Machine learning approaches to analysing textual injury surveillance data: A systematic review

Objective To synthesise recent research on the use of machine learning approaches to mining textual injury surveillance data. Design Systematic review. Data sources The electronic databases which were searched included PubMed, Cinahl, Medline, Google Scholar, and Proquest. The bibliography of all relevant articles was examined and associated articles were identified using a snowballing technique. Selection criteria For inclusion, articles were required to meet the following criteria: (a) used a health-related database, (b) focused on injury-related cases, AND used machine learning approaches to analyse textual data. Methods The papers identified through the search were screened resulting in 16 papers selected for review. Articles were reviewed to describe the databases and methodology used, the strength and limitations of different techniques, and quality assurance approaches used. Due to heterogeneity between studies meta-analysis was not performed. Results Occupational injuries were the focus of half of the machine learning studies and the most common methods described were Bayesian probability or Bayesian network based methods to either predict injury categories or extract common injury scenarios. Models were evaluated through either comparison with gold standard data or content expert evaluation or statistical measures of quality. Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes. However, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed. Conclusions The use of narrative text for injury surveillance has grown in popularity, complexity and quality over recent years. With advances in data mining techniques, increased capacity for analysis of large databases, and involvement of computer scientists in the injury prevention field, along with more comprehensive use and description of quality assurance methods in text mining approaches, it is likely that we will see a continued growth and advancement in knowledge of text mining in the injury field.

Injury narrative text classification using factorization model

Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.

Developing and evaluating approaches for utilising injury data to support product safety initiatives

With increasing concern about consumer product-related injuries in Australia, product safety regulators need evidence-based research to understand risks and patterns to inform their decision making. This study analysed paediatric injury data to identify and quantify product-related injuries in children to inform product safety prioritisation. This study provides information on novel techniques for interrogating health data to identify trends and patterns in product-related injuries to inform strategic directions in this growing area of concern.

A randomized controlled trial of a program to reduce adolescent road-related medically-treated injuries

Background Injury is the leading cause of adolescent death and injury around the road is a common source of adolescent injuries. Skills for Preventing Injury in Youth (SPIY) is a comprehensive program developed in Australia for early adolescents (term-long curriculum, including looking out for friends, first-aid training coupled with teacher school-connectedness professional development). Jessors’ Protection-Risk Framework guided the program approach focusing on building protective relationships. Method A randomized controlled trial with 35 schools was undertaken. Students completed surveys at baseline, six-months post-intervention and twelve-months post intervention. There were 1686 students (56% female) who completed the twelve-month survey, including the Extended-Adolescent Injury Checklist whereby students self-report on medically-treated injuries over the previous three-months (only road-related items are reported in this study; cycling, motorcycle riding, pedestrian, and riding as a passenger). Randomly selected SPIY classes also participated in focus groups and reported on perceptions of SPIY and injury risk behavior. Results As a check of randomization baseline differences of the variables were examined, with no significant differences between intervention and control groups. At the 12-month follow-up, there were fewer medically-treated injuries among the intervention students compared with the control group, particularly associated with being a passenger. The process evaluation revealed students perceived change in injury risk and risk behaviors. Conclusions While data analyses are continuing, the results indicate that the program seeking to encourage adolescents to look out for their friends, build connections to school and provide first aid skills training goes some way to reducing self-reported medically-treated injuries around the road.

Impact of real-time traffic characteristics on freeway crash occurrence: Systematic review and meta-analysis

The development of methods for real-time crash prediction as a function of current or recent traffic and roadway conditions is gaining increasing attention in the literature. Numerous studies have modeled the relationships between traffic characteristics and crash occurrence, and significant progress has been made. Given the accumulated evidence on this topic and the lack of an articulate summary of research status, challenges, and opportunities, there is an urgent need to scientifically review these studies and to synthesize the existing state-of-the-art knowledge. This paper addresses this need by undertaking a systematic literature review to identify current knowledge, challenges, and opportunities, and then conducts a meta-analysis of existing studies to provide a summary impact of traffic characteristics on crash occurrence. Sensitivity analyses were conducted to assess quality, publication bias, and outlier bias of the various studies; and the time intervals used to measure traffic characteristics were also considered. As a result of this comprehensive and systematic review, issues in study designs, traffic and crash data, and model development and validation are discussed. Outcomes of this study are intended to provide researchers focused on real-time crash prediction with greater insight into the modeling of this important but extremely challenging safety issue.

Evaluation of ANPR trials for traffic policing in Queensland. Report to the Queensland Police Service, State Traffic Support Branch

In response to the Travelsafe Committee Report No. 51 – report on the inquiry into Automatic Plate Recognition Technology – it was recommended that the Queensland Police Service continue to trial the deployment of ANPR technology for traffic enforcement work and to evaluate the road safety impacts and operational effectiveness of the technology. As such, the purpose of this report is to provide an independent evaluation of a trial of ANPR that was conducted by a project team within the State Traffic Support Branch of the Queensland Police Service (QPS) and provide recommendations as to the applicability and usability of the technology for use throughout Queensland...

Road operation phase sustainability indicator as a response to the climate change phenomena

Road infrastructure is a major contributor of greenhouse gas (GHG) around the world. Once constructed, a road becomes a part of a road network and is subjected to recurrent maintenance/rehabilitation activities. Studies to date are mostly aimed at the development of sustainability indicators that deal with the material and construction phases of a road when it is constructed. The operation phase is infrequently studied and there is a need for sustainability indicators to be developed relating to this phase to better understand the GHG emissions as a proper response to the climate change phenomena. During the operation phase, maintenance/rehabilitation activities are undertaken based on certain agreed intervention criteria that do not include environmental implications relating to the climate change aspect properly. Availability of appropriate indicators may, therefore, assist in sustainable road asset maintenance management. This paper presents the findings of a literature based study and has proposed a way forward to develop a key “road operation phase” environmental indicator, which can contribute to road operation phase carbon footprint management based on a comprehensive road life cycle system boundary model. The proposed indicator can address multiple aspects of high impact road operation life environmental components such as: pavement rolling resistance, albedo, material, traffic congestion and lighting, based on availability of relevant scientific knowledge. Development of the indicator to appropriate level would offset the impacts of these components significantly and contribute to sustainable road operation management.

Characterizing self-reported sleep disturbance after mild traumatic brain injury

Sleep disturbance after mild traumatic brain injury (mTBI) is commonly reported as debilitating and persistent. However, the nature of this disturbance is poorly understood. This study sought to characterize sleep after mTBI compared with a control group. A cross-sectional matched case control design was used. Thirty-three persons with recent mTBI (1–6 months ago) and 33 age, sex, and ethnicity matched controls completed established questionnaires of sleep quality, quantity, timing, and sleep-related daytime impairment. The mTBI participants were compared with an independent sample of close-matched controls (CMCs; n=33) to allow partial internal replication. Compared with controls, persons with mTBI reported significantly greater sleep disturbance, more severe insomnia symptoms, a longer duration of wake after sleep onset, and greater sleep-related impairment (all medium to large effects, Cohen's d>0.5). No differences were found in sleep quantity, timing, sleep onset latency, sleep efficiency, or daytime sleepiness. All findings except a measure of sleep timing (i.e., sleep midpoint) were replicated for CMCs. These results indicate a difference in the magnitude and nature of perceived sleep disturbance after mTBI compared with controls, where persons with mTBI report poorer sleep quality and greater sleep-related impairment. Sleep quantity and timing did not differ between the groups. These preliminary findings should guide the provision of clearer advice to patients about the aspects of their sleep that may change after mTBI and could inform treatment selection.

Size-resolved particle distribution and gaseous concentrations by real-world road tunnel measurement

Measurements of aerosol particle number size distributions (15-700 nm), CO and NOx were performed in a bus tunnel, Australia. Daily mean particle size distributions of mixed diesel/CNG (Compressed Natural Gas) buses traffic flow were determined in 4 consecutive measurement days. EFs (Emission Factors) of Particle size distribution of diesel buses and CNG buses were obtained by MLR (Multiple Linear Regression) methods, particle distributions of diesel buses and CNG buses were observed as single accumulation mode and nuclei-mode separately. Particle size distributions of mixed traffic flow were decomposed by two log-normal fitting curves for each 30 minutes interval mean scans, all the mix fleet PSD emission can be well fitted by the summation of two log-normal distribution curves, and these were composed of nuclei mode curve and accumulation curve, which were affirmed as the CNG buses and diesel buses PN emission curves respectively. Finally, particle size distributions of diesel buses and CNG buses were quantified by statistical whisker-box charts. For log-normal particle size distribution of diesel buses, accumulation mode diameters were 74.5～87.5nm, geometric standard deviations were 1.89～1.98. As to log-normal particle size distribution of CNG buses, nuclei-mode diameters were 21～24 nm, geometric standard deviations were 1.27～1.31.

Young and unaffected by road policing strategies: Using deterrence theory to explain provisional drivers' (non)compliance

Newly licenced drivers are disproportionately represented in traffic injuries and crash statistics. Despite the implementation of countermeasures designed to improve safety, such as graduated driver licencing (GDL) schemes, many young drivers do not comply with road rules. This study used a reconceptualised deterrence theory framework to investigate young drivers’ perceptions of the enforcement of road rules in general and those more specifically related to GDL. A total of 236 drivers aged 17–24 completed a questionnaire assessing their perceptions of various deterrence mechanisms (personal and vicarious) and their compliance with both GDL-specific and general road rules. Hierarchical multiple regressions conducted to explore noncompliant behaviour revealed that, contrary to theoretical expectations, neither personal nor vicarious punishment experiences affected compliance in the expected direction. Instead, the most influential factors contributing to noncompliance were licence type (P2) and, counterintuitively, having previously been exposed to enforcement. Parental enforcement was also significant in the prediction of transient rule violations, but not fixed rule violations or overall noncompliance. Findings are discussed in light of several possibilities, including an increase in violations due to more time spent on the road, an ‘emboldening effect’ noted in prior studies and possible conceptual constraints regarding the deterrence variables examined in this study.

The psychosocial purpose of driving and its relationship with the risky driving behaviour of young novice drivers

Background The overrepresentation of young drivers in road crashes, injuries and fatalities around the world has resulted in a breadth of injury prevention efforts including education, enforcement, engineering, and exposure control. Despite multifaceted intervention, the young driver problem remains a challenge for injury prevention researchers, practitioners and policy-makers. The intractable nature of young driver crash risks suggests that a deeper understanding of their car use – that is, the purpose of their driving – is required to inform the design of more effective young driver countermeasures. Aims This research examined the driving purpose reported by young drivers, including the relationship with self-reported risky driving behaviours including offences. Methods Young drivers with a Learner or Provisional licence participated in three online surveys (N1 = 656, 17–20 years; N2 = 1051, 17–20 years; N3 = 351, 17–21 years) as part of a larger state-wide project in Queensland, Australia. Results A driving purpose scale was developed (the PsychoSocial Purpose Driving Scale, PSPDS), revealing that young drivers drove for psychosocial reasons such as for a sense of freedom and to feel independent. Drivers who reported the greatest psychosocial purpose for driving were more likely to be male and to report more risky driving behaviours such as speeding. Drivers who deliberately avoided on-road police presence and reported a prior driving-related offence had significantly greater PSPDS scores, and higher reporting of psychosocial driving purposes was found over time as drivers transitioned from the supervised Learner licence phase to the independent Provisional (intermediate) licence phase. Discussion and conclusions The psychosocial needs met by driving suggest that effective intervention to prevent young driver injury requires further consideration of their driving purpose. Enforcement, education, and engineering efforts which consider the psychosocial purpose of the driving are likely to be more efficacious than those which presently do not. Road safety countermeasures could reduce the young driver’s exposure to risk through such mechanisms as encouraging the use of public transport.

Modelling collision potentials in Port Anchorages: Application of the Navigational Traffic Conflict Technique (NTCT)

Despite the extent of works done on modelling port water collisions, not much research effort has been devoted to modelling collisions at port anchorages. This paper aims to fill this important gap in literature by applying the Navigation Traffic Conflict Technique (NTCT) for measuring the collision potentials in anchorages and for examining the factors contributing to collisions. Grounding on the principles of the NTCT, a collision potential measurement model and a collision potential prediction model were developed. These models were illustrated by using vessel movement data of the anchorages in Singapore port waters. Results showed that the measured collision potentials are in close agreement with those perceived by harbour pilots. Higher collision potentials were found in anchorages attached to shoreline and international fairways, but not at those attached to confined water. Higher operating speeds, larger numbers of isolated danger marks and day conditions were associated with reduction in the collision potentials.

Real-time traffic state estimation in urban corridors from heterogeneous data

In recent years, rapid advances in information technology have led to various data collection systems which are enriching the sources of empirical data for use in transport systems. Currently, traffic data are collected through various sensors including loop detectors, probe vehicles, cell-phones, Bluetooth, video cameras, remote sensing and public transport smart cards. It has been argued that combining the complementary information from multiple sources will generally result in better accuracy, increased robustness and reduced ambiguity. Despite the fact that there have been substantial advances in data assimilation techniques to reconstruct and predict the traffic state from multiple data sources, such methods are generally data-driven and do not fully utilize the power of traffic models. Furthermore, the existing methods are still limited to freeway networks and are not yet applicable in the urban context due to the enhanced complexity of the flow behavior. The main traffic phenomena on urban links are generally caused by the boundary conditions at intersections, un-signalized or signalized, at which the switching of the traffic lights and the turning maneuvers of the road users lead to shock-wave phenomena that propagate upstream of the intersections. This paper develops a new model-based methodology to build up a real-time traffic prediction model for arterial corridors using data from multiple sources, particularly from loop detectors and partial observations from Bluetooth and GPS devices.

Pedestrian Crashes in Ethiopia: Identification of contributing factors through modelling of exposure and road environment variables

Pedestrian safety is a critical issue in Ethiopia. Reports show that 50 to 60% of traffic fatality victims in the country are pedestrians. The primary aim of this research was to examine the possible causes of and contributing factors to crashes with pedestrians in Ethiopia, and improve pedestrian safety by recommending possible countermeasures. The secondary aim was to develop appropriate pedestrian crash models for two-way two-lane rural roads and roundabouts in the capital city of Ethiopia. This research uses quantitative methods throughout the process of the investigation. The research has applied various statistical methods. The results of this research support the idea that geometric and operational features have significant influence on pedestrian safety and crashes. Accordingly, policies and strategies are needed to safeguard pedestrians in Ethiopia.

Somewhere between haste and delay... Investigating the interactions of road users and pedestrians in a dynamic rail level crossing environment

There are currently 23,500 level crossings in Australia, broadly divided into one of two categories: active level crossings which are fully automatic and have boom barriers, alarm bells, flashing lights, and pedestrian gates; and passive level crossings, which are not automatic and aim to control road and pedestrianised walkways solely with stop and give way signs. Active level crossings are considered to be the gold standard for transport ergonomics when grade separation (i.e. constructing an over- or underpass) is not viable. In Australia, the current strategy is to annually upgrade passive level crossings with active controls but active crossings are also associated with traffic congestion, largely as a result of extended closure times. The percentage of time level crossings are closed to road vehicles during peak periods increases with the rise in the frequency of train services. The popular perception appears to be that once a level crossing is upgraded, one is free to wipe their hands and consider the job done. However, there may also be environments where active protection is not enough, but where the setting may not justify the capital costs of grade separation. Indeed, the associated congestion and traffic delay could compromise safety by contributing to the risk taking behaviour by motorists and pedestrians. In these environments it is important to understand what human factor issues are present and ask the question of whether a one size fits all solution is indeed the most ergonomically sound solution for today’s transport needs.