Search

Objective: We analyzed the described resolutions of patient safety event reports related to health information technology to determine how healthcare systems responded to these events, recognizing that certain types of solutions such as training and education have a limited impact. Methods: A large database of over 1.7 million patient safety event reports was filtered to include those identified by the reporter as being related to health information technology. The resolution text was manually reviewed and coded into one or more of four categories: No Resolution, Training/Education, Policy, Information Technology-oriented solution. Results: Most events (64%) did not include a resolution. Of those that did, Training/Education was the most commonly reported single or component of a multi-pronged solution (55%), followed by Information Technology (45%). Only 59 events (6% of resolutions) described more than one method of resolution. Conclusion: Health information technology-related patient safety event resolutions most often described a solution that suggested additional training or education for healthcare staff, despite the recognized limitations of training and education in resolving these events. Few events suggested multiple resolution methods. Ensuring health information technology-related events are resolved and incorporate effective solutions should be a continued focus area for healthcare systems. [ABSTRACT FROM AUTHOR]

Objective: The objective of this paper was to identify health information technology (HIT) related events from patient safety event (PSE) report free-text descriptions. A difference-based scoring approach was used to prioritize and select model features. A feature-constraint model was developed and evaluated to support the analysis of PSE reports., Methods: 5287 PSE reports manually coded as likely or unlikely related to HIT were used to train unigram, bigram, and combined unigram-bigram logistic regression and support vector machine models using five-fold cross validation. A difference-based scoring approach was used to prioritize and select unigram and bigram features by their relative importance to likely and unlikely HIT reports. A held-out set of 2000 manually coded reports were used for testing., Results: Unigram models tended to perform better than bigram and combined models. A 300-unigram logistic regression had comparable classification performance to a 4030-unigram SVM model but with a faster relative run-time. The 300-unigram logistic regression model evaluated with the testing data had an AUC of 0.931 and a F1-score of 0.765., Discussion: A difference-based scoring, prioritization, and feature selection approach can be used to generate simplified models with high performance. A feature-constraint model may be more easily shared across healthcare organizations seeking to analyze their respective datasets and customized for local variations in PSE reporting practices., Conclusion: The feature-constraint model provides a method to identify HIT-related patient safety hazards using a method that is applicable across healthcare systems with variability in their PSE report structures., (Copyright © 2018 Elsevier Inc. All rights reserved.)