Prevalence of alcohol impairment and odds of a driver injury or fatality in on-road farm equipment crashes

Applying systems thinking to improve the safety of work-related drivers: A systematic review of the literature

INTRODUCTION

Light vehicles (<4.5 tons) driven for work purposes represent a significant proportion of the registered motor vehicles on our roads. Drivers of these vehicles have significant exposure to the dangers of the road transport environment. To optimize safety for these workers, it is critical to understand the factors contributing to risk of being involved in an incident. This information can then be used to inform the review and revision of existing risk controls and the development of targeted prevention activities.

METHOD

The aim of the study was to undertake a systematic review of the literature to identify the factors associated with work-related driving incidents. The factors identified in the review were represented within an adapted version of Rasmussen's risk management framework (Rasmussen, 1997). Fifty studies were analyzed following data screening and review of full text. The highest proportion of risk factors were categorized at the lower levels of the system, including the 'Drivers and Other Road Users' level (n = 20, 44.4%) and the 'Equipment, Environment, and Meteorological Surroundings' level (n = 19, 42.2%). There were no risk factors identified at the 'Regulatory and Government Bodies' levels of the framework, confirming the narrow investigative scope of past research and the need to acknowledge a broader range of factors within and across higher levels of the system.

CONCLUSIONS

The findings of this study inform the direction of future research and design of targeted prevention activities capable of creating system change for the safety of work-related drivers.

Traversing Community Attitudes and Interaction Experiences with Large Agricultural Vehicles on Rural Roads

Agriculture is one of Australia’s largest rural industries. Oversized and slow moving industry equipment and vehicles, hereafter referred to as large agricultural vehicles (LAVs), use public roads. Restrictions exist regarding their on-road operation, but whether this is a function of the risk that their on-road use represents is unknown. A convenience sample of community members was used to explore perspectives about LAVs’ presence on roads. An online survey was used to explore LAV interaction experiences, risk perceptions, and how best to promote safe interactions. Ethics approval was obtained. The participants’ (N = 239) exposure to LAVs on roads in the last 12 months was variable, but there were clear seasonal points when encounters could be expected. The participants indicated that LAVs have a right to drive on the road (94.8%), and most interactions were neutral, with four LAV crashes reported. Other vehicle types were perceived as representing a higher risk to rural road safety than LAVs. The use of the driver’s license test to increase knowledge about LAVs’ presence, how to respond, and the use of signs were suggested in order to improve safety. The participants commonly interacted with LAVs, and rarely experienced negative events such as crashes. Continued communication about LAV presence on rural roads is an important consideration in order to help ensure safe interactions.

Crash narrative classification: Identifying agricultural crashes using machine learning with curated keywords

OBJECTIVE

Traditionally, structured or coded data fields from a crash report are the basis for identifying crashes involving different types of vehicles, such as farm equipment. However, using only the structured data can lead to misclassification of vehicle or crash type. The objective of the current article is to examine the use of machine learning methods for identifying agricultural crashes based on the crash narrative and to transfer the application of models to different settings (e.g., future years of data, other states).

METHODS

Different data representations (e.g., bag-of-words [BoW], bag-of-keywords [BoK]) and document classification algorithms (e.g., support vector machine [SVM], multinomial naïve Bayes classifier [MNB]) were explored using Texas and Louisiana crash narratives across different time periods.

RESULTS

The BoK-support vector classifier (SVC), BoK-MNB, and BoW-SVC models trained with Texas data were better predictive models than the baseline rule-based algorithm on the future year test data, with F1 scores of 0.88, 0.89, 0.85 vs. 0.84. The BoK-MNB trained with Louisiana data performed the closest to the baseline rule-based algorithm on the future year test data (F1 scores, 0.91 baseline rule-based algorithm vs. 0.89 BoK-MNB). The BoK-SVC and BoK-MNB models trained with Texas and Louisiana data were better productive models for Texas future year test data with F1 scores 0.89 and 0.90 vs. 0.84. The BoK-MNB model trained with both states' data was a better predictive model for the Louisiana future year test data, F1 score 0.94 vs. 0.91.

CONCLUSIONS

The findings of this study support that machine learning methodologies can potentially reduce the amount of human power required to develop key word lists and manually review narratives.

Interpol review of toxicology 2016-2019

This review paper covers the forensic-relevant literature in toxicology from 2016 to 2019 as a part of the 19th Interpol International Forensic Science Managers Symposium. The review papers are also available at the Interpol website at: https://www.interpol.int/content/download/14458/file/Interpol%20Review%20.Papers%202019.pdf.

Examination of Realism in a High-fidelity Tractor Driving Simulator

Transportation-related incidents are the leading cause of occupational fatalities for all industries in the U.S., including the agricultural industry, which suffers thou- sands of crashes involving farm equipment each year. Simulated driving studies offer a safe and cost-effective way to conduct driving research that would not be feasible in the real world. A tractor driving miniSim was developed and then evaluated for realism at the University of Iowa among 99 Midwestern farm equipment operators. It is important for driving simulators to have a high degree of realism for their results to be applicable to non-simulated driving operations. High-fidelity driving simulators facilitate extrapolations made by driving research but should be re-tested for realism when changes are made to the design of the simulator. The simulator used in this study emulated a tractor cab with realistic controls, three high-resolution screens, and high-fidelity sound. After completing a 10-minute drive, farm equipment operators completed a survey and scored four specific domains assessing specific characteristics (i.e., appearance, user interface, control, and sound) of the tractor simulator's realism using a seven-point Likert scale (from 0 = not at all realistic to 6 = completely realistic). An overall realism score and domain scores were calculated. Farm equipment operators were also asked to provide recommendations for improving the tractor miniSim. Overall, farm equipment operators rated the simulator's realism favorably (i.e., >3 on a scale from 0 to 6) for all individual items and domains. The appearance domain received the highest average realism score (mean = 4.58, SD = 1.03), and the sound domain received the lowest average realism score (mean = 3.86, SD = 1.57). We found no significant differences in realism scores across farm equipment operator characteristics. The most frequently suggested improvements were to tighten the steering wheel (27%), make the front tires visible (19%), and that no improvements were needed to improve the simulator realism (18%). This study demonstrates that the new trac- tor miniSim is a viable approach to studying farm equipment operations and events that can lead to tractor-related crashes. Future studies should incorporate the suggested improvements and seek to validate the simulator as a research and outreach instrument.

A semi-automated tool for identifying agricultural roadway crashes in crash narratives

Objective: Crash reports contain precoded structured data fields and a crash narrative that can be a source of rich information not included in the structured data. The narrative can be useful for identifying vulnerable roadway users, such as agricultural workers. However, using the narratives often requires manual reviews that are time consuming and costly. The objective of this research was to develop a simple and relatively inexpensive, semi-automated tool for screening crash narratives and expediting the process of identifying crashes with specific characteristics, such as agricultural crashes. Methods: Crash records for Louisiana from 2010 to 2015 were obtained from the Louisiana Department of Transportation (LaDOTD). Records with narratives were extracted and stratified by vehicle type. The majority of analyses focused on a vehicle type of farm equipment (Type T). Two keyword lists, an inclusion list and an exclusion list, were created based on the published literature, subject-matter experts, and findings from a pilot project. Next, a semi-automated tool was developed in Microsoft Excel to identify agricultural crashes. Lastly, the tool's performance was assessed using a gold standard set of agricultural narratives identified through manual review. Results: The tool reduced the search space (e.g., number of narratives that need manual review) for narratives requiring manual review from 6.7 to 59.4% depending on the research question. Sensitivity was high, with 96.1% of agricultural crash narratives being correctly classified. Of the gold standard agricultural narratives, 58.3% included an equipment keyword and 72.8% included a farm equipment brand. Conclusion: This article provides information on how crash narratives can supplement structured crash data. It also provides an easy-to-implement method to facilitate incorporating narratives into safety research along with keyword lists for identifying agricultural crashes.