Journal of Safety Research最新文献

{"title":"Prevalence of hearing loss among noise-exposed U.S. workers within the Construction sector, 2010–2019","authors":"Elizabeth A. Masterson,&nbsp;Christa L. Themann","doi":"10.1016/j.jsr.2024.11.005","DOIUrl":"10.1016/j.jsr.2024.11.005","url":null,"abstract":"<div><div><em>Background:</em> The purpose of this cross-sectional study is to estimate the prevalence of hearing loss among noise-exposed U.S. workers during 2010–2019 within the Construction sector. <em>Methods:</em> Audiograms for 26,653 workers at 833 Construction companies (and for 1.3 million other workers) were examined. Period prevalence and adjusted risk for hearing loss as compared with a reference industry (Couriers and Messengers) were estimated for the Construction sector and sub-sectors, and all industries combined. <em>Results:</em> The prevalence of hearing loss within the Construction sector was 23% compared to 20% for all industries combined. Several sub-sectors exceeded the overall prevalence and all but two had adjusted risks significantly higher than the reference industry. The sub-sectors with the highest prevalences for hearing loss were: Highway, Street, and Bridge Construction (28%), Site Preparation Contractors (26%), New Single-Family Housing Construction (except Operative Builders) (25%), Oil and Gas Pipeline and Related Structures Construction (25%), and Other Building Finishing Contractors (25%). The sub-sectors with the highest adjusted risks were Industrial Building Construction; Other Heavy and Civil Engineering Construction; Oil and Gas Pipeline and Related Structures Construction; Finish Carpentry Contractors; and Site Preparation Contractors; with risks 62%, 61%, 60%, 59% and 58% higher than the reference industry, respectively. <em>Conclusions:</em> Hearing loss continues to be a significant issue within Construction. Reducing noise exposure is critical, including buying quieter equipment, keeping moving parts oiled and well-maintained, enclosing noise sources, and employing administrative controls to reduce the number of workers in noisy areas. Barriers to workers consistently and correctly wearing their hearing protection also need to be addressed. <em>Practical Applications:</em> Within Construction, hazardous noise is common and the risk of hearing loss is high. This study identified the Construction sub-sectors with the highest prevalences and risks to guide interventions toward workers most in need of prevention and described strategies for reducing exposures.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 158-165"},"PeriodicalIF":3.9,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety climate and fatigue have differential impacts on safety issues","authors":"Adam T. Biggs ,&nbsp;Jason Jameson ,&nbsp;Todd R. Seech ,&nbsp;Rachel Markwald ,&nbsp;Christopher Paight ,&nbsp;Dale W. Russell","doi":"10.1016/j.jsr.2024.11.017","DOIUrl":"10.1016/j.jsr.2024.11.017","url":null,"abstract":"<div><div><em>Introduction:</em> Safety climate describes a collection of perceptions and practices that encapsulate the general attitude toward safety within an organization. A better safety climate presumably leads to a safer and more effective workplace. However, there are many contributing factors to safety outcomes, and these variables may interact with the safety climate to affect actual safety behaviors. <em>Method:</em> This study examined fatigue as a possible moderator between safety climate and safety outcomes, including actual safety incidents reported, near-misses experienced, and safety underreporting. Structural equation modeling explored this question using a large dataset (N &gt; 11,000) gathered from naval personnel who operate in a challenging work environment and must regularly contend with the consequences of fatigue. <em>Results:</em> Results indicated a differential effect on the relationship between safety climate and safety outcomes; that is, safety climate affected underreporting the most, followed by likelihood of experiencing a near-miss, but had the weakest impact on actual safety reporting. Conversely, fatigue had a comparable impact across all safety outcomes, both directly as a moderating influence when accounting for safety climate. <em>Practical Applications:</em> These findings suggest that safety climate may differentially affect safety outcomes, but fatigue appears to have the same impact across different types of safety issues despite their severity.