Clinical Experience with SATURN, a Public Domain Self-administered Cognitive Screening Test (P5-12.002)
Bibliographic record
Abstract
Objective: Validation via regular clinical use of a free, public domain, automatically scored, and self-administered cognitive screening test. Background: Emerging therapies for neurodegenerative disease are directed at patients with little cognitive impairment. How do we efficiently identify these patients? Universal screening with paper-and-pencil tests like the Mini Mental State Exam (MMSE) or the Montreal Cognitive Assessment (MoCA) is cost-prohibitive due to clinician time investment. Self-Administered Tasks Uncovering Risk of Neurodegeneration (SATURN) is a tablet-based cognitive screening test designed to bypass that cost. After a small validation study, SATURN was integrated into regular clinical use alongside paper-and-pencil tests. We hypothesized that SATURN’s psychometric properties continued to compare favorably to paper-and-pencil tests. Design/Methods: We will retrospectively analyze data from every patient (n>500) visiting one dementia sub-specialist clinic over a 24-month period. To-date, we have analyzed 66 patients’ records. We documented visit diagnoses and SATURN, MoCA, and MMSE scores. Primary analyses (1) use regression to test whether SATURN is well-correlated with the other tests, and (2) compare test scores to clinical diagnosis using receiver operating characteristic (ROC) curves. Results: For this interim analysis, we analyzed patients (n=37) who met prespecified inclusion criteria and also had scores for at least two of the three aforementioned tests. Clinical diagnoses – normal (n=8), mild cognitive impairment (n=16), and dementia (n=13) – were strongly associated with (mean±sd) test scores (SATURN: 27±3, 18±5, 13±6) (MoCA: 25±3, 20±4, 15±4) (MMSE: 30±0, 25±2, 21±6) (each p<0.02; one-way ANOVA). ROC curves were statistically similar for all three tests (p>0.10). SATURN was well-correlated with MoCA (n=24 tested with both: r=0.87, p<0.0001), and MMSE (n=20 with both: r=0.81, p<0.0001). MMSE and MoCA were also correlated (n=17 with both: r=0.69, p=0.002). Conclusions: The freely-available SATURN (https://doi.org/10.5061/dryad.02v6wwpzr) is comparable to the MoCA and MMSE in regular clinical practice; a prerequisite for larger-scale efforts to efficiently screen for cognitive impairment. Disclosure: Dr. Florendo has nothing to disclose. Dr. Bissig has received personal compensation in the range of $100,000-$499,999 for serving as a Physician with University of California - Davis.
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 | 0.008 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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) | 0.003 | 0.002 |
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".