Using multiclass classification to automate the identification of patient safety incident reports by type and severity

作者：Wang Ying; Coiera Enrico; Runciman William; Magrabi Farah

来源：BMC Medical Informatics and Decision Making, 2017, 17(1): 84.

DOI：10.1186/s12911-017-0483-8

• Machine learning
• Patient safety
• Text mining
• Incident reporting
• Medical informatics

Background: Approximately 10% of admissions to acute-care hospitals are associated with an adverse event. Analysis of incident reports helps to understand how and why incidents occur and can inform policy and practice for safer care. Unfortunately our capacity to monitor and respond to incident reports in a timely manner is limited by the sheer volumes of data collected. In this study, we aim to evaluate the feasibility of using multiclass classification to automate the identification of patient safety incidents in hospitals.
Methods: Text based classifiers were applied to identify 10 incident types and 4 severity levels. Using the oneversus-one (OvsO) and one-versus-all (OvsA) ensemble strategies, we evaluated regularized logistic regression, linear support vector machine (SVM) and SVM with a radial-basis RBF) kernel. Classifiers were trained and tested with "balanced" datasets (n(-Type) = 2860, n(-SeverityLevel) = 1160) from a state-wide incident reporting system. Testing was also undertaken with imbalanced "stratified" datasets (n(-Type) = 6000, n(-SeverityLevel) = 5950) from the state-wide system and an independent hospital reporting system. Classifier performance was evaluated using a confusion matrix, as well as F-score, precision and recall.
Results: The most effective combination was a OvsO ensemble of binary SVM RBF classifiers with binary count feature extraction. For incident type, classifiers performed well on balanced and stratified datasets (F-score: 78.3, 73. 9%), but were worse on independent datasets (68.5%). Reports about falls, medications, pressure injury, aggression and blood products were identified with high recall and precision. "Documentation" was the hardest type to identify. For severity level, F-score for severity assessment code (SAC) 1 (extreme risk) was 87.3 and 64% for SAC4 (low risk) on balanced data. With stratified data, high recall was achieved for SAC1 (82.8-84%) but precision was poor (6.8-11.2%). High risk incidents (SAC2) were confused with medium risk incidents (SAC3).
Conclusions: Binary classifier ensembles appear to be a feasible method for identifying incidents by type and severity level. Automated identification should enable safety problems to be detected and addressed in a more timely manner. Multi-label classifiers may be necessary for reports that relate to more than one incident type.

• 出版日期2017-6-12