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 142-147"},"PeriodicalIF":3.9,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Great to use as a conversation starter: End user views on the acceptability and feasibility of a prototype decision aid for older drivers","authors":"Nadine Veerhuis ,&nbsp;Melanie Randle ,&nbsp;Victoria Traynor","doi":"10.1016/j.jsr.2024.11.006","DOIUrl":"10.1016/j.jsr.2024.11.006","url":null,"abstract":"<div><div><em>Background:</em> Conversations about driving with older adults are often emotionally laden and decisions about retiring from driving can be challenging. Tailored tools, such as evidence-based decision aids could support conversations and decisions about driving for older adults. This study aimed to explore the acceptability and feasibility of a prototype decision aid for older drivers from the perspective of end-users. <em>Method:</em> This qualitative cross-sectional study utilized an online survey with 106 adults living in Australia. The 36-page web-based decision aid prototype was developed for older drivers living in New South Wales, Australia, using a co-design approach with multiple stakeholders. <em>Results:</em> Respondents were healthcare professionals, older adults, family members, or friends of older adults and other professional groups. Decision aid acceptability was high. The presentation of the aid was highly regarded by older adults and healthcare professionals. The length and comprehensiveness were salient characteristics and could impact utility for healthcare professionals and older adults. Personal stories, risks, and incentives for driving retirement were important content to include. Various benefits of the decision aid were highlighted: supporting conversations and decision making about driving decisions and planning for future mobility changes. <em>Conclusions:</em> The older driver decision aid was a supported approach by healthcare professionals and family members to guide conversations and decision-making about driving with older adults. The decision aid triggered older adults to reflect upon their current driving, think about ways to stay safe on the road, or plan for alternatives to driving in the future. <em>Practical applications:</em> The older driver decision aid could be a useful tool for Australian healthcare professionals and family members when approaching a conversation and decision-making about driving with older adults. Using the decision aid may prompt older adults to reflect upon various aspects of decisions about driving early in the decision pathway.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 121-132"},"PeriodicalIF":3.9,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating perspectives towards online content that promotes road safety: A qualitative study across three age groups","authors":"Michelle Nicolls,&nbsp;Verity Truelove,&nbsp;Kayla B. Stefanidis","doi":"10.1016/j.jsr.2024.11.018","DOIUrl":"10.1016/j.jsr.2024.11.018","url":null,"abstract":"<div><div><em>Introduction</em>: Social media is an ideal platform for displaying online material that promotes road safety and discourages road rule violations. However, limited research has investigated the impact of online material promoting road safety on attitudes and behavior, and whether different age groups are influenced by such content. <em>Method:</em> The qualitative study explored: (a) opinions and attitudes towards online material/content that promotes road safety/discourages illegal driving behavior; (b) whether participants believe this content can influence attitudes/behavior; and (c) whether these opinions differed across age groups. Sixty-six licensed Queensland drivers participated in a focus group. Three age groups were included: young drivers (17–25 years; <em>n</em> = 21), middle-aged drivers (26–49 years; <em>n</em> = 22), and older drivers (50 + years; <em>n</em> = 23). <em>Results:</em> The data were analyzed using reflexive thematic analysis, resulting in four themes: (1) Metrics behind a persuasive message, (2) Diverse and compelling content, (3) Demographics matter, (4) Each to their own. <em>Conclusions:</em> There is the potential for social media to help promote road safety messages. Therefore, these findings have important implications for road safety messaging strategies and future research. <em>Practical Applications:</em> Future research could benefit by exploring ways to increase exposure to online material promoting road safety and determining which social media platforms are more likely to promote road safety material, with consideration to online algorithms.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 133-141"},"PeriodicalIF":3.9,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatial analysis of telematics-based surrogate safety measures","authors":"Dimitrios Nikolaou ,&nbsp;Apostolos Ziakopoulos ,&nbsp;Armira Kontaxi ,&nbsp;Athanasios Theofilatos ,&nbsp;George Yannis","doi":"10.1016/j.jsr.2024.09.012","DOIUrl":"10.1016/j.jsr.2024.09.012","url":null,"abstract":"<div><div><em>Introduction</em>: Surrogate Safety Measures (SSMs) such as time-to-collision, harsh braking, and post-encroachment time, are widely proposed in transportation science and are fruitful for road safety evaluations when detailed crash data are unavailable. Hence, this study aims to conduct spatial analysis of harsh braking events to explore their adaptability and informative power in a region with low crash counts, as this approach remains briefly addressed in the literature. <em>Method:</em> The analysis utilizes smartphone driving behavior data and OpenStreetMap road network