The use of narrative text for injury surveillance research : a systematic review

Objective: To summarise the extent to which narrative text fields in administrative health data are used to gather information about the event resulting in presentation to a health care provider for treatment of an injury, and to highlight best practise approaches to conducting narrative text interrogation for injury surveillance purposes.----- Design: Systematic review----- Data sources: Electronic databases searched included CINAHL, Google Scholar, Medline, Proquest, PubMed and PubMed Central.. Snowballing strategies were employed by searching the bibliographies of retrieved references to identify relevant associated articles.----- Selection criteria: Papers were selected if the study used a health-related database and if the study objectives were to a) use text field to identify injury cases or use text fields to extract additional information on injury circumstances not available from coded data or b) use text fields to assess accuracy of coded data fields for injury-related cases or c) describe methods/approaches for extracting injury information from text fields.----- Methods: The papers identified through the search were independently screened by two authors for inclusion, resulting in 41 papers selected for review. Due to heterogeneity between studies metaanalysis was not performed.----- Results: The majority of papers reviewed focused on describing injury epidemiology trends using coded data and text fields to supplement coded data (28 papers), with these studies demonstrating the value of text data for providing more specific information beyond what had been coded to enable case selection or provide circumstantial information. Caveats were expressed in terms of the consistency and completeness of recording of text information resulting in underestimates when using these data. Four coding validation papers were reviewed with these studies showing the utility of text data for validating and checking the accuracy of coded data. Seven studies (9 papers) described methods for interrogating injury text fields for systematic extraction of information, with a combination of manual and semi-automated methods used to refine and develop algorithms for extraction and classification of coded data from text. Quality assurance approaches to assessing the robustness of the methods for extracting text data was only discussed in 8 of the epidemiology papers, and 1 of the coding validation papers. All of the text interrogation methodology papers described systematic approaches to ensuring the quality of the approach.----- Conclusions: Manual review and coding approaches, text search methods, and statistical tools have been utilised to extract data from narrative text and translate it into useable, detailed injury event information. These techniques can and have been applied to administrative datasets to identify specific injury types and add value to previously coded injury datasets. Only a few studies thoroughly described the methods which were used for text mining and less than half of the studies which were reviewed used/described quality assurance methods for ensuring the robustness of the approach. New techniques utilising semi-automated computerised approaches and Bayesian/clustering statistical methods offer the potential to further develop and standardise the analysis of narrative text for injury surveillance.

Sources of coding discrepancies in injury morbidity data: Implications for injury surveillance

Objective: To examine the sources of coding discrepancy for injury morbidity data and explore the implications of these sources for injury surveillance.-------- Method: An on-site medical record review and recoding study was conducted for 4373 injury-related hospital admissions across Australia. Codes from the original dataset were compared to the recoded data to explore the reliability of coded data aand sources of discrepancy.---------- Results: The most common reason for differences in coding overall was assigning the case to a different external cause category with 8.5% assigned to a different category. Differences in the specificity of codes assigned within a category accounted for 7.8% of coder difference. Differences in intent assignment accounted for 3.7% of the differences in code assignment.---------- Conclusions: In the situation where 8 percent of cases are misclassified by major category, the setting of injury targets on the basis of extent of burden is a somewhat blunt instrument Monitoring the effect of prevention programs aimed at reducing risk factors is not possible in datasets with this level of misclassification error in injury cause subcategories. Future research is needed to build the evidence base around the quality and utility of the ICD classification system and application of use of this for injury surveillance in the hospital environment.

Quality of child abuse information in emergency department injury surveillance data : linking hospital and child welfare data

Emergency departments (EDs) are often the first point of contact with an abused child. Despite legal mandate, the reporting of definite or suspected abusive injury to child safety authorities by ED clinicians varies due to a number of factors including training, access to child safety professionals, departmental culture and a fear of ‘getting it wrong’. This study examined the quality of documentation and coding of child abuse captured by ED based injury surveillance data and ED medical records in the state of Queensland and the concordance of these data with child welfare records. A retrospective medical record review was used to examine the clinical documentation of almost 1000 injured children included in the Queensland Injury Surveillance Unit database (QISU) from 10 hospitals in urban and rural centres. Independent experts re-coded the records based on their review of the notes. A data linkage methodology was then used to link these records with records in the state government’s child welfare database. Cases were sampled from three sub-groups according to the surveillance intent codes: Maltreatment by parent, Undetermined and Unintentional injury. Only 0.1% of cases coded as unintentional injury were recoded to maltreatment by parent, while 1.2% of cases coded as maltreatment by parent were reclassified as unintentional and 5% of cases where the intent was undetermined by the triage nurse were recoded as maltreatment by parent. Quality of documentation varied across type of hospital (tertiary referral centre, children’s, urban, regional and remote). Concordance of health data with child welfare data varied across patient subgroups. Outcomes from this research will guide initiatives to improve the quality of intentional child injury surveillance systems.

Can SNOMED CT as implemented in New South Wales, Australia be used for road trauma injury surveillance in emergency departments?

The introduction of Systematized Nomenclature of Medicine - Clinical Terms (Snomed CT) for diagnosis coding in emergency departments (EDs) in New South Wales (NSW) has implications for injury surveillance abilities. This study aimed to assess the consequences of its introduction, as implemented as part of the ED information system in NSW, for identifying road trauma-related injuries in EDs. It involved a retrospective analysis of road trauma-related injuries identified in linked police, ED and mortality records during March 2007 to December 2009. Between 53.7% to 78.4% of all Snomed CT classifications in the principal provisional diagnosis field referred to the type of injury or symptom experienced by the individual. Of the road users identified by police, 3.2% of vehicle occupants, 6% of motorcyclists, 10.0% of pedal cyclists and 5.2% of pedestrians were identified using Snomed CT classifications in the principal provisional diagnosis field. The introduction of Snomed CT may provide flexible terminologies for clinicians. However, unless carefully implemented in information systems, its flexibility can lead to mismatches between the intention and actual use of defined data fields. Choices available in Snomed CT to indicate either symptoms, diagnoses, or injury mechanisms need to be controlled and these three concepts need to be retained in separate data fields to ensure a clear distinction between their classification in the ED.

A needle in a haystack : the use of routinely collected emergency department injury surveillance data to help identify physical child abuse

A retrospective, descriptive analysis of a sample of children under 18 years presenting to a hospital emergency department (ED) for treatment of an injury was conducted. The aim was to explore characteristics and identify differences between children assigned abuse codes and children assigned unintentional injury codes using an injury surveillance database. Only 0.1% of children had been assigned the abuse code and 3.9% a code indicating possible abuse. Children between 2-5 years formed the largest proportion of those coded to abuse. Superficial injury and bruising were the most common types of injury seen in children in the abuse group and the possible abuse group (26.9% and 18.8% respectively), whereas those with unintentional injury were most likely to present with open wounds (18.4%). This study demonstrates that routinely collected injury surveillance data can be a useful source of information for describing injury characteristics in children assigned abuse codes compared to those assigned no abuse codes.

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.

Infant product-related injuries: comparing specialised injury surveillance and routine emergency department data

- Objective To explore the potential for using a basic text search of routine emergency department data to identify product-related injury in infants and to compare the patterns from routine ED data and specialised injury surveillance data. - Methods Data was sourced from the Emergency Department Information System (EDIS) and the Queensland Injury Surveillance Unit (QISU) for all injured infants between 2009 and 2011. A basic text search was developed to identify the top five infant products in QISU. Sensitivity, specificity, and positive predictive value were calculated and a refined search was used with EDIS. Results were manually reviewed to assess validity. Descriptive analysis was conducted to examine patterns between datasets. - Results The basic text search for all products showed high sensitivity and specificity, and most searches showed high positive predictive value. EDIS patterns were similar to QISU patterns with strikingly similar month-of-age injury peaks, admission proportions and types of injuries. - Conclusions This study demonstrated a capacity to identify a sample of valid cases of product-related injuries for specified products using simple text searching of routine ED data. - Implications As the capacity for large datasets grows and the capability to reliably mine text improves, opportunities for expanded sources of injury surveillance data increase. This will ultimately assist stakeholders such as consumer product safety regulators and child safety advocates to appropriately target prevention initiatives.

Harnessing information from injury narrative in the 'big data' era: Understanding and applying machine learning for injury surveillance

Objective Vast amounts of injury narratives are collected daily and are available electronically in real time and have great potential for use in injury surveillance and evaluation. Machine learning algorithms have been developed to assist in identifying cases and classifying mechanisms leading to injury in a much timelier manner than is possible when relying on manual coding of narratives. The aim of this paper is to describe the background, growth, value, challenges and future directions of machine learning as applied to injury surveillance. Methods This paper reviews key aspects of machine learning using injury narratives, providing a case study to demonstrate an application to an established human-machine learning approach. Results The range of applications and utility of narrative text has increased greatly with advancements in computing techniques over time. Practical and feasible methods exist for semi-automatic classification of injury narratives which are accurate, efficient and meaningful. The human-machine learning approach described in the case study achieved high sensitivity and positive predictive value and reduced the need for human coding to less than one-third of cases in one large occupational injury database. Conclusion The last 20 years have seen a dramatic change in the potential for technological advancements in injury surveillance. Machine learning of ‘big injury narrative data’ opens up many possibilities for expanded sources of data which can provide more comprehensive, ongoing and timely surveillance to inform future injury prevention policy and practice.

The use of injury surveillance databases to identify emerging injury hazards

Among the many valuable uses of injury surveillance is the potential to alert health authorities and societies in general to emerging injury trends, facilitating earlier development of prevention measures. Other than road safety, to date, few attempts to forecast injury data have been made, although forecasts have been made of other public health issues. This may in part be due to the complex pattern of variance displayed by injury data. The profile of many injury types displays seasonality and diurnal variance, as well as stochastic variance. The authors undertook development of a simple model to forecast injury into the near term. In recognition of the large numbers of possible predictions, the variable nature of injury profiles and the diversity of dependent variables, it became apparent that manual forecasting was impractical. Therefore, it was decided to evaluate a commercially available forecasting software package for prediction accuracy against actual data for a set of predictions. Injury data for a 4-year period (1996 to 1999) were extracted from the Victorian Emergency Minimum Dataset and were used to develop forecasts for the year 2000, for which data was also held. The forecasts for 2000 were compared to the actual data for 2000 by independent t-tests, and the standard errors of the predictions were modelled by stepwise hierarchical multiple regression using the independent variables of the standard deviation, seasonality, mean monthly frequency and slope of the base data (R = 0.93, R² = 0.86, F_{(3, 27)} = 55.2, p < 0.0001). Significant contributions to the model included the SD (β = 1.60, p < 0.001), mean monthly frequency (β =  - 0.72, p < 0.002), and the seasonality of the data (β = 0.16, p < 0.02). It was concluded that injury data could be reliably forecast and that commercial software was adequate for the task. Variance in the data was found to be the most important determinant of prediction accuracy. Importantly, automated forecasting may provide a vehicle for identifying emerging trends.

Evaluation of minimum drinking age laws using the National Electronic Injury Surveillance System. Final report.

Mode of access: Internet.

Evaluation of state motorcycle helmet laws using the National Electronic Injury Surveillance System. Final report.

Mode of access: Internet.

Pesticide-related illness and injury surveillance : a how-to guide for state-based programs.

"October 2005."

Child injury in Brisbane South 1985-91: Implications for future injury surveillance

Specific childhood injury types are ranked by occurrence rate for mortality, hospital admission and emergency department attendance. Cases are drawn from the resident population of Brisbane South, 0-13 years of age, for the period 1 July 1985 to 30 June 1991. A total of 47,244 injuries, 7056 admissions and 99 deaths were analysed. The overall mortality rate was 12.6/100,000 per year (95% confidence interval (CI), 10.2-15.3), the overall admission rate was 911/100,000 per year (95% CI, 890-932) and the overall hospital attendance rate was 6013/100,000 per year (95% CI, 5958-6067). A fall was the most frequent injury mechanism for admissions and 65% of attendances involved injury in the child's own home. The surveillance data establish regional variation for childhood injury risk within Australia and identify an unexplained downward trend in head injury that requires further investigation. The future development of injury surveillance in Australia requires simplified coding which can be integrated into new computerized patient management information systems. Article in Journal of Paediatrics and Child Health 30(2):114-22 · May 1994

Feasibility of using health data sources to inform product safety surveillance in Queensland : a report for the Queensland Injury Prevention Council

This report provides an evaluation of the current available evidence-base for identification and surveillance of product-related injuries in children in Queensland. While the focal population was children in Queensland, the identification of information needs and data sources for product safety surveillance has applicability nationally for all age groups. The report firstly summarises the data needs of product safety regulators regarding product-related injury in children, describing the current sources of information informing product safety policy and practice, and documenting the priority product surveillance areas affecting children which have been a focus over recent years in Queensland. Health data sources in Queensland which have the potential to inform product safety surveillance initiatives were evaluated in terms of their ability to address the information needs of product safety regulators. Patterns in product-related injuries in children were analysed using routinely available health data to identify areas for future intervention, and the patterns in product-related injuries in children identified in health data were compared to those identified by product safety regulators. Recommendations were made for information system improvements and improved access to and utilisation of health data for more proactive approaches to product safety surveillance in the future.