Time‐dependent biomarker accuracy in forecasting mild cognitive impairment
Bibliographic record
Abstract
BACKGROUND: Several biomarkers have been proposed for predicting the risk of progression of asymptomatic individuals to mild cognitive impairment (MCI). However, there is the need of characterizing the dynamic change in their accuracy as a function of the time between biomarker collection and MCI diagnosis. In addition, the potential contribution of direct measures of neurophysiological activity for estimating the risk of MCI progression has not been explored in depth. METHOD: We assessed spectral power features from task-free magnetoencephalographic (MEG) recordings, MRI-derived hippocampal volumes, plasma biomarkers, and PET measures of Aβ and tau deposition in a group of cognitively unimpaired older adults with a family history of AD (N = 102). From this sample, 31 individuals developed MCI based on a multidisciplinary consensus who had access to longitudinal neuropsychological assessments but were blind to biomarker information (mean time between biomarkers collection and MCI diagnosis = 4 years; SD = 1.9 years). We benchmarked these biomarkers using a series of logistic regression models to assess the temporal evolution of their accuracy for predicting MCI progression, in combination with clinical information (Figure 1). RESULT: Neurophysiological activity features and tau pet provided additional information to the clinical model when acquired up to ∼4 years prior to diagnosis, but their accuracy decreased at larger intervals. In contrast, the accuracy gained by incorporating Aβ PET or plasma biomarkers remained high up to 6 years before diagnosis (Figure 2). These observations were confirmed after running stepwise logistic regression on the model including all biomarkers, highlighting the contribution of age, sex, plasma p-tau217, Aβ and tau PET and neurophysiological activity for predicting MCI progression at different time intervals (Figure 3). CONCLUSION: Overall, our results delineate a timeline of the accuracy provided by different biomarkers for predicting progression to MCI. Such findings highlight the dynamic sensitivity of different biomarkers, which is dependent on the time lapse between biomarkers collection and clinical diagnosis. This is particularly relevant for future clinical trials that intend to use biomarkers for screening participants.
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 | 0.011 | 0.038 |
| 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 | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".