Automated identification of reports about patient safety incidents

Centre for health informatics

Research stream

Patient Safety Informatics

Project members

Professor Farah Magrabi
Dr Ying Wang

Former Project members

Dr Mei-Sing Ong
Dr Mi Ok Kim

Project contact

Professor Farah Magrabi
E: farah.magrabi@mq.edu.au

Project main description

Ten percent of admissions to Australian acute-care hospitals are associated with harm to patients or adverse events. The reporting of critical incidents by health professionals is now well established and the rate of reporting continues to increase worldwide. Current methods, which rely on retrospective manual review of incident reports, do not permit timely detection of safety problems and can no longer keep up with this growing volume of data. In the New South Wales public hospital system alone, more than 200,000 patient-safety incidents were reported in 2019.

We have developed AI-based tools to identify incident reports using text classification. Text classifiers use features such as word frequency and patterns to identify similar reports or classify reports against known categories. Our tools can identify both type and risk rating of incident reports, and generalise to 10 common incident classes and 4 severity levels. Recently using convolutional neural networks as a classifier, we improved F-scores by 12% compared to symbolic classifiers, partly due to improved performance on unbalanced data sets including rare event types. The next stage of this research is to integrate these AI-based tools in clinical workflows and investigate their impact on improving incident management processes.

References

1. Wang Y, Coiera E, Magrabi F. Can Unified Medical Language System-based semantic representation improve automated identification of patient safety incident reports by type and severity? J Am Med Inform Assoc. 2020.
2. Wang Y, Coiera E, Magrabi F. Using convolutional neural networks to identify patient safety incident reports by type and severity. J Am Med Inform Assoc. 2019;26(12):1600-8.
3. Wang Y, Coiera E, Runciman W, Magrabi F. Using multiclass classification to automate the identification of patient safety incident reports by type and severity. Bmc Med Inform Decis. 2017;17.
4. Wang Y, Coiera E, Runciman W, Magrabi F. Automating the Identification of Patient Safety Incident Reports Using Multi-Label Classification. MEDINFO 2017: Precision Healthcare Through Informatics: Proceedings of the 16th World Congress on Medical and Health Informatics. p. 609-13.
5. Chai KE, Anthony S, Coiera E, Magrabi F. Using statistical text classification to identify health information technology incidents. J Am Med Inform Assoc. 2013;20(5):980-5.
6. Ong MS, Magrabi F, Coiera E. Automated identification of extreme-risk events in clinical incident reports. J Am Med Inform Assoc. 2012;19(1e):e110-8.
7. Ong MS, Magrabi F, Coiera E. Automated categorisation of clinical incident reports using statistical text classification. Qual Saf Health Care. 2010;19(6):e55.

Project sponsors

• NHMRC Project APP1022964

Collaborative partners

• NSW Clinical Excellence Commission
• Australian Commission on Safety and Quality in Health Care

Related projects

• Classifying patient safety incidents involving digital health
• Automated detection of health information technology failures

Project status

Current

Centres related to this project

Centre for Health Informatics