391 Application of a machine learning-based decision support tool in injury surveillance system. (20th November 2022)

• Record Type: Journal Article
• Authors: Catchpoole, Jesani; Nanda, Gaurav; Vallmuur, Kirsten; Nand, Goshad; Lehto, Mark
• Is Part Of: Injury prevention. Volume 28(2022)Supplement 2
• Page Start: A59
• Page End: A59
• Publication Date: 2022-11-20
• Subjects: Children's accidents -- Prevention -- Periodicals; Accidents -- Prevention -- Periodicals; 617.1
• DOI: 10.1136/injuryprev-2022-safety2022.175
• Languages: English
• ISSNs: 1353-8047

Abstract

Abstract : Background: Emergency department (ED)-based injury surveillance systems across many countries face resourcing challenges related to the validation and coding of data, which largely rely on manual coding. This presentation describes the evaluation of a machine learning-based Decision Support Tool (DST) to assist injury surveillance departments in the validation, coding and use of their data. Methods: Manually-coded Queensland Injury Surveillance Unit (QISU) data has been used to develop, train and iteratively refine a machine learning-based classifier to enable semi-automated coding of injury narrative data. This paper describes a trial implementation of the machine learning-based DST in the QISU workflow using a major pediatric hospital's ED data comparing outcomes in coding time and accuracy pre and post-implementation. Results: In total, 3174 injury records in February and March 2020 were analyzed. Statistical analysis shows a 10% reduction in manual coding time after introducing the DST. Concordance study comparing the kappa statistics from both DST-assisted and unassisted data shows increases in accuracy across three data fields; injury intent (85.4% unassisted vs. 94.5% assisted), external cause (88.8% unassisted vs. 91.8% assisted) and injury factor (89.3% unassisted vs. 92.9% assisted). The classifier was also used to produce a timely report monitoring injury patterns during the COVID-19 pandemic. Hence, it has the potential for near real-time surveillance of emerging hazards to inform public health responses. Conclusion: The integration of the DST into the QISU workflow shows benefits to the unit as it facilitates timely reporting and acts as a DST in the manual coding process.