characteristics of 6,103 road segments in the Region of Eastern Macedonia and Thrace, Greece. A series of advanced statistical and machine learning models were applied. In addition to developing non-spatial models, the identification of spatial autocorrelation led to the development of spatial modeling techniques to account for spatial dependencies. <em>Results:</em> The number of trips per segment, segment length, speeding and mobile phone use are positively correlated with harsh braking. Conversely, motorways exhibited fewer harsh braking events compared to other road types. Furthermore, the number of trips per examined road segment was the most influential predictor, highlighting its importance as a proxy measure of risk exposure. In terms of model performance, the Spatial Zero-Inflated Negative Binomial (SZINB) model outperformed the corresponding non-spatial model. Moreover, the Spatial Random Forest (SRF) model reduced the absolute values of spatial autocorrelation in the residuals and showed a better fit to the observed data compared to the conventional Random Forest model. <em>Conclusions:</em> Geometrical and behavioral parameters can be combined to meaningfully conduct road safety analysis spatially and proactively, as they are highly correlated with harsh braking SSMs, while the SZINB and the SRF model exhibited better model fit than their non-spatial counterparts. <em>Practical Applications:</em> The study results can assist policymakers in developing appropriate countermeasures to reduce harsh braking in targeted spatial units, thereby enhancing overall road safety.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 98-108"},"PeriodicalIF":3.9,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The ROADS project: Road observational assessment of driving distractions","authors":"Marko Gjorgjievski ,&nbsp;Bradley Petrisor ,&nbsp;Sheila Sprague ,&nbsp;Silvia Li ,&nbsp;Herman Johal ,&nbsp;Bill Ristevski","doi":"10.1016/j.jsr.2024.11.016","DOIUrl":"10.1016/j.jsr.2024.11.016","url":null,"abstract":"&lt;div&gt;&lt;div&gt;&lt;em&gt;Background&lt;/em&gt;: Globally, motor-vehicle collisions cause 1.35 million deaths and more than 78 million injuries every year, with distracted driving contributing to many of these tragedies. Our main objective was to covertly determine the proportion of distracted drivers in live traffic. &lt;em&gt;Methods:&lt;/em&gt; ROADS was a covert observational study conducted from November 2020–June 2021. We observed drivers on the highways and urban streets between Hamilton and Toronto, Ontario. The research team observed drivers of moving vehicles and collected data covertly while driving beside them in live traffic. Moving passenger vehicles ahead of the research team were randomly screened for inclusion. Stopped/parked vehicles, buses, and semi-trucks were excluded. Demographic and safety variables included estimated age and sex, seatbelt usage, and two-handed driving. Driving distractions were categorized as in-vehicle, outer-vehicle, and mobile phones. Driving errors, such as lane drift, evasive maneuvers, and near-crash/crash, were recorded. We analyzed associations between demographic and situational variables (weekday/weekend, urban/highway, presence/absence of passenger) and distracted driving, as well as associations between driving errors and distracted driving. &lt;em&gt;Results:&lt;/em&gt; Of the observed 1,105 drivers, 609 (55.1%) were distracted. In-vehicle distractions (42.3%, 467/1105) were most prevalent, while 151 (13.7%) drivers were using mobile phones. Hands-free usage was observed in 92 (8.3%) drivers, while 63 (5.7%) drivers used a handheld device, visibly manipulating (3.4%, 38/1105), or actively talking (2.3%, 25/1105). Of the 24 (2.2%) drivers observed exhibiting driving errors, 23 (95.8%) drivers were visibly distracted. Younger estimated age (under 30 years old: OR 2.0, CI 1.320–3.105; 30–50 years old: OR 1.5, CI 1.090–1.925), and driver errors were significantly associated with distracted driving (p &lt; 0.005). Sex, urban vs highways, and weekday vs weekend did not demonstrate a statistically significant association with distracted driving. &lt;em&gt;Conclusion:&lt;/em&gt; By covertly observing moving vehicles while actively participating in live traffic, we identified that 55.1% of drivers were distracted, and approximately one in seven drivers used their mobile phones. Of the 24 drivers who were recorded making driving errors, an astounding 95.8% (23) were distracted, with two-thirds of these drivers illegally engaging with their phones. Also, driving on city streets versus highways (&gt;60 km/hr) did not play a role in distracted driving. All this indicates that distracted driving is not only prevalent but also pervasive. Future research should focus on targeted driver education and behavioral modification. &lt;em&gt;Practical Applications:&lt;/em&gt; This data can be applied towards driver education programs counseling drivers on dangerous distracting behaviors, as well as influencing legislature, informing, and providing