Rapid cognitive testing predicts real-world driving risk in commercial and medically at-risk drivers
Bibliographic record
Abstract
Abstract Road safety is a major public and occupational health issue. Safe driving requires numerous cognitive and sensorimotor skills, and past literature suggests that cognitive testing can predict safe or unsafe driving in both healthy and medically at-risk drivers. However, such testing is often time-consuming and inaccessible. In this study, we designed a modified version of the Trail Making Test (TMT) which can be completed on a smartphone in approximately 5 minutes. We recruited 4405 commercially-licensed drivers and 314 medically at-risk drivers to complete the TMT, plus an on-road test of their driving abilities. We then trained and tested a logistic regression model using 50-50 splits on each dataset. The results of the model showed that the longer it took drivers in both groups to complete the TMT, the more likely they were to fail the on-road driving test. Accuracy for the commercial group was 83.8%, with a positive predictive value (PPV) of 34.4% and a negative predictive value (NPV) of 85.3%. Accuracy for the medically at-risk group was 63.1%, with a PPV of 55.8% and an NPV of 65.8%. Overall accuracy was 82.5%, with a PPV of 43.0% and an NPV of 84.3%. Log-transformed reaction time to targets was significantly associated with on-road failure in both driving groups. The results of this study suggest that a rapid and accessible version of the TMT can predict unsafe driving with comparable accuracy to more time-consuming and administratively burdensome means of testing.
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 | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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 | 0.001 |
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".