Toward Pre-Diagnostic Detection of Dementia in Primary Care
Bibliographic record
Abstract
BACKGROUND: Preventing dementia warrants the pragmatic engagement of primary care. OBJECTIVE: This study predicted conversion to dementia 12 months before diagnosis with indicators that primary care can utilize within the practical constraints of routine practice. METHODS: The study analyzed data from the Alzheimer's Disease Neuroimaging Initiative (Total sample = 645, converting participants = 54). It predicted the conversion from biological (plasma neurofilament light chain), cognitive (Trails Making Test- B), and functional (Functional Activities Questionnaire) measures, in addition to demographic variables (age and education). RESULTS: A Gradient Booster Trees classifier effectively predicted the conversion, based on a Synthetic Minority Oversampling Technique (n = 1,290, F1 Score = 92, AUC = 94, Recall = 87, Precision = 97, Accuracy = 92). Subsequent analysis indicated that the MCI False Positive group (i.e., non-converting participants with cognitive impairment flagged by the model for prospective conversion) scored significantly lower on multiple cognitive tests (Montreal Cognitive Assessment, p < 0.002; ADAS-13, p < 0.0004; Rey Auditory Verbal Learning Test, p < 0.002/0.003) than the MCI True Negative group (i.e., correctly classified non-converting participants with cognitive impairment). These groups also differed in CSF tau levels (p < 0.04), while consistent effect size differences emerged in the all-pairwise comparisons of hippocampal volume and CSF Aβ1 - 42. CONCLUSION: The model effectively predicted 12-month conversion to dementia and further identified non-converting participants with MCI, in the False Positive group, at relatively higher neurocognitive risk. Future studies may seek to extend these results to earlier prodromal phases. Detection of dementia before diagnosis may be feasible and practical in primary care settings, pending replication of these findings in diverse clinical samples.
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 | 0.007 | 0.029 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".