law enforcement insight into worri","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 91-97"},"PeriodicalIF":3.9,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perception of distraction and risk among drivers engaging in non-driving tasks: Findings from a German study","authors":"Maria Kreusslein ,&nbsp;Katja Schleinitz ,&nbsp;Markus Schumacher","doi":"10.1016/j.jsr.2024.11.019","DOIUrl":"10.1016/j.jsr.2024.11.019","url":null,"abstract":"<div><div><em>Introduction:</em> One of the leading causes of traffic crashes is the distraction of drivers caused by performing secondary tasks. <em>Method:</em> We conducted a nationwide interview study with car drivers in Germany. A total sample of 1,072 drivers participated in a face-to-face semi-standardized interview based on quota sampling. Almost 90% of all drivers performed a secondary task. <em>Results:</em> On average, drivers reported two non-driving-related activities in the last 30 min of driving. The most frequent activities were interactions with passengers, internal distractions (e.g., intense thinking, singing), and operating vehicle instruments. Mobile phone operations were mentioned less frequently, and texting, reading, and browsing were reported in 6% of the activities. Texting, reading, browsing, and hand-held phoning were rated as the most distracting and risky. Drivers perceive secondary tasks like passenger interaction and hygiene as less risky. The risk ratings when performing a secondary task were significantly lower than the overall risk rating of the respective task. Demographic analysis showed that women rated some tasks as riskier than men, while older drivers perceived higher risks than younger ones. <em>Conclusion:</em> The findings on the frequency of performed secondary tasks illustrate that drivers underestimate the risks of seemingly trivial secondary activities. Age and gender influence risk perception and distraction. <em>Practical implication</em>: Raising awareness of the negative consequences of engaging in activities that appear insignificant is advisable. Information about the crash risk of all secondary tasks should be provided more often (e.g., in commercials, especially for tasks that appear trivial and safe to perform while driving). Additionally, interventions aimed at promoting safer driving practices should consider demographic factors, such as age and gender, to enhance their effectiveness.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 109-120"},"PeriodicalIF":3.9,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Driving a car under the influence of alcohol in Germany: Results from a trip-based self-report measurement","authors":"Bernhard Schrauth","doi":"10.1016/j.jsr.2024.10.001","DOIUrl":"10.1016/j.jsr.2024.10.001","url":null,"abstract":"<div><div><em>Introduction:</em> Driving under the influence of alcohol comprises a serious road safety issue. A comprehensive investigation is challenging and a high number of unreported cases of driving under the influence of alcohol is suspected. Existing methods, including roadside surveys or period-based self-reports, are either difficult to implement or may lack informative value. <em>Method:</em> This paper describes a newly developed questionnaire-based survey conducted in a nationwide online survey in Germany that measures the prevalence of driving under the influence of alcohol via self-reports concerning randomly selected trips from 7 days prior. The trip-based data collection includes details about the reported car ride. Expected low case numbers are addressed by additionally recording the last trip driven under the influence of alcohol from the previous week. <em>Results:</em> Within the previous 7 days, 6.3% of the surveyed drivers had driven under the influence of alcohol. Further analyses aligned with familiar patterns from prior research: Age, sex, daytime, and days of the week significantly predict driving under the influence of alcohol. However, attitudes toward stricter rules are also identified as a factor. <em>Conclusions:</em> The proposed survey design enables the current findings to surpass results of previous surveys and yields data comparable to roadside survey results. The questionnaire proved feasible in conducting the survey and gathered valid findings that correspond to international research and traffic crash data. For Germany, in particular, and in alignment with familiar patterns related to times and days, the findings point to the likelihood that particularly males and younger drivers will drive under the influence of alcohol. <em>Practical Applications:</em> The proposed survey concept adds a new variant to the set of instruments for recording driving under the influence of alcohol by determining a trip-based prevalence, thus offering new insights into driving under the influence in alcohol of Germany.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"91 ","pages":"Pages 447-464"},"PeriodicalIF":3.9,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characteristics of media-reported road traffic crashes related to new energy vehicles in China","authors":"Shuying Zhao ,&nbsp;Peixia Cheng ,&nbsp;David C. Schwebel ,&nbsp;Min Zhao ,&nbsp;Lei Yang ,&nbsp;Wangxin Xiao ,&nbsp;Guoqing Hu","doi":"10.1016/j.jsr.2024.11.012","DOIUrl":"10.1016/j.jsr.2024.11.012","url":null,"abstract":"<div><div><em>Introduction</em>: New energy vehicles (NEVs) refer to vehicles entirely or primarily powered by energy sources outside of conventional fuels. As the number of NEVs increases, road traffic crashes related to NEVs have emerged as a new challenge for road traffic injury prevention. However, basic epidemiological data are scarce concerning NEV-related crashes. <em>Methods</em>: Using media-reported crash data from the Automated Road Traffic Crash Data Platform (ARTCDP), a data platform developed and validated by our research group to gather eligible reports automatically and systematically from online Chinese media concerning road traffic crashes, we examined the characteristics of new energy vehicles between 2015 and 2022 in China. <em>Results:</em> The ARTCDP captured 2,927 crashes related to NEVs from 2015 to 2022, accounting for 1.1% of total number of motor vehicle-related crashes indexed by the ARTCDP during the same time period. Of them, 2,262 (77.3%) crashes occurred in east and central China. NEV-related traffic crashes occurred most often on urban roads (68.8%), well-lit roads (72.2%), roads without adequate safety infrastructure facilities (63.2%), and at intersections (78.7%). 1,864 media reports described the reason for the crash, with 44.1% listing two or more factors to explain the NEV-related crashes. Brake system failure and dangerous or improper driving operations were more frequently reported in NEV-related crashes than in other motorvehicle crashes (55.6% vs. 18.3% and 37.5% vs. 20.8%, <em>P</em> &lt; 0.01). NEV-related crashes occurred more often on rainy days and on foggy or smoggy days than other motor-vehicle crashes (83.6% vs. 72.2% and 4.1% vs. 0.7%, <em>P</em> &lt; 0.01). <em>Conclusions</em>: Media-reported news elucidate distinct characteristics of road traffic crashes involving NEVs versus other motor vehicles in China. <em>Practical applications:</em> NEV-related crashes represent an emerging road traffic safety challenge in China and worldwide. Characteristics revealed by media-reported NEV-related crashes merit the attention of policymakers, automobile industry, researchers, and law enforcement.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 48-54"},"PeriodicalIF":3.9,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk of crashes among self-employed truck drivers: Prevalence evaluation using fatigue data and machine learning prediction models","authors":"Rodrigo Duarte Soliani ,&nbsp;Alisson Vinicius Brito Lopes ,&nbsp;Fábio Santiago ,&nbsp;Luiz Bueno da Silva ,&nbsp;Nwabueze Emekwuru ,&nbsp;Ana Carolina Lorena","doi":"10.1016/j.jsr.2024.11.002","DOIUrl":"10.1016/j.jsr.2024.11.002","url":null,"abstract":"<div><div><em>Introduction</em>: Transportation companies have increasingly shifted their workforce from permanent to outsourced roles, a trend that has consequences for self-employed truck drivers. This transition leads to extended working hours, resulting in fatigue and an increased risk of crashes. The present study investigates the factors contributing to fatigue and impairment in truck driving performance while developing a machine learning-based model for predicting the risk of traffic crashes. <em>Method:</em> To achieve this, a comprehensive questionnaire was designed, covering various aspects of the participants’ sociodemographic characteristics, health, sleep, and working conditions. The questionnaire was administered to 363 self-employed truck drivers operating in the State of São Paulo, Brazil. Approximately 63% of the participants were smokers, while 17.56% reported drinking alcohol more than four times a week, and also admitted to being involved in at least one crash in the last three years. Fifty percent of the respondents reported consuming drugs (such as amphetamines, marijuana, or cocaine). <em>Results:</em> The surveyed individuals declared driving for approximately 14.62 h (SD = 1.97) before they felt fatigued, with an average of approximately 5.92 h of sleep in the last 24 h (SD = 0.96). Truck drivers unanimously agreed that waiting times for truck loading/unloading significantly impact the duration of their working day and rest time. The study employed eight machine learning algorithms to estimate the likelihood of truck drivers being involved in crashes, achieving accuracy rates ranging between 78% and 85%. <em>Conclusions:</em> These results validated the construction of accurate machine learning-derived models. <em>Practical Applications</em>: These findings can inform policies and practices aimed at enhancing the safety and well-being of self-employed truck drivers and the broader public.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 68-80"},"PeriodicalIF":3.9,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}