Feeling sleepy? stop driving—awareness of fall asleep crashes
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study investigates whether drivers are aware of their sleepiness and whether subjective reports of sleepiness symptoms can predict subsequent driving impairment and physiological drowsiness. Motivated by the significant public health burden of drowsy driving, which contributes to a substantial portion of serious injury and fatal crashes, the research addresses a critical gap in understanding how well drivers recognize warning signs in real-world conditions. While previous studies often relied on simulators or retrospective data, this prospective, on-road study aimed to determine which specific self-reported symptoms best predict adverse driving outcomes and provide optimal thresholds for when drivers should cease driving. The researchers employed a within-subject, cross-over design involving sixteen night-shift workers who drove an instrumented vehicle for two hours on a closed-loop track after both a night of sleep and a night of work. Subjective sleepiness and specific symptoms were rated every 15 minutes using the Karolinska Sleepiness Scale (KSS), Likelihood of Falling Asleep (LFA), and a Sleepiness Symptoms Questionnaire (SSQ). Objective measures included driving impairment, defined by emergency brake maneuvers (severe) and lane deviations (moderate), and physiological drowsiness, measured via eye-closure metrics (Johns Drowsiness Scores) and EEG-based microsleep events. Statistical analyses, including binary logistic regression and receiver operating characteristic (ROC) curve analysis, were used to assess the predictive value of subjective ratings for adverse events in the subsequent 15-minute interval. The results demonstrated that all subjective sleepiness ratings and symptom frequencies significantly increased after the night shift compared to the post-sleep condition. Crucially, no severe driving events (emergency braking) occurred without noticeable symptoms beforehand. Subjective ratings, particularly ocular symptoms like struggling to keep eyes open and vision blurring, as well as difficulty maintaining lane position, were strong predictors of severe driving events in the next 15 minutes, with high accuracy (AUC > 0.81). However, predicting moderate lane deviations was less accurate (AUC 0.59–0.65). All sleepiness ratings also predicted severe ocular-based drowsiness with very good-to-excellent accuracy (AUC > 0.8), while moderate drowsiness and microsleep events were predicted with fair-to-good accuracy. Notably, "head dropping" was a poor predictor of severe driving events compared to other symptoms. The study concludes that drivers are generally aware of sleepiness and that many self-reported symptoms, especially those related to eyes and driving performance, reliably predict subsequent impairment and physiological drowsiness. The findings imply that public safety messaging should encourage drivers to monitor a wide range of specific symptoms rather than relying solely on a general sense of sleepiness. Ignoring early warning signs such as blurred vision or difficulty staying in the lane significantly increases crash risk. Therefore, drivers should be advised to stop driving immediately upon experiencing these symptoms to mitigate the escalating danger of drowsy driving.
Key finding
Subjective sleepiness ratings and specific symptoms, particularly ocular issues and difficulty keeping to the center of the road, significantly predicted subsequent severe driving impairment and physiological drowsiness events.
Methodology
on_road
Sample size: 16
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via author_sweep_intake on 2026-05-28.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-28 |
| archive | success | openalex | — | — | 9 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-28 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- drowsiness
- drowsiness detection algorithms
- microsleep
- sleep deprivation
- truck driver fatigue
- drowsy as impairment
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data