A machine learning approach to predict tau positivity using clinical features in amyloid‐positive individuals
Bibliographic record
Abstract
Abstract Background Anti‐amyloid therapy appears to have an increased effect on reducing cognitive decline in amyloid‐ and tau‐positive individuals. However, clinical trials inclusion criteria require solely amyloid positivity. Herein, we developed a machine‐learning prediction model to identify tau positivity in amyloid‐positive individuals using clinical variables. Method We selected 1191 amyloid‐positive participants and tau status from ADNI, TRIAD, PPMI databases. Commonly shared clinical features selected between datasets were age, total MOCA scores, clinical diagnosis, sex, education, BMI, heart disease, stroke, hyperlipidemia and diabetes. Amyloid positivity was defined by amyloid‐PET (PIB‐PET, FBB‐PET or AZD4694‐PET) or CSF AB42 and Tau positivity defined by Tau‐PET (MK6240‐PET or AV1451‐PET) or CSF p‐tau181. The dataset was split into training (49%), validation (21%), and testing datasets (30%). A XGBoost model was tuned, and then used to predict the tau status outcome in the testing dataset. Result A total of 647 men and 544 women were included with mean age 66.1 ± 10.4 (mean ± SD) years, MOCA 25.1 ± 4.1 scores and education 16.1 ± 3.2 years (Table). The population consisted of 794 controls, 271 MCI and 126 dementia individuals. Tau status was negative for 854 individuals and positive for 337. The receiver‐operator characteristic (ROC) analysis showed that the area under the curve (AUC) was 0.81 for discriminating tau‐negative vs. tau‐positive, with 0.76 as sensitivity, specificity as 0.86, and accuracy as 0.83. The top 3 most impactful features were found to be age, diagnosis‐CN and MOCA score through a SHAP value analysis (Figure). Conclusion Predicting tau positivity with clinical and cognitive variables may improve the selection of individuals for AD trials. A two‐step workflow using this approach may significantly reduce the need for tau‐PET exams in trials by screening individuals using clinical variables. The following steps should include adding more individuals and other clinical variables through different cohorts to optimize the model applicability and test their performance in outcomes of 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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".