Application of tablet-based cognitive tasks to predict unsafe drivers in older adults
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Due to aging and medication interferences, a wide range of motor, sensory, and cognitive skills that are imperative for driving are affected in older adults. Though on-road tests are most indicative of driving ability, they are costly, stressful, time-consuming, and risky. Application of tablet-based cognitive tasks is investigated in identifying unsafe drivers in a population of healthy and at-risk for driving older adults. Forty-nine older adult participants aged 54 to 81 (M = 78.08, SD = 9.78) that were screened by their physicians as “at-risk for driving impairment”, and forty-eight control participants aged 54 to 81 years (M = 65.85, SD = 6.93) completed an on-road driving test designed specifically to evaluate cognitive decline related to driving, and a set of tablet-based cognitive tasks (composed of reaction speed, decision making, memory, and bi-manual perceptual-motor tasks) that measured the cognitive skills needed during driving. Accuracy and reliability of predicting unsafe drivers based on the cognitive tasks were investigated using different trichotomous classifiers (class outputs: safe, unsafe, undefined). Trichotomous naive Bayes demonstrated the highest overall accuracy performance of 73%, a sensitivity of 69%, and a specificity of 75%. The rate of misclassified unsafe drivers was 19%, and the rate of misclassified safe drivers was 8%. High accuracy and reliable prediction of unsafe drivers using cognitive-only tasks in a sample of older adults population demonstrate the efficacy of a widely available screening tool that can be applied in other cognitively impaired populations such as drug users.
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.
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 | 0.001 | 0.000 |
| 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it