Screening and Management of Obstructive Sleep Apnea and Daytime Sleepiness Among Professional Drivers in Tunisia: Protocol for a Machine Learning Study
Bibliographic record
Abstract
BACKGROUND: Obstructive sleep apnea (OSA) is highly prevalent among professional drivers; however, its true burden in this population remains underexplored and likely underdiagnosed. OBJECTIVE: This study aims to determine the prevalence of OSA and excessive daytime sleepiness (EDS) and identify their risk factors among a large representative sample of professional drivers in Tunisia. We will also evaluate the risk of accidents associated with OSA and EDS before and after the treatment. METHODS: This will be a population-based and prospective study of about 3000 professional drivers. Participants will receive a structured questionnaire to evaluate five main outcomes: the likelihood of OSA, EDS, drowsy driving, related sleepiness near misses and accidents, as well as work productivity. Validated self-report measures will be used to evaluate these outcomes. Participants suspected of having OSA or EDS will undergo sleep laboratory investigations, including a sleep study. Participants who have moderate-to-severe OSA will be recommended continuous positive airway pressure (CPAP) treatment. After one year of follow-up, all participants will be re-evaluated with self-report questionnaires. For those treated with CPAP, they will undergo the Maintenance of Wakefulness Test (MWT). We will evaluate several widely used machine learning models in medical diagnosis that are known for their high accuracy, including random forests, extreme gradient boosting, and deep neural networks, to predict the probability of OSA and its association with road traffic accidents. RESULTS: . A medical history was reported by 20.5% (26/127) of patients. The median driver experience was 8 (IQR 4.0-15.0) years. Among the drivers, 49 (39.5%) were working night shifts, and 30 (23.6%) were in hazardous materials transportation. Machinery (41.3%) was the most common mode of transportation, followed by trucks (34.9%), and light vehicles (22.2%). Notably, 11 drowsiness accidents were avoided. The overall score of presenteeism was 12.25 out of 100, whereas absenteeism was 1.74 out of 100. The overall daily activity impairment and productivity loss were 11.46 out of 100 and 12.76 out of 100, respectively. Overall, 30 (23.62%) cases were identified with either a pathological Epworth Sleepiness Scale or a positive Berlin score. CONCLUSIONS: Our preliminary findings revealed that a significant proportion of drivers were at a high risk of OSA. Our results will pave the way for the creation of a clinical screening instrument that can identify sleep-wake disturbances in professional drivers. This is likely to have a significant impact on the legal regulations concerning driving fitness and road safety.
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 | 0.011 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.035 | 0.006 |
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".