Using subject‐specific disease progression as an estimation of the disease time to model longitudinal neurodegeneration in AD
Bibliographic record
Abstract
Abstract Background When patients with clinically probable‐AD get their diagnosis, it is difficult to determine exactly when the disease started. Moreover, not all subjects progress in the same manner and rate. However, clinical measurements such as cognitive scores can help give an estimation of where in the disease trajectory each patient stands. To address the issue of estimating the time of disease onset, we investigated a new technique that leverages cognitive test scores to estimate a latent timeline that models the subject‐specific disease progression. Method We used the work of Kühnel et al. (2021) to model the progression of AD using cognitive scores (ADAS13 and MMSE). This method aligns patients along a continuous latent timeline based on their predicted disease progression. Data included the MRI scans of 677 amyloid‐positive subjects from ADNI. Scan resolution was increased to 0.5mm isotropic voxel‐size by super‐sampling (Manjón et al. 2010) before non‐linear registration to an ADNI‐based unbiased template. The resulting deformation fields were used to compute the Jacobian determinant map for each subject and find mean atrophy for different ROIs. we were then able to plot the changes in different regions of the brain across the estimated disease progression timeline and compare slopes for the two methods. Result Assuming a zero time‐shift for normal subjects, the average time‐shift for the eMCI, lMCI, and AD group was 36.8, 87.5, and 128.8 months respectively. Using the latent time‐shift variable to offset the individual baseline scans, we were able to plot the changes in different regions of the brain across the disease timeline. The results for Hippocampus are shown in figure 1, comparing the estimated timeline to the age as the time‐related axes. We saw much sharper slopes (‐0.01 vol/estimated_time vs ‐0.0025 vol/age) when using the individualized time offset. Conclusion Calendar time is perhaps not a good measure for disease progression. The new method offers an estimation of a latent timeline that models the subject‐specific disease progression and may better model the longitudinal changes in different brain regions, and in turn, would enable us to better compare the magnitude and speed of degeneration across brain regions.
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 | 0.005 | 0.006 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".