Fatigue driving is one of the leading causes of traffic accidents, posing a significant threat to drivers and road safety. Most existing methods focus on studying whole-brain multi-channel electroencephalogram (EEG) signals, which involve a large number of channels, complex data processing, and cumbersome wearable devices. To address this issue, this paper proposes a fatigue detection method based on frontal EEG signals and constructs a fatigue driving detection model using an asymptotic hierarchical fusion network. The model employed a hierarchical fusion strategy, integrating an attention mechanism module into the multi-level convolutional module. By utilizing both cross-attention and self-attention mechanisms, it effectively fused the hierarchical semantic features of power spectral density (PSD) and differential entropy (DE), enhancing the learning of feature dependencies and interactions. Experimental validation was conducted on the public SEED-VIG dataset. The proposed model achieved an accuracy of 89.80% using only four frontal EEG channels. Comparative experiments with existing methods demonstrate that the proposed model achieves high accuracy and superior practicality, providing valuable technical support for fatigue driving monitoring and prevention.
Humans ; Electroencephalography/methods* ; Automobile Driving ; Fatigue/diagnosis* ; Accidents, Traffic/prevention & control* ; Signal Processing, Computer-Assisted ; Neural Networks, Computer ; Algorithms ; Prefrontal Cortex/physiology*

Electroencephalogram (EEG) serves as an effective indicator of detecting fatigue driving. Utilizing the open accessible Shanghai Jiao Tong University Emotion Electroencephalography Dataset (SEED-VIG), driving states are divided into three categories including awake, tired and drowsy for investigation. Given the characteristics of mutual influence and interdependence among EEG channels, as well as the consistency of the graph convolutional neural network (GCNN) structure, we designed an adjacency matrix based on the Pearson correlation coefficients of EEG signals among channels and their positional relationships. Subsequently, we developed a GCNN for recognition. The experimental results show that the average classification accuracy of driving state categories for 20 subjects, from the SEED-VIG dataset under the smooth feature of differential entropy (DE) linear dynamic system is 91.66%. Moreover, the highest classification accuracy can reach 98.87%, and the average Kappa coefficient is 0.83. This work demonstrates the reliability of this method and provides a guideline for the research field of safe driving brain computer interface.
Humans ; Electroencephalography/methods* ; Neural Networks, Computer ; Fatigue/physiopathology* ; Automobile Driving ; Brain-Computer Interfaces ; Signal Processing, Computer-Assisted ; Convolutional Neural Networks

PURPOSE: Attention-deficit/hyperactivity disorder (ADHD) increases the risk of road traffic injuries through various mechanisms including higher risky driving behaviors. Therefore, drivers with ADHD are shown to be more prone to road traffic injuries. This study was conducted in a community-based sample of drivers to determine how ADHD affects driving behavior components. METHODS: At the cross-sectional phase of a national population-based cohort, a representative sample of 1769 drivers were enrolled. Manchester driving behavior questionnaire and Conners' adult ADHD rating scales were used to assess driving behavior and ADHD symptom scores, respectively. Data were analyzed using Stata version 17. Multiple linear regression was used to investigate the association of driving behavior with ADHD while adjusting for the potential confounding role of age, sex, marital status, educational level, driving history, etc. RESULTS: According to the results, the normalized driving behavior score of drivers with ADHD was 4.64 points higher than drivers without ADHD. Having an academic compared to school education, increased the driving behavior score by 1.73 points. The normalized driving behavior score of drivers under 18 years of age was 6.27 points higher than drivers aged 31-45 years. The score of the aggressive violation subscale of drivers with ADHD was 7.33 points higher than drivers without ADHD compared to an increment of a range of 4.50-4.82 points for other driving subscales. The score of the ordinary violation subscale of female drivers was 2.23 points lower than that of male drivers. No significant relationship was found between sex and other subscales of driving. CONCLUSION Drivers with ADHD who are in adolescence or early adulthood exhibit more dangerous and aggressive driving behaviors than those who are older. Implementing training interventions to increase awareness of drivers with ADHD, their families, and psychologists regarding the effects of ADHD on driving is an essential step in preventing motor vehicle crashes among drivers with ADHD.
Humans ; Attention Deficit Disorder with Hyperactivity/psychology* ; Automobile Driving/psychology* ; Male ; Adult ; Female ; Middle Aged ; Cross-Sectional Studies ; Accidents, Traffic ; Iran ; Adolescent ; Surveys and Questionnaires ; Young Adult ; Cohort Studies ; Risk-Taking

