Screening and Management of Obstructive Sleep Apnea and Daytime Sleepiness Among Professional Drivers in Tunisia: Protocol for a Machine Learning Study
Authors:
- Sameh MsaadSMSameh Msaad
- Nesrine KammounNKNesrine Kammoun
- Rahma GargouriRGRahma Gargouri
- Rim KhemakhemRKRim Khemakhem
- Amira TrikiATAmira Triki
- Narjes AbidNANarjes Abid
- Sonia FehriSFSonia Fehri
- Kaouthar KallelKKKaouthar Kallel
- Rim KammounRKRim Kammoun
- Leila Douik EL GharbiLGLeila Douik EL Gharbi
- Sonia MaalejBellajSMSonia MaalejBellaj
- Heni BouhamedHBHeni Bouhamed
Open Access
- 15 August 2025
- journal article
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 14, e70441
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 total of 127 male drivers participated in the study, with a mean age of 39.22 (SD 8.62) years. Most participants (76/127, 60.3%) had completed secondary education, 54.3% (69/127) were smokers, and the median BMI was 25.6 kg/m2. 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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Neck injury mechanisms in train collisions: Dynamic analysis and data mining of the driver impact injuryAccident Analysis & Prevention, 2020
- Employer-mandated obstructive sleep apnea treatment and healthcare cost savings among truckersSLEEP, 2020
- Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysisThe Lancet Respiratory Medicine, 2019
- Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan developmentTransportation Research Part C: Emerging Technologies, 2018
- Do management practices support or constrain safe driving behaviour? A multi-level investigation in a sample of occupational driversAccident Analysis & Prevention, 2017
- Validation de la version arabe de l’échelle de somnolence d’Epworth : étude multicentriqueRevue des Maladies Respiratoires, 2012
- Maintenance of Wakefulness Test, obstructive sleep apnea syndrome, and driving riskAnnals of Neurology, 2008
- A logistic model of the effects of roadway, environmental, vehicle, crash and driver characteristics on hit-and-run crashesAccident Analysis & Prevention, 2008
- Practice Parameters for Clinical Use of the Multiple Sleep Latency Test and the Maintenance of Wakefulness TestSLEEP, 2005
- A New Method for Measuring Daytime Sleepiness: The Epworth Sleepiness ScaleSLEEP, 1991