Presentation
Evaluating Active Learning Strategies for Automated Classification of Patient Safety Event Reports in Hospitals
DescriptionPatient safety event (PSE) reports, documenting incidents that compromise patient safety, are fundamental for improving healthcare quality and safety. Accurate classification of these reports is crucial for analyzing trends, guiding interventions, and organizational learning. However, this process is labor-intensive due to the high volume and complex taxonomy of reports. Previous work has shown that machine learning (ML) can automate PSE report classification; however, its success depends on large manually-labeled datasets. This study leverages Active Learning (AL) strategies with human expertise to streamline PSE-report labeling. We utilize pool-based AL sampling to selectively query reports for human annotation, developing a robust dataset for training ML classifiers. Our experiments demonstrate that AL significantly outperforms random sampling in accuracy across various text representations, reducing the need for labeled samples by 25-70%. Based on these findings, we suggest that incorporating AL strategies into PSE-report labelling can effectively reduce manual workload while maintaining high classification accuracy.
Contributors
MASc Student
Assistant Professor | SED Lab Director
Event Type
Lecture
TimeTuesday, September 10th3:40pm - 4pm MST
LocationGrand Ballroom
Health Care