Clinical note creation, binning, and artificial intelligence

Posted on August 28, 2017 By Shawn Douglas Journal articles

This brief viewpoint article by Deliberato et al. looks at the state of note taking in electronic health records (EHRs) and proposes that EHR developers look to artificial intelligence (AI) components to improve note taking and other tasks in their software. Not only would AI improve note taking, they argue, but "AI would provide helpful suggestions to the user about what information is available and how it might influence the next course of action. AI could also function to emphasize or deemphasize certain elements of the record, based on previous results, external databases, and knowledge networks."

Predicting biomedical metadata in CEDAR: A study of Gene Expression Omnibus (GEO)

Posted on August 23, 2017 By Shawn Douglas Journal articles

In this 2017 paper published in the Journal of Biomedical Informatics, Panahiazar et al. "propose a novel metadata prediction framework to learn associations from existing metadata that can be used to predict metadata values." They tested their framework using experimental metadata contained in the Gene Expression Omnibus (GEO), an international public repository for community-contributed genomic datasets. The framework itself uses association rule mining (ARM) algorithms to predict structured metadata, and they found that indeed ARM is a strong tool towards that goal, though with several limitations. They conclude that with tools like theirs, the discovered "[p]redictive metadata can be used both prospectively to facilitate metadata authoring, and retrospectively to improve, correct and augment existing metadata in biomedical databases."

Rapid development of entity-based data models for bioinformatics with persistence object-oriented design and structured interfaces

Posted on August 16, 2017 By Shawn Douglas Journal articles

When it comes to bioinformatics data, databases are one of the more important the behind-the-scenes work horses. Yet inherent challenges of data heterogeneity and context-dependent interconnection in database design have driven the creation of specialized databases, which has, as a byproduct, caused additional problems in their creation. In this paper, Jerusalem College of Technology's Ezra Tsur proposes "an open-source framework for the curation of specialized databases," one that demonstrates "integration of the most relevant technologies to OO-based database design in a single framework" as well as extensibility to function with many other bioinformatics tools.

Bioinformatics education in pathology training: Current scope and future direction

Posted on August 9, 2017 By Shawn Douglas Journal articles

What are the links between pathology in the clinical setting and bioinformatics? Are residents in pathology gaining enough training in bioinformatics? And why should they learn about it in the first place? Clay and Fisher provide their take on these questions in this 2017 review paper published in Cancer Informatics. From their point-of-view, bioinformatics training is vital to practicing pathology "in the 'information age' of diagnostic medicine," and training should be taken more seriously at the residency and fellowship levels. They conclude that "in order for bioinformatics education to firmly integrate into the fabric of resident education, its importance and broad application to the practice of pathology must be recognized and given a prominent seat at the education table."