BACKGROUND: Technological innovations in the public transport sector are increasingly leveraged to support the goals of environmental sustainability and public health. Eco-driving assistance (EDA) systems represent one such intervention, aimed at reducing fuel consumption, emissions, and operating costs while improving passenger comfort. However, the potential unintended impacts of EDA technologies on driver health and well-being remain understudied. The EDA Trial, part of the EU-funded INTERCAMBIO project, seeks to evaluate whether the use of EDA systems may introduce new psychosocial stressors for professional drivers, with implications for occupational and public health. METHODS: The EDA tested in this trial is called "NAVIG". Buses will be assigned randomly. Operating EDA-equipped vehicle will be considered as intervention condition, operating vehicle without EDA as control. Each participant will be monitored for 10 working days maximum to accumulate at least 5 intervention shifts during the trial. Heart rate variability (HRV) will be continuously recorded during working hours to assess autonomous stress responses. The root mean square of successive differences (RMSSD) will be averaged over intervention and control shifts to enable within-subject comparisons between intervention and control conditions. Subjective stress levels will be evaluated using the self-report instruments: Cohen's perceived stress scale at baseline and visual analogous scale at baseline and daily. Moreover, neuroendocrine stress biomarkers (salivary cortisol and cortisone) will be collected repeatedly across shifts, as additional outcomes. Mixed-effects models with participant's ID as a random effect variable will be used to compare stress outcomes between EDA and non-EDA driving conditions. Models will be adjusted for potential confounders. RESULTS: A sample size of 26-40 participants was estimated to provide 80% power (α = 0.05) to detect differences of 12-15% between conditions. Ethical approval was obtained from the Swissethics (CER-VD 2024-01573), and participant recruitment is ongoing, with 27 drivers enrolled as of June 2025. CONCLUSIONS: This study will provide empirical evidence on the potential health trade-offs associated with implementing eco-driving technologies in real-world settings. By assessing physiological and psychological stress responses to EDA, the trial supports a more integrated approach to environmental technology evaluation-one that considers not only energy efficiency but also the health and sustainability of the workforce. TRIAL REGISTRATION The trial was registered in the ClinicalTrials.gov database (NCT06688721).
Humans ; Automobile Driving/psychology* ; Stress, Psychological ; Motor Vehicles ; Adult ; Male ; Randomized Controlled Trials as Topic ; Female

PURPOSE: This study aimed to investigate the possible association between psychological disorders and risky driving behavior (RDB) in Iran. METHODS: This case-control study conducted in Shiraz, Iran in 2021. The case group included drivers with psychological disorders and the control group included those without any disorders. The inclusion criteria for selecting patients were: active driving at the time of the study, being 18 - 65 years old, having a driving license, having a psychological disorder including depression, bipolar disorder, anxiety spectrum disorder, or psychotic disorder spectrum confirmed by a psychiatrist, and completing an informed consent form. The exclusion criterion was the existence of conditions that interfered with answering and understanding the questions. The inclusion criteria for selecting the healthy cases were: active driving at the time of the study, being 18 - 65 years old, having a driving license, lack of any past or present history of psychiatric problems, and completing an informed consent form. The data were gathered using a researcher-made checklist and Manchester driving behavior questionnaire. First, partition around medoids method was used to extract clusters of RDB. Then, backward logistic regression was applied to investigate the association between the independent variables and the clusters of RDB. RESULTS: The sample comprised of 344 (153 with psychological disorder and 191 without confirmed psychological disorder) drivers. Backward elimination logistic regression on total data revealed that share of medical expenditure ≤ 10% of total household expenditure (OR = 3.27, 95% CI: 1.48 - 7.24), psychological disorder (OR = 3.08, 95% CI: 1.67 - 5.70), and substance abuse class (OR = 6.38, 95% CI: 3.55 - 11.48) were associated with high level of RDB. CONCLUSION Substance abuse, psychological illnesses, and share of medical costs from total household expenditure were found to be main predictors of RDB. Further investigations are necessary to explain the impact of different psychological illnesses on driving behavior.
Humans ; Adolescent ; Young Adult ; Adult ; Middle Aged ; Aged ; Automobile Driving ; Iran ; Case-Control Studies ; Mental Disorders/epidemiology* ; Surveys and Questionnaires ; Risk-Taking

Humans ; Accidents, Traffic ; Automobile Driving ; Risk Factors

Objective: This study aims to identify the epidemiological characteristics and co-morbidities of eyelid injuries among Filipino patients seen at the Emergency and Out-patient Clinics of a single, tertiary, government, urbanbased hospital from June 2014 to June 2015. Methods: This is a retrospective, cross-sectional, descriptive single-center study. Medical records of 85 patients who consulted at the Emergency or Out-Patient Clinics of the Department of Ophthalmology and Visual Sciences of the Philippine General Hospital, Manila due to eyelid injuries that resulted to skin breaks with or without tissue loss or other ocular co-morbidities were reviewed. Information collected included: demographic data of the patient; the offending object; mechanism, place, date and time of injury; date and time of consult; possible risk factors and predisposing conditions such as alcohol intoxication and lack of use of protective gears. Complications associated with eyelid injuries were also noted. Descriptive statistics was used for analysis of patient demographics, epidemiologic characteristics of eyelid injuries and its associated complications. Results: Of the 85 cases, 78% were males. Most of the patients were below 50 years of age with a range of 1-79 and a mean age of 25 years old. There is male preponderance across all age groups except in the pediatric group below 10 years of age. The right eye was involved in 58% of cases. The most common area affected was the right lower lid as seen in 36 cases. Most of the eyelid injuries were severe: 21 (25%) were margin-involving, 17 (20%) had canalicular transection and 34 (40%) had both. Other co-morbidities included some degree of tissue loss or avulsion (16%) and globe involvement (29%). Majority were accidental (36%). Public places (33%) and the home (33%) were the most common places of injury. Most of the injuries that happened at home were accidents (82%) while those that occurred in public places were mostly assault cases (71%). The most common offending objects that caused the eyelid injuries included metal (33%), pavement/cement (18%), and wood (16%). The most common mechanism of injury was blunt trauma (67%). There were 18 cases of vehicular crash, 89% of the patients were not wearing helmets. All work-related injuries reported absence of protective gear. Alcohol intoxication was reported in 30% of assault cases and 72% of vehicular crash. Conclusion Eyelid injuries continue to pose as a public health concern. Campaigns organized toward educating the public can stress on the importance of increased vigilance regarding safety especially in children and young adults. Use of protective gear and eyewear while driving or working in hazardous environments should also be emphasized. Monitoring of public places for any disturbance can prevent violent acts from escalating. The AntiDrunk and Drugged Driving Act of 2013 should also be strictly enforced.
Accidents ; Driving Under the Influence

PURPOSE: Traffic accidents are one of the major health problems in the world, being the first cause of burden of illness and the second leading cause of death in Iran. The Sistan-Baluchestan province is one of the most accidental provinces of Iran with the highest rate of accidents-caused deaths. This study was conducted to determine the risk factors associated with traffic accidents in Zahedan through 2013 to 2016. METHODS: This analytical cross-sectional study was carried out on 223 drivers from Zahedan who were traumatized by traffic accident and sent to Zahedan hospitals. The data were obtained through interviews taken by the trained interviewers via refereeing to the medical records and collected in the researcher-made checklist. Census was obtained from the study subjects. For data analysis, independent t-test, one-way ANOVA, Chi-square and logistic regression were used with the Stata software version 11.0. RESULTS: In this study, 223 male subjects with the mean age of (32.54 ± 12.95) years, 39.8% single and 60.2% married, entered for investigation. Most accidents (38.8%) occurred between 12:00 to 17:59. While driving, 47.1% of the study subjects were using cell phones, 89.1% had manual use of mobile phones, 21.9% had a habit of sending short message service (SMS) and 23.4% had sent SMS within 10 min before the accident. The one way analysis of variance showed that the mean age of individuals with marital status, driving experience, education and accident with motorcycle were significantly different (p < 0.05). Also, the multivariate logistic regression test indicated a significant relationship of smoking, ethnicity, insurance and SMS typing while driving with motorcycle accident (p < 0.05). CONCLUSION In this study, SMS and smoking while driving had the highest risk among the variables studied in the motorcycle accidents. Therefore, effective education attempting to enhance people's awareness about the consequences of using cell phone and smoking during driving to reduce traffic accidents seems necessary.
Accidents, Traffic/statistics & numerical data* ; Adolescent ; Adult ; Aged ; Aged, 80 and over ; Automobile Driving ; Cause of Death ; Cell Phone Use/adverse effects* ; Cross-Sectional Studies ; Female ; Health Education ; Humans ; Iran/epidemiology* ; Male ; Marital Status ; Middle Aged ; Risk ; Smoking/adverse effects* ; Young Adult

PURPOSE: Road traffic accidents (RTAs) are a public health issue and cost a lot to individuals, families, communities and nations. Trauma care systems in India are at a nascent stage of development. There is gross disparity between trauma services available in various parts of the country. Rural area in India has inefficient services for trauma care, due to the varied topography, financial constraints, and lack of appropriate health infrastructure. The present study is to study the trends of occurrence of RTA cases by month, week and time of accident occurrence as well as to research the types of vehicle involved in accidents and other various risk factors related to them. METHODS: During 1st January 2017 to 31st December 2017, a hospital-based and cross-sectional study of RTA victims was conducted. The patients were admitted in emergency department of Uttar Pradesh University of Medical Sciences, Saifai, Etawah, when stabilized, they were shifted to the orthopaedics and surgery ward. RESULTS: In the study, 654 road accident victims were included, of which the majority were males (77.5%) and the most of them belonged to rural (67%). RTA victims according to the month of occurrence majority were found in January (12.5%) and evening was time of a day with maximum accidents (32.1%). Mortality cases of RTA victims based on type of road user and it shows decreasing trend of mortality of motorcyclists (54.2%) followed by pedestrian (25.1%). CONCLUSION There should be control over people driving vehicles under the influence of alcohol and drivers over-speeding and rash driving on urban roads as well as rural village roads.
Accidental Injuries ; epidemiology ; mortality ; prevention & control ; Accidents, Traffic ; prevention & control ; statistics & numerical data ; Adolescent ; Adult ; Automobile Driving ; Cross-Sectional Studies ; Emergency Service, Hospital ; statistics & numerical data ; Female ; Humans ; Male ; Middle Aged ; Risk Factors ; Seasons ; Tertiary Care Centers ; statistics & numerical data ; Time ; Young Adult

Objective To explore the characteristics of individuals with mental disorders suspected of road traffic offences and to find their differences from normal offenders, in order to regulate mental disorder patients' driving activities and prevent road traffic offences. Methods One hundred and twenty-three cases of forensic psychiatry testimony of individuals suspected of road traffic offences between 2014 and 2019 from the West China Forensic Center of Sichuan Province were collected. Fisher exact probability test was used to compare the differences between offenders with mental disorders and without mental disorders in terms of demographic characteristics, criminological characteristics, psychiatric characteristics and criminal responsibilities. Results There was no statistical significance in the differences of demographic characteristics, vehicles and kinds of alcohol between the two groups （P>0.05）. The main type of road traffic related crimes committed by offenders with mental disorders was risky driving and were mainly evaluated as partial criminal responsibility, whereas most offenders without mental disorders committed crime of causing traffic casualties and all were evaluated as full criminal responsibility. There was statistical significance in the differences of the types of crime and the criminal responsibility rating between the two groups （P<0.05）. Meanwhile, patients with mental disorders were characterized by long course of disease and irregular treatment, and individuals diagnosed as having mental disorders caused by psychoactive substances accounted for a large proportion. Conclusion There are differences in the characteristics of road traffic-related crimes between mental disorder patients and normal people. It is of great practical significance for reducing road traffic offences to evaluate whether the individuals with mental disorders are fit for driving.
Automobile Driving ; China/epidemiology* ; Crime ; Criminals ; Forensic Psychiatry ; Humans ; Mental Disorders/epidemiology*