Application of a Machine Learning-based Decision Support Tool to Improve an Injury Surveillance System Workflow

Potential for advances in data linkage and data science to support injury prevention research

The recent COVID-19 pandemic stimulated unprecedented linkage of datasets worldwide, and while injury is endemic rather than pandemic, there is much to be learned by the injury prevention community from the data science approaches taken to respond to the pandemic to support research into the primary, secondary and tertiary prevention of injuries. The use of routinely collected data to produce real-world evidence, as an alternative to clinical trials, has been gaining in popularity as the availability and quality of digital health platforms grow and the linkage landscape, and the analytics required to make best use of linked and unstructured data, is rapidly evolving. Capitalising on existing data sources, innovative linkage and advanced analytic approaches provides the opportunity to undertake novel injury prevention research and generate new knowledge, while avoiding data waste and additional burden to participants. We provide a tangible, but not exhaustive, list of examples showing the breadth and value of data linkage, along with the emerging capabilities of natural language processing techniques to enhance injury research. To optimise data science approaches to injury prevention, injury researchers in this area need to share methods, code, models and tools to improve consistence and efficiencies in this field. Increased collaboration between injury prevention researchers and data scientists working on population data linkage systems has much to offer this field of research.

Radiologists' perspectives on the workflow integration of an artificial intelligence-based computer-aided detection system: A qualitative study

In healthcare, artificial intelligence (AI) is expected to improve work processes, yet most research focuses on the technical features of AI rather than its real-world clinical implementation. To evaluate the implementation process of an AI-based computer-aided detection system (AI-CAD) for prostate MRI readings, we interviewed German radiologists in a pre-post design. We embedded our findings in the Model of Workflow Integration and the Technology Acceptance Model to analyze workflow effects, facilitators, and barriers. The most prominent barriers were: (i) a time delay in the work process, (ii) additional work steps to be taken, and (iii) an unstable performance of the AI-CAD. Most frequently named facilitators were (i) good self-organization, and (ii) good usability of the software. Our results underline the importance of a holistic approach to AI implementation considering the sociotechnical work system and provide valuable insights into key factors of the successful adoption of AI technologies in work systems.

External causes of emergency department presentations: A missing piece to understanding unintentional childhood injury in Australia

OBJECTIVE

To identify external causes of unintentional childhood injury presenting to Australian EDs.

METHODS

Six major paediatric hospitals in four Australian states supplied de-identified ED data for 2011-2017 on age, sex, attendance time/date, presenting problem, injury diagnosis, triage category and mode of separation. Three hospitals supplied data on external cause and intent of injury. A machine classifier tool was used to supplement the missing external cause coding in the remaining hospitals to enable the compilation of a standardised dataset for childhood injury causes analysis.

RESULTS

A total of 486 762 ED presentations for unintentional injury in children aged 0-14 years were analysed. The leading specified cause of ED presentations was low fall (35.0%) followed by struck/collision with an object (13.8%) with little sex difference observed. Males aged 10-14 years had higher rates of motorcycle, pedal cycle and fire/flame-related injury and lower rates of horse-related injury and drug/medicinal substance poisoning compared with females. The leading specified external cause resulting in hospitalisation was low fall (32.2%) followed by struck/collision with an object (11.1%). The injuries with the highest proportion of children being hospitalised were drownings (64.4%), pedestrian (53.4%), motorcycle (52.7%) and horse-related injuries (50.0%).

CONCLUSIONS

This is the first large-scale study since the 1980s to explore external causes of unintentional childhood injury presenting to Australian paediatric EDs. It demonstrates a hybrid human-machine learning approach to create a standardised database to overcome data deficiencies. The results supplement existing knowledge of hospitalised paediatric injury to better understand the causes of childhood injury by age and sex, which require health service utilisation.