Developing a similarity searching module for patient safety event reporting system using semantic similarity measures

A prototype of knowledge-based patient safety event reporting and learning system

Background

Patient falls, the most common safety events resulting in adverse patient outcomes, impose significant costs and have become a great burden to the healthcare community. Current patient fall reporting systems remain in the early stage that is far away from reaching the ultimate goal toward a safer healthcare. According to the Kirkpatrick model, the key challenge in reaction, learning, behavior and results is the realization of learning stage due to the lack of knowledge management, sharing and growing mechanism.

Methods

Based on the key contributing factors defined by AHRQ Common Formats 2.0, a hierarchical list of contributing factors for patient falls was established by expert review and discussion. Using the list as an infrastructure, we designed and developed a novel reporting system, where a strategy to identify contributing factors is intended to provide reporters knowledge support, in the form of similar cases and potential solutions. A survey containing two scenarios was conducted to evaluate the learning effect of our system.

Results

In both scenarios, potential solutions recommended by the system were annotated with correct contributing factors, and presented only when the corresponding factors were identified from the query report or selected by the user. The five experts show substantial consistency (Fleiss’ kappa > 0.6) and high agreement (ranging between fully agree and mostly agree) in the assessment of the three perspectives of the system, which verifies the effectiveness of the proposed knowledge support toward sharing and learning through the novel reporting system.

Conclusions

This study proposed a profile of contributing factors that could measure the similarity of patient safety events. Based on the profile, a knowledge-based reporting and learning system was developed to bridge the gap between surveillance, reporting, and retrospective analysis in the fall management circle. The system holds promise in improving event reporting toward better and safer healthcare.

An automated pipeline for analyzing medication event reports in clinical settings

BACKGROUND

Medication events in clinical settings are significant threats to patient safety. Analyzing and learning from the medication event reports is an important way to prevent the recurrence of these events. Currently, the analysis of medication event reports is ineffective and requires heavy workloads for clinicians. An automated pipeline is proposed to help clinicians deal with the accumulated reports, extract valuable information and generate feedback from the reports. Thus, the strategy of medication event prevention can be further developed based on the lessons learned.

METHODS

In order to build the automated pipeline, four classic machine learning classifiers (i.e., support vector machine, Naïve Bayes, random forest, and multi-layer perceptron) were compared to identify the event originating stages, event types, and event causes from the medication event reports. The precision, recall and F-1 measure were calculated to assess the performance of the classifiers. Further, a strategy to measure the similarity of medication event reports in our pipeline was established and evaluated by human subjects through a questionnaire.

RESULTS

We developed three classifiers to identify the medication event originating stages, event types and causes, respectively. For the event originating stages, a support vector machine classifier obtains the best performance with an F-1 measure of 0.792. For the event types, a support vector machine classifier exhibits the best performance with an F-1 measure of 0.758. And for the event causes, a random forest classifier reaches an F-1 measure of 0.925. The questionnaire results show that the similarity measurement is consistent with the domain experts in the task of identifying similar reports.

CONCLUSION

We developed and evaluated an automated pipeline that could identify three attributes from the medication event reports and calculate the similarity scores between the reports based on the attributes. The pipeline is expected to improve the efficiency of analyzing the medication event reports and to learn from the reports in a timely manner.

Introduction: the International Conference on Intelligent Biology and Medicine (ICIBM) 2016: special focus on medical informatics and big data

In this editorial, we first summarize the 2016 International Conference on Intelligent Biology and Medicine (ICIBM 2016) held on December 8-10, 2016 in Houston, Texas, USA, and then briefly introduce the ten research articles included in this supplement issue. At ICIBM 2016, a special theme, "Medical Informatics and Big Data," was dedicated to the recent advances of data science in the medical domain. After peer review, ten articles were selected for this special issue, covering topics such as Knowledge and Data Personalization, Social Media Applications to Healthcare, Clinical Natural Language Processing, Patient Safety Analyses, and Data Mining Using Electronic Health Records.