Dataset Information

An automated pipeline for analyzing medication event reports in clinical settings.

ABSTRACT:

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.

SUBMITTER: Zhou S

PROVIDER: S-EPMC6284273 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An automated pipeline for analyzing medication event reports in clinical settings.

Zhou Sicheng S Kang Hong H Yao Bin B Gong Yang Y

BMC medical informatics and decision making 20181207 Suppl 5

<h4>Background</h4>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 ...[more]

PMID: 30526590

Similar Datasets

Project description:Phages are the most abundant biological entities on the planet, and they play an important role in controlling density, diversity, and network interactions among bacterial communities through predation and gene transfer. To date, a variety of bacteriophage identification tools have been developed that differ in the phage mining strategies used, input files requested, and results produced. However, new users attempting bacteriophage analysis can struggle to select the best methods and interpret the variety of results produced. Here, we present MetaPhage, a comprehensive reads-to-report pipeline that streamlines the use of multiple phage miners and generates an exhaustive report. The report both summarizes and visualizes the key findings and enables further exploration of key results via interactive filterable tables. The pipeline is implemented in Nextflow, a widely adopted workflow manager that enables an optimized parallelization of tasks in different locations, from local server to the cloud; this ensures reproducible results from containerized packages. MetaPhage is designed to enable scalability and reproducibility; also, it can be easily expanded to include new miners and methods as they are developed in this continuously growing field. MetaPhage is freely available under a GPL-3.0 license at https://github.com/MattiaPandolfoVR/MetaPhage. IMPORTANCE Bacteriophages (viruses that infect bacteria) are the most abundant biological entities on earth and are increasingly studied as members of the resident microbiota community in many environments, from oceans to soils and the human gut. Their identification is of great importance to better understand complex bacterial dynamics and microbial ecosystem function. A variety of metagenome bacteriophage identification tools have been developed that differ in the phage mining strategies used, input files requested, and results produced. To facilitate the management and the execution of such a complex workflow, we developed MetaPhage (MP), a comprehensive reads-to-report pipeline that streamlines the use of multiple phage miners and generates an exhaustive report. The pipeline is implemented in Nextflow, a widely adopted workflow manager that enables an optimized parallelization of tasks. MetaPhage is designed to enable scalability and reproducibility and offers an installation-free, dependency-free, and conflict-free workflow execution.

Project description:BACKGROUND:Little is known regarding the association between adverse events (AEs) and psychiatric medications administered to pregnant women in clinical trials during the pre-marketing period. This study analyzes reports of AE association with psychiatric medication administrated during pregnancy using post-marketing spontaneous reports of AE from the Japanese Adverse Drug Event Report (JADER) database and Food and Drug Administration Adverse Event Reporting System in the United States (FAERS-US). METHODS:We summarized AE reports of psychiatric medication administrated during pregnancy by comparing data obtained from JADER and FAERS-US databases with medication patterns determined as classes via latent class analysis. The odds ratios (ORs) of AE reports categorized into system organ classes in which each class was compared with those without psychiatric medications. RESULTS:The proportions of AE reports under psychiatric medication in pregnancy among all AE reports were 22.0% and 16.6% in JADER and FAERS-US, respectively. The 10,389 reports of psychiatric medication during pregnancy were classified into 11 classes. The proportion of patients receiving four or more psychiatric drugs in JADER was larger than that in FAERS-US. The maximum number of reports in combinations of AE and medication pattern in JADER was 169, for 'general disorders and administration site conditions' from the class of four or more medications (OR = 9.1), while that in FAERS-US was 1,654, for 'injury, poisoning, and procedural complications' from the class of single psychiatric medication (OR = 2.8). CONCLUSIONS:The main AE reports and associated AE differed depending on medication patterns in pregnant women taking psychiatric medication. This study may provide a prediction of AEs that are likely to be reported with each medication pattern. Our findings of the association between AE reports and medication patterns could help improve the administration of psychiatric medications during pregnancy, though further research on additional datasets is needed to clarify these results.

Dataset Information

An automated pipeline for analyzing medication event reports in clinical settings.

Background

Methods

Results

Conclusion

Publications

An automated pipeline for analyzing medication event reports in clinical settings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets