ICA score could better differentiate HC from MCI or mild AD compared to their hippocampal volume, suggesting that impairment in ICA performance precedes that of hippocampal volume.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".