Greater AD prediction accuracy is obtained using hippocampal grading over hippocampal volume
Bibliographic record
Abstract
Abstract Background To develop new Alzheimer’s disease (AD) treatments, diagnostic tools must be applied before too much irreversible neurodegeneration occurs. One of the key features used to identify AD neurodegeneration is hippocampal (HC) volume. However, prediction accuracy using HC volume is not high enough to be implemented in clinical and research settings. The goal of this study was to compare prediction accuracy of HC volume and HC grading, a method that measures local morphological similarity of the HC to a library of NC and AD subjects. Methods Participants were selected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and were included if they had a baseline diagnosis of either healthy older adult (cognitively normal, CN) or AD and baseline MRI scans. A total of 841 older adults met the inclusion criteria (513 CN and 328 AD). A second analysis examining the 388 amyloid positive participants was also completed (179 CN and 209 AD). A previously validated MRI analysis method (SNIPE) was used for HC grading (Coupe et al., 2012) and a similar non‐local patch‐based method was used to segment the HC to obtain volumes (Coupe et al. 2010). HC volumes provided by ADNI using Freesurfer were also analyzed for comparison. Age, sex, and either SNIPE grading, SNIPE volume, or Freesurfer volumes were used as features in three support vector machines to classify participants as either CN or AD, using a 10‐fold cross validation. Results Using SNIPE grading, 88% accuracy was obtained when classifying CN from AD. SNIPE volume, generated 76% accuracy, while Freesurfer HC volume resulted in 67% accuracy when distinguishing CN from AD. The second analysis of only the amyloid positive participants yielded accuracies of 87% (SNIPE Grading), 77% (SNIPE volume), and 52% (Freesurfer volume). Conclusion HC grading, as measured by SNIPE, provides much higher accuracy at classifying CN from AD than both patch‐based HC segmentation volumes or Freesurfer HC volumes. These findings suggest that HC grading may be a useful tool at successfully predicting AD. The ability to correctly differentiate between groups who are amyloid positive is important for improving participant selection in clinical trials.
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 | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".