P.013 Machine Learning on Drawing Tests of Cognition: A Systematic Review
Bibliographic record
Abstract
Background: Machine learning (ML) methods hold promise in allowing early detection of dementia. We performed a systematic review to assess the quality of published evidence for using ML methods applied to drawing tests of cognition, and to describe the accuracy of the methods. Methods: Embase, Medline, and Cochrane Central Library databases were searched for potential studies up to December 8, 2018 by four independent reviewers. Included articles satisfied the following criteria: 1) use of ML on 2) a drawing test in order to 3) assess cognition. The quality of evidence was then assessed using GRADE methodology. Results: The initial search yielded 4620 citations. Of these, 64 were eligible for full text review. 18 articles then met inclusion criteria. Median AUC across all models was 0.765, with certain ML algorithms performing better in terms of AUC or diagnostic accuracy. However, based on GRADE, the quality of evidence was deemed very low. Conclusions: ML has been applied by several groups to drawing tests of cognition. The quality of evidence is currently too low to make recommendations on their use. Future work must focus on improving reporting, and using standard algorithms and larger, more diverse datasets to improve comparability and generalizability.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.003 | 0.006 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.000 |
| Research integrity | 0.000 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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; both teacher heads agree on what is shown here